[
  {
    "id": "PMC10014736_multi",
    "image": [
      "images/PMC10014736-f1.png",
      "images/PMC10014736-f2.png",
      "images/PMC10014736-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The diagnostic yield of CGH and WES in neurodevelopmental disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Flowchart of the process followed in this study: 105 patients with age range from 1 month to 19 years diagnosed with specialist investigated through CGH and/or WES, 16% was the hit rate of CNVs. 82% of positive CNVs were classified as pathogenic and 17% were classified as likely pathogenic; 79 patients out of 105 were CNV negative and WES was subsequently requested for those patients. Twenty-four patients out of 79 were positive as pathogenic or likely pathogenic SNVs. The hit rate of SNVs was 30%; 79% were classified as pathogenic and 20% as likely pathogenic. A variant of uncertain significance was reported in 27 patients; 9 patients were classified to have CNVs and the rest 18 patients have SNVs. CGH, comparative hybridization; WES, whole exome sequencing; CNVs, copy number variations; SNVs, single-nucleotide variants.\n\nFigure 2: Figure 2. The percentage of different neurodevelopmental disorders among all 105 cases. Developmental delay was the most frequently observed formed 60%, while 5% of patients had epilepsy, 4% had intellectual disability, and 1% had learning disorders.\n\nFigure 3: Figure 3. Breakdown of the hit rate by test type. The number of solved cases (CNVs/SNVs) was divided by the total number of cases. Data represented as percentage. CNVs, copy number variations; SNVs, single-nucleotide variants."
      }
    ]
  },
  {
    "id": "PMC10092344_multi",
    "image": [
      "images/PMC10092344-f1.png",
      "images/PMC10092344-f2.png",
      "images/PMC10092344-f3.png",
      "images/PMC10092344-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Metabolomics analysis of antiquitin deficiency in cultured human cells and plasma: Relevance to pyridoxine‐dependent epilepsy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Overview of lysine degradation pathway. Dashed lines indicate proposed reactions for which no enzymes have yet been identified in human. The proposed structure of the Knoevenagel condensation product has only been shown in vitro. AASS α‐aminoadipic semialdehyde synthase; ATQ antiquitin (α‐aminoadipic semialdehyde dehydrogenase); CRYM/KR, μ‐crystallin/ketimine reductase; PIPOX pipecolic acid oxidase; P5CR pyrroline‐5‐carboxylase reductase\n\nFigure 2: Figure 2. Western blot analysis showing antiquitin and β‐Actin expression in control (untransfected) and CRISPR/Cas transfected colonies of neuronal progenitor cells (NPCs) following single cell expansion\n\nFigure 3: Figure 3. Overview of the folate cycle and methionine cycle. Metabolites that are significantly changed in any of the cell culture experiments are indicated by gray boxes. Pathways that require vitamin B6 as a cofactor 36 are indicated by dashed lines. 5‐methyltetrahydrofolate (5‐MTHF); 5,10‐methylene tetrahydrofolate (5,10 methylene THF); S‐adenosyl methionine (SAM); S‐adenosyl homocysteine (SAH)\n\nFigure 4: Figure 4. The gamma‐glutamyl cycle, adapted from Larsson A. (1990) Disorders of the Gamma Glutamyl Cycle. In: Fernandes J., Saudubray JM., Tada K. (eds) Inborn Metabolic Diseases. Springer, Berlin, Heidelberg. 37 Glutathione synthetase (GSS), gamma‐glutamyl transferase (GGT), gamma‐glutamylcyclotransferase (GGCT), 5‐oxoprolinase (OPLAH), glutamate cystein lygase (GCS)"
      }
    ]
  },
  {
    "id": "PMC10092852_multi",
    "image": [
      "images/PMC10092852-f1.png",
      "images/PMC10092852-f2.png",
      "images/PMC10092852-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Sex‐specific newborn screening for X‐linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The Dutch 4‐tier ALD newborn screening algorithm. In the Dutch 4‐tier ALD newborn screening algorithm, males with ALD are identified based on elevated C26:0‐LPC concentrations, the presence of one X‐chromosome and a variant in ABCD1, in heel prick dried bloodspots. The first tier consists of quantification of C26:0‐LPC using a high‐throughput flow injection analysis/tandem mass spectrometric (FIA–MS/MS) method. Samples that are above the cut‐off are screened in Tier 2 for the presence of one X‐chromosome. Next, C26:0‐LPC is re‐analyzed in Tier 3 using the more sensitive and specific high‐performance liquid chromatography (HPLC)‐MS/MS method. If C26:0‐LPC is above the cut‐off the ABCD1 gene is sequenced in Tier 4. Numbers in black and in parentheses indicate the number of samples analyzed in each tier. Numbers and percentages indicate the number and percentage of screen positive (green) and screen negative (red) samples in each tier.\n\nFigure 2: Figure 2. Correlation of C26:0‐LPC with FIA–MS/MS and HPLC–MS/MS. Correlation plot showing the correlation between the “putative” C26:0‐LPC (+isobaric interferent(s)) concentration measured in Tier 1 with FIA–MS/MS (X‐axis) and the (accurate) C26:0‐LPC concentration measured in Tier 3 with HPLC–MS/MS (Y‐axis). Blue circles are Tier 1 positive, but Tier 3 negative samples and orange triangles are both Tier 1 and Tier 3 positive samples. The dashed lines represent the cut‐offs for Tier 1 (≥0.32 mol/L) and Tier 3 (≥0.150 mol/L), respectively.\n\nFigure 3: Figure 3. Effect of age at blood sampling, gestational age and birth weight on C26:0‐LPC. (A–C) Correlation plots showing the correlation between age of the newborn at heel prick blood sampling (A), gestational age at birth (B), birth weight (C) and C26:0‐LPC concentrations by FIA–MS/MS. Blue dots indicate males and pink dots indicate females. (D) Correlation plot showing the correlation between gestational age at birth and birth weight for all boys in Tier 1 (blue), 249 boys in Tier 2 (green), 20 screen‐positive boys in Tier 3 (pink) and the four ALD newborns (yellow)."
      }
    ]
  },
  {
    "id": "PMC10120039_multi",
    "image": [
      "images/PMC10120039-f1.png",
      "images/PMC10120039-f2.png",
      "images/PMC10120039-f3.png",
      "images/PMC10120039-f4.png",
      "images/PMC10120039-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A genome-wide optical pooled screen reveals regulators of cellular antiviral responses\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A genome-wide optical pooled screen reveals regulators of pIRF3 translocation. (A) Genome-wide screening workflow. (B) Bright in situ signals enable imaging of phenotyping fluorescence signals that overlap with in situ SBS fluorescence signals. (C) Example images for each of the six immunofluorescence channels imaged in the genome-wide screen (DAPI was additionally imaged). (Scale bar, 20 μm.) (D) First six in situ sequencing cycles (of 12 total cycles) for the same group of cells shown in C. (E) Single-cell images from genome-wide screen show a decrease in IRF3 translocation in positive control genes. (F) Histograms of z-scored IRF3 translocation for positive control genes. Individual traces correspond to unique sgRNAs. (G) Hits from the genome-wide screen were assessed using a distinct library of 342 genes with six sgRNAs/gene in two secondary screens with different IRF3 detection assays. (H) Secondary translocation screens are well correlated with the primary screen for both antibody staining (r = 0.65, P = 2.6e−42) and reporter (r = 0.50, P = 5.22e−23). Blue dots indicate significant hits with decreased IRF3 translocation upon knockout, while red dots indicate genes with increased IRF3 translocation. (I) Volcano plot of secondary screen results for antibody staining with hits confirmed via secondary screening marked in blue or red. Two-sided P values were calculated as described in the Materials and Methods, corrected using the Benjamini–Hochberg procedure, and aggregated on the gene level using Fisher’s method.\n\nFigure 2: Figure 2. Analysis of combined hits from secondary screens (A). STRING clusters for hits showing decreased translocation using MCL inflation parameter 3 for clustering. Novel genes are in gray, and hits that did not cluster with other hits are listed by the black cluster marker. Table: Top significant GO/Reactome terms associated with each cluster among putative positive regulators. P values in A and B are computed via Enrichr (34) using the Fisher exact test and adjusted using the Benjamini–Hochberg procedure. (B) STRING clusters as described in (A) for combined hits that increased IRF3 translocation. Table contains top significant GO/Reactome terms associated with each cluster among putative negative regulators. (C) IRF3 translocation score plotted against SeV intensity scores for all genes in the antibody staining secondary screen. Black dots indicate nontargeting controls. (D) Example single-cell images for nontargeting control cells and the top gene for increased SeV or decreased SeV burden. For each gene/control, pIRF3 staining appears in green in the top row and SeV staining in cyan in the bottom row; each overlaid with DAPI nuclear staining. (E) Workflow for secondary screening to assess IRF3 reporter translocation differences upon either Sendai or VSV infection. (F) Comparison of per-gene translocation effects between VSV and Sendai virus infections; significance indicates genes with an FDR-adjusted P value <0.01.\n\nFigure 3: Figure 3. Deep learning and multidimensional analysis reveal regulators of IRF3, peroxisomes, and SeV. (A) Schematic showing extraction of features from representative single-cell crops where each channel is processed by either a pretrained neural network (Xception) or an autoencoder that yielded the example reconstructions shown on the right. (B) Both transfer learning and the autoencoder, as well as combined features, improved prediction of true IRF3 translocation hits based on secondary screen results compared to translocation alone using random forest models. (C) Eight of fourteen genes predicted to decrease translocation by combined deep learning features showed significantly decreased translocation in arrayed testing with two sgRNAs. *Adjusted P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001. Two-sided P values for C and F were calculated by computing the delta AUC for the feature of interest between cells in each well and nontargeting control cells (minimum n = 3,000); delta AUCs for all wells containing cells with an sgRNA of interest were then compared to nontargeting delta AUCs using a t test; P values were combined using Fisher’s method and corrected using the Benjamini–Hochberg procedure. (D) Mean peroxisome intensity delta AUC plotted against FDR-adjusted P values for genome-wide screen. Two-sided P values were calculated as described in the Materials and Methods and corrected using the Benjamini–Hochberg procedure. (E) Genes with reduced peroxisome intensity for targeted, transfer, autoencoder, or all three (13 genes in the Venn diagram in SI AppendixFig. S2C) features showed significant enrichment of GO:0005777 (Peroxisome), while genes showing increased peroxisome intensity based on autoencoder features, unlike targeted features, were enriched for GO:0006783 (heme biosynthesis). Enrichr P values for E and H are computed using the Fisher exact test and adjusted using the Benjamini–Hochberg procedure. (F) Three genes with predicted reduction in peroxisome intensity using two sgRNAs per gene showed decreased peroxisome intensity in arrayed testing. (Scale bar, 20 μm.) *Adjusted P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001. (G) Mean SeV intensity delta AUC plotted against FDR-adjusted P values for genome-wide screen. Two-sided P values were calculated as described in the Materials and Methods and corrected using the Benjamini–Hochberg procedure. (H) PHATE plot of genes derived from transfer learned features from the SeV channel with the top 30 genes that reduced SeV intensity marked in orange (nontargeting controls marked in black). (I) Same as (H) with the top 30 transfer learned perturbations most distant from nontargeting controls (black points) marked in purple. (J) Genes with reduced SeV intensity using targeted and autoencoder features were enriched for R-HSA-446203 (glycosylation) and R-HSA-4085001 (sialic acid metabolism), while genes showing reduced intensity in transfer learning showed stronger enrichment of features related to RNA processing (R-HSA-72203, pre-mRNA processing, and R-HSA-72163, mRNA splicing). (K) Images of single cells that scored in the 99th (Bottom) or first (Top) percentile for the SeV transfer learning feature that most differentiated cells with perturbations shown in purple in panel I from nontargeting control cells. (L) PHATE plot of genes in secondary screen clustered using Leiden clustering on autoencoder features from the IRF3 and RIG-I channels, with select genes that decreased IRF3 translocation upon knockout marked with blue text and genes that increased translocation marked in red text; cluster membership is denoted by marker color. (M) Same as L but using autoencoder features from the Sendai virus channel. (N) Same as L but using autoencoder features from the nuclei/DAPI channel. (O) Same as I but using autoencoder features from the peroxisome channel.\n\nFigure 4: Figure 4. Arrayed validation and RNA sequencing of IRF3 translocation hits. (A) IRF3 translocation in HeLa cells in response to SeV stimulation for the indicated genes. *Adjusted P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001 throughout. Two-sided P values for A–D were calculated by computing the delta AUC for the feature of interest between cells in each well and nontargeting control cells (minimum n = 3,000); delta AUCs for all wells containing cells with an sgRNA of interest were then compared to nontargeting delta AUCs using a t test; P values were combined using Fisher’s method and corrected using the Benjamini–Hochberg procedure. (B) RIG-I activation in HeLa cells in response to SeV stimulation for the indicated genes. (C) IRF3 translocation defects in U937 cells in response to SeV stimulation for the indicated genes. (D) RIG-I activation in HeLa cells in response to hpRNA stimulation for the indicated genes. (E) Normalized enrichment score (NES) computed via GSEA for ISGs (genes significantly enriched in nontargeting control cells with transfected hairpin RNA relative to unstimulated nontargeting control cells). P values were obtained from the gseapy package using 1,000 permutations over all gene sets considered and corrected using the Benjamini–Hochberg procedure. (F) Heatmaps showing z-scored gene expression for ISGs in (E) in response to hpRNA or SeV treatment for 6 or 15 h. (G) GSEA results show increased serine-type endopeptidase activity (TADA2B, MED16, and MED24), NOD-like receptor signaling (TADA2B), and lysosomal lumen components (MED16 and MED24). P values were obtained from the gseapy package using 1,000 permutations over all gene sets considered and corrected using the Benjamini–Hochberg procedure. (H). Enrichr results for genes that were decreased compared to positive controls DDX58 and MAVS in response to SeV stimulation (15 h) show significant enrichment of nucleolus components and small nucleolar RNAs for CAPN15, while ATP13A1 had a significant decrease in mitochondrial components. Enrichr P values are computed using the Fisher exact test and adjusted using the Benjamini–Hochberg procedure.\n\nFigure 5: Figure 5. MAVS is mislocalized in the absence of functional ATP13A1. (A) Overexpressed ATP13A1 rescues IRF3 translocation in ATP13A1 knockout HeLa cells. ****P < 0.0001. Two-sided P values for A, B, D, and F were calculated by computing the delta AUC for the feature of interest between cells in each well and nontargeting control cells (minimum n = 3,000); delta AUCs for all wells containing cells with an sgRNA of interest were then compared to nontargeting delta AUCs using a t test; P values were combined using Fisher’s method and corrected using the Benjamini–Hochberg procedure. (B) IRF3 translocation is not rescued by the addition of exogenous divalent cations in HeLa cells; cytokines added 24 h prior to SeV infection. ****P < 0.0001 (C) Diagram showing experimental setup for split-GFP experiment, where MAVS is overexpressed in HeLa cells along with either mitochondrial, peroxisomal, or ER GFP1-10. (D) In the presence of an ATP13A1 knockout, MAVS targeting to mitochondria and peroxisomes is reduced, while targeting to the ER is increased in HeLa cells. ****P < 0.0001. (E) In hTERT-immortalized primary BJ1 cells. (Scale bar, 20 μm.) (F) Quantification of experiment in (E). ****P < 0.0001 using a t test."
      }
    ]
  },
  {
    "id": "PMC10135575_multi",
    "image": [
      "images/PMC10135575-f1.png",
      "images/PMC10135575-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Redox Imbalance in Neurological Disorders in Adults and Children\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic representation of the alterations in redox mechanisms that can lead to numerous aberrant processes, and ultimately lead to neurological disorders.\n\nFigure 2: Figure 2. Schematic representation of mitochondrial damage mechanisms in some examples of pediatric-onset neurodegenerative diseases."
      }
    ]
  },
  {
    "id": "PMC10149961_multi",
    "image": [
      "images/PMC10149961-f1.png",
      "images/PMC10149961-f2.png",
      "images/PMC10149961-f3.png",
      "images/PMC10149961-f4.png",
      "images/PMC10149961-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal defects in microglial cells induce a disease-associated microglial signature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Differentially expressed genes (DEGs) between mutant and WT cells. (A) Comparative analysis of the sets of DEGs using Venn diagram (n = 3 for each genotype). The significant genes (number and percentage) were selected using a cut off adjusted p-value (DESeq2 Wald test with Benjamini and Hochberg p-value adjustment) lower than 0.05 and an absolute log2 FC higher than 0.58 (higher than 1.5-fold change in both directions) and are indicated in each group [Abcd1−/− (5,390 DEGs: 2765 up, 2,625 down), Abcd2−/− (5,842 DEGs: 2894 up, 2,948 down), Abcd1−/−Abcd2−/− (5,326 DEGs: 2675 up, 2,651 down), and Acox1−/− (5,068 DEGs, 2,369 up, 2,699 down)]. Numbers below correspond to the genes found in each group when the analysis was performed exclusively on upregulated genes (left) or downregulated genes (right). (B) Gene set enrichment analysis in mutant BV-2 cells presenting a selection of the main gene ontology biological process and KEGG pathway terms found in the 4 mutant genotypes. Functional annotation was obtained using DAVID online tools from upregulated and downregulated differentially expressed genes, respectively, in each mutant genotype. Gene count (green for GO Biological process and magenta for KEGG pathway) and Benjamini-corrected p-values are mentioned in color-coded form and available in a source data file. The number of genes contained in each term is indicated.\n\nFigure 2: Figure 2. Reprogramming of lipid metabolism in mutant cells. (A) Comparative analysis of the sets of DEGs using Venn diagram (n = 3 for each genotype). From the 1,190 genes associated with the GO term “Lipid metabolic process” and expressed in BV-2 cells, the significant genes (number and percentage) were selected using a cut off adjusted p-value (DESeq2 Wald test with Benjamini and Hochberg p-value adjustment) lower than 0.05 and an absolute log2 FC higher than 0.58 (higher than 1.5-fold change in both directions) and are indicated in each group [Abcd1−/− (348 DEGs: 177 up, 171 down), Abcd2−/− (419 DEGs: 242 up, 177 down), Abcd1−/−Abcd2−/− (350 DEGs: 165 up, 185 down), and Acox1−/− (366 DEGs: 184 up, 182 down)]. Numbers below correspond to the genes found in each group when the analysis was performed exclusively on upregulated genes (left) or downregulated genes (right). (B) Expression-based heatmap showing hierarchical clustering (left) using average linking and Pearson distances based on the 164 DEGs of the intersection between the 4 mutant genotypes (right). Each point corresponds to the Row Z-score collected from the means of the reads normalized and divided by median of transcripts length in kb from 3 independent cell samples for each genotype. (C) Biological processes and gene ontology pathways related to lipid metabolism corresponding to over and under-expressed genes in mutant BV-2 cells. Functional annotation was obtained using DAVID online tools from upregulated and downregulated DEGs in each mutant genotype. A selection of the most represented terms is presented with their number of associated genes mentioned in color-coded form (green for GO Biological process and magenta for KEGG pathway) and available in a source data file. The number of genes contained in each term is indicated.\n\nFigure 3: Figure 3. Cholesterol metabolism and membrane cholesterol in mutant cells. (A) Differential gene expression between mutant and WT BV-2 cells (n = 3 for each genotype) concerning the genes involved in lanosterol biosynthesis. The histogram represents the log2 FC for each gene based on RNA-seq data. * indicates an adjusted p-value lower than 0.05 (DESeq2 Wald test with Benjamini and Hochberg p-value adjustment). (B) Differential gene expression between mutant and WT BV-2 cells concerning the genes involved in cholesterol biosynthesis from lanosterol (Bloch and Kandutsch-Russell pathways). The histogram represents the estimated log2 FC for each gene based on RNA-seq data. * indicates an adjusted p-value lower than 0.05 (DESeq2 Wald test with Benjamini and Hochberg p-value adjustment). (C) Schematic representation of cholesterol biosynthesis. Enzymatic steps are represented by arrows and the associated genes are indicated. The peroxisomal location of the initial steps of cholesterol biosynthesis remains controversial especially the steps concerning Hmgcr, Mvk, Pmvk, and Mvd (green windows). (D) Western blotting analysis of DHCR4 from cell lysates of WT and mutant BV-2 cells. For densitometric analysis, see Supplementary Figure 3. Source data are available online for this figure. (E) Cholesterol precursors levels in WT and mutant BV-2 cells and their ratio. Gas chromatography mass spectrometry (GC–MS) analysis was performed from cellular homogenates (3 independent experiments). Histograms represent the mean levels of cholesterol precursors (ng/mg protein) with their respective standard deviation and their ratios. Statistical significance at p < 0.05* determined by Mann–Whitney test analysis is indicated. (F) Analysis of cholesterol accumulation in plasma membrane of WT and mutant BV-2 cells. Left panel, Filipin III binding kinetics in living cells recorded by flow cytometry during 256 s. Right panel, median fluorescence intensities calculated from the last minute filipin III binding kinetics (green gate on the left panel) were normalized as a fold of the BV2 WT fluorescence (n = 3 independent experiments).\n\nFigure 4: Figure 4. DEGs associated with lysosome and autophagy. (A) Comparative analysis of the sets of DEGs using Venn diagram (n = 3 for each genotype). From the 513 genes associated with lysosome and expressed in BV-2 cells, the significant genes (number and percentage) were selected using a cut off adjusted p-value lower than 0.05 (DESeq2 Wald test with Benjamini and Hochberg p-value adjustment) and an absolute log2 FC higher than 0.58 (higher than 1.5-fold change in both directions) and are indicated in each group [Abcd1−/− (214 DEGs: 158 up, 56 down), Abcd2−/− (244 DEGs: 192 up, 52 down), Abcd1−/−Abcd2−/− (194 DEGs: 130 up, 64 down), and Acox1−/− (217 DEGs: 161 up, 156 down)]. Numbers below correspond to the genes found in each group when the analysis was performed only on upregulated genes (left) and downregulated genes (right). (B) Expression-based heatmap showing hierarchical clustering (left) using average linking and Pearson distances based on the 118 DEGs of the intersection between the 4 mutant genotypes (right). Each point corresponds to the Row Z-score collected from the means of the reads normalized and divided by median of transcripts length in kb from 3 independent cell samples for each genotype. (C) Differential gene expression between mutant and WT BV-2 cells concerning the cathepsin genes. The histogram represents the estimated log2 FC for each gene based on RNA-seq data. For C and D, the bars represent significant differential expression (adjusted p-value lower than 0.05) except those indicated by #. (D) Differential gene expression between mutant and WT BV-2 cells concerning the V-ATPase genes. The histogram represents the log2 FC for each gene based on RNA-seq data.\n\nFigure 5: Figure 5. Lysosome and autophagy in mutant cells. (A) Western blotting analysis of proteins associated with lysosome [CTSB, CTSK, LAMP2, ATP6V0D2, ATP6V1B2, GRN (Progranulin), LGALS3 (Galectin 3)], autophagy (ATG13, LC3, P62, mMTOR, p-mTOR, ULK1, p-ULK1), lipid metabolism and microglial functions (APOE, CD36) from cell lysates of WT and mutant BV-2 cells. The histogram represents the LC3-II/LC3-I ratio, p-mTOR/mTOR ratio, and p-ULK1/ULK1 ratio obtained from densitometric analysis shown in Supplementary Figure 3. Source data are available online for this figure. (B) Transmission electron micrographs of WT (1) and Abcd1−/−Abcd2−/− (2, 3, 4) BV-2 cells illustrating the presence of autophagic figures in the mutant cells (bar = 500 nm). The arrows indicate diaminobenzidine-stained peroxisomes (1), a late autophagic compartment (2), an autophagosome engulfing mitochondria (3) and pexophagy (4). Although less numerous, similar observations were made in the Abcd1−/− and in the Acox1−/− cells but not in the Abcd2−/− cells."
      }
    ]
  },
  {
    "id": "PMC10154930_multi",
    "image": [
      "images/PMC10154930-f1.png",
      "images/PMC10154930-f2.png",
      "images/PMC10154930-f3.png",
      "images/PMC10154930-f4.png",
      "images/PMC10154930-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"ACOX-driven peroxisomal heterogeneity and functional compartmentalization in brown adipocytes of hypothyroid rats\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Protein expression of ACOX1 72 kDa (a), ACOX1 50 kDa (b), and ACOX3 (c) in rat BAT in control (black bars) and hypothyroid groups (grey bars) treated with methimazole for 7 (M7), 15 (M15) and 21 (M21) days. ACOX protein levels are expressed as a percentage of the control (set at 100%). Representative Western blot of three independent trials are shown (d). Data are represented as mean ± s.e.m. **p < 0.01; ***p < 0.001.\n\nFigure 2: Figure 2. Immunohistochemical labelling of ACOX1 (a1–a16) and ACOX3 (b1–b16) in serial paraffin sections of BAT of euthyroid (a1–a4, b1–b4) and hypothyroid groups treated with methimazole for 7 (a5–a8, b5–b8), 15 (a9–a12, b9–b12) and 21 (a13–a16, b13–b16) days, respectively. Ellipse marked heterogeneous expression of ACOX1 and ACOX3 in different brown adipocytes within a tissue (Harlequin effect). Scale bars: a13, b13, 100 µm; a14, b14, 50 µm; a16, b16, 20 µm.\n\nFigure 3: Figure 3. Immunogold labelling of ACOX1 and ACOX3 on ultrathin BAT sections with pre-stained peroxisomes (using DAB). Labelled peroxisomes from euthyroid control (a1, a2) and hypothyroid groups treated for 7 (M7, b1, b2), 15 (M15, c1, c2) and 21 days (M21, d1, d2) are indicated by colours: single ACOX1-positive peroxisomes, yellow; single ACOX3-positive peroxisomes, blue; double ACOX1/ACOX3-positive peroxisomes, red. In addition, positive (renal cortex cell, c1, inset pc) and negative (brown adipocytes, d1, inset nc) controls are shown. Mitochondria (MTH); lipid body (LB); endoplasmic reticulum (*); immunonegative peroxisome (not contain any ACOX isoform, ►). Size of gold particles: ACOX1, 20 nm; ACOX3, 10 nm. Scale bars 1 µm. Magnification for all electron micrographs 17 000× and all insets 28 000×.\n\nFigure 4: Figure 4. Distribution of: (a) single ACOX1-positive and double ACOX1/ACOX3-positive, and (b) single ACOX3-positive and double ACOX1/ACOX3-positive peroxisomes localized closely adjacent to lipid bodies (LB), mitochondria (MTH) and to mitochondria and lipid bodies together (MTH/LB) in brown adipocytes, within euthyroid control (C) and hypothyroid groups (M7, M15, M21). Bars represent the absolute number of single or double immunopositive peroxisomes per group.\n\nFigure 5: Figure 5. Distribution and representative electron micrographs of: (a,c,d) single ACOX1-positive (yellow) and double ACOX1/ACOX3-positive (red) peroxisome, and (b,c,d) single ACOX3-positive (blue) and double ACOX1/ACOX3-positive (red) peroxisomes localized closely adjacent to the endoplasmic reticulum (ER, green) and in the cytoplasm (CYT), in brown adipocytes within euthyroid control (C) and hypothyroid groups (M7, M15, M21). Bars represent the absolute number of single or double immunopositive peroxisomes per group (a,b). Magnification for all electron micrographs 17 000×. Scale bars 1 µm."
      }
    ]
  },
  {
    "id": "PMC10154978_multi",
    "image": [
      "images/PMC10154978-f1.png",
      "images/PMC10154978-f2.png",
      "images/PMC10154978-f3.png",
      "images/PMC10154978-f4.png",
      "images/PMC10154978-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The origin of long-chain fatty acids required for de novo ether lipid/plasmalogen synthesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The relative abundance of ether phospholipids with an odd number of side-chain carbons after the incubation of cells with 1-heptadecanol. A: Profiles of phosphatidylethanolamine (PE) and phosphatidylcholine (PC) ether lipids in wild-type and ΔPEX1 HeLa cells. Cells were cultured with (black bars) or without (white bars) 1-heptadecanol. Ether phospholipids with side chains comprising a total of 36–40 carbon atoms and a different number of double bonds (increases from left to right) are presented. The results are shown as mean ± standard deviation (n = 2). B, C, Time-dependent formation of PE(O-39:7) and PC(O-37:4) in wild-type or ΔPEX1 HeLa cells after incubation with 1-heptadecanol. The results are shown as mean ± standard deviation (n = 3). D, E, Ether phospholipid synthesis from 1-heptadecanol in wild-type, ΔPEX1, ΔFAR1, ΔPEX7, and ΔAGPS HeLa cells. The results are shown as individual values and mean ± standard deviation (n = 2, three different clones are plotted with different symbols). One-way ANOVA with Dunnett’s multiple comparisons test was performed to determine if differences are significant when compared with the wild-type cells. Relative abundance of lipids (arbitrary units) is defined as relative to the corresponding internal standards added prior to lipid extraction (see Materials and Methods section). The de novo ether lipid synthesis of PE(O-39:7) or PC(O-37:4) was calculated as an increase in the relative abundance after 1-heptadecanol treatment (arbitrary units).\n\nFigure 2: Figure 2. Identification of homologous genes expressed in wild-type (black) or peroxisome-deficient ΔPEX1 (red) HeLa cells. mRNA abundance (expressed as number of specific transcripts per million transcripts, TPM (24)) of peroxisomal ATP-binding cassette transporters, acyl-CoA oxidases, bifunctional proteins, and fatty acyl-CoA reductases is presented. The results are shown as individual values of three experiments and mean ± standard deviation (n = 3).\n\nFigure 3: Figure 3. Loss of ABCD transporters or peroxisomal beta-oxidation enzymes causes a decrease in ether phospholipid synthesis in HeLa cells. A: 1-[14C] hexacosanoic acid beta-oxidation activity in wild-type, ΔABCD1, ΔABCD3, ΔABCD1ΔABCD3, ΔPEX1, ΔACOX1, or ΔHSD17B4 cells. The results are shown as individual values and mean ± standard deviation. To determine if differences are significant, one-way ANOVA with Tukey’s multiple comparisons test or with Dunnett’s multiple comparisons test when compared with the wild-type cells was performed. Nonsignificant differences are marked as “ns.” B, C, The de novo ether lipid synthesis of PE(O-39:7) or PC(O-37:4) was calculated as an increase in the relative abundance (arbitrary units) (see Materials and Methods section) after 1-heptadecanol treatment. The results are shown as individual values and mean ± standard deviation (n = 2, three different clones are plotted with different symbols). One-way ANOVA with Dunnett’s multiple comparisons test was performed to determine if differences are significant when compared with the wild-type cells.\n\nFigure 4: Figure 4. Peroxisomal beta-oxidation supplies long-chain acyl-CoA for GNPAT. (A) Wild-type or ΔPEX1 cells were incubated with 10 μM or 30 μM of deuterium (D)-labeled D3-docosanoic acid. The amount of produced D3-labeled hexadecanoic (circle), octadecanoic (square), and eicosanoic (triangle) acids was measured after incubation for the indicated amount of time. The results are shown as mean values ± standard deviation (n = 3). (B–C) Loss of peroxisomal beta-oxidation in ΔABCD3 cells leads to a decrease in ether lipid synthesis. The de novo ether lipid synthesis of PE(O-39:7) or PC(O-37:4) was calculated as an increase in the relative abundance (arbitrary units) (see Materials and Methods section) after 1-heptadecanol treatment. The results are shown as individual values and mean ± standard deviation (n = 3, different clones are plotted with different symbols). To determine if differences are significant, one-way ANOVA with Tukey’s multiple comparisons test or with Dunnett’s multiple comparisons test when compared with the wild-type cells was performed.\n\nFigure 5: Figure 5. ER-localized ether phospholipid synthesis steps are not affected by peroxisomal beta-oxidation deficiency. Wild-type, ΔHSD17B4, ΔFAR1, ΔAGPS, ΔABCD3, or ΔABCD1ΔABCD3 cells were cultured with or without 20 μM of batyl alcohol (1-O-octadecyl-rac-glycerol) for 24 h. The relative abundance of PE(O-40:7) and PC(O-40:6) endogenous (left) and de novo synthesized from batyl alcohol (right) is presented. Relative abundance of lipids is defined as relative to the corresponding internal standards added prior to lipid extraction (arbitrary units) (see Materials and Methods section). The de novo ether lipid synthesis of PE(O-40:7) or PC(O-40:6) was calculated as an increase in the relative abundance after batyl alcohol treatment (arbitrary units). The results are shown as individual values and mean ± standard deviation (n = 3). To determine if differences are significant, one-way ANOVA with Tukey’s multiple comparisons test or with Dunnett’s multiple comparisons test when compared with the wild-type cells was performed."
      }
    ]
  },
  {
    "id": "PMC10154978_multi_2",
    "image": [
      "images/PMC10154978-f6.png",
      "images/PMC10154978-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The origin of long-chain fatty acids required for de novo ether lipid/plasmalogen synthesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Supplementation of hexadecanoic acid rescues the de novo ether lipid synthesis in beta-oxidation-deficient cells. HeLa cells were cultured with 1-heptadecanol and in addition with or without hexadecanoic acid (100 μM), as indicated. The de novo ether lipid synthesis of PE(O-39:7) (A) or PC(O-37:4) (B) was calculated as an increase in the relative abundance (arbitrary units) (see Materials and Methods section) after 1-heptadecanol treatment. The results are shown as individual values and mean ± standard deviation (n = 3). To determine if differences are significant, one-way ANOVA with Tukey’s multiple comparisons test or with Dunnett’s multiple comparisons test when compared with the wild-type cells was performed.\n\nFigure 7: Figure 7. Peroxisomal ABCD transporters can import long-chain fatty acids used in de novo ether lipid synthesis. ABCD1, ABCD2, or ABCD3 was expressed in ΔABCD1ΔABCD3 cells (A–C) or ΔABCD3ΔACOX1 cells (D–F). Total cell lysates containing equal amounts of protein were processed by Western blotting with specified antibodies against ABCD1 (A, D), ABCD2 (B, E), or ABCD3 (C, F). The arrows mark specific immune-reactive bands. G: Wild-type, ΔPEX1, ΔABCD1ΔABCD3, or ΔABCD1ΔABCD3 HeLa cells expressing one of the ABCD transporters were incubated with 30 μM of D3-docosanoic acid for 24 h. The amount of produced D3-labeled octadecanoic acid was measured. Results are shown as mean values ± standard deviation (n=3, different clones are plotted with different symbols). H–I, Wild-type, ΔABCD1ΔABCD3, ΔABCD3ΔACOX1, or ΔABCD3ΔACOX1 cells after expression of one of the ABCD transporters were cultured with 1-heptadecanol and in addition with or without hexadecanoic acid (100 μM), as indicated. The de novo ether lipid synthesis of PE(O-39:7) or PC(O-37:4) was calculated as an increase in the relative abundance (arbitrary units) (see Materials and Methods section) after 1-heptadecanol treatment. The results are shown as individual values and mean ± standard deviation (n = 2). To determine if differences are significant, one-way ANOVA with Tukey’s multiple comparisons test or with Dunnett’s multiple comparisons test when compared with the wild-type cells was performed."
      }
    ]
  },
  {
    "id": "PMC10171005_multi",
    "image": [
      "images/PMC10171005-f1.png",
      "images/PMC10171005-f2.png",
      "images/PMC10171005-f3.png",
      "images/PMC10171005-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Prevalence, Clinic-Etiological Spectrum and Outcome of Pediatric Metabolic Epilepsy – A Single Centre Experience\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (a and b) T2 axial Magnetic Resonance Imaging shows Bats wing appearance, widened sylvian fissure with poor operculisation in a child with Glutaric aciduria type 1. (c and d). T2 axial MR image showing hyperintense globus pallidi and midbrain with marked diffusion restriction in Maple Syrup Urine Disease. (e) T2 axial MR imaging showing subcortical white matter hyperintensity with sparing of periventricular white matter in a child with L2 hydroxy glutaric aciduria. (f) MR imaging axial FLAIR sequence showing symmetrical periventricular white matter hyperintensity typical of metachromatic leukodystrophy. (g) T2 axial MR image shows periventricular white matter hyperintensity in posterior regions in a child with Krabbe disease. (h) MR contrast image depicting peri ventricular white matter hyperintensity in the posterior region with contrast enhancement characteristic of adrenoleukodystrophy. (i) MR axial FLAIR image showing multicystic encephalomalacia in a child with molybdenum cofactor deficiency\n\nFigure 2: Figure 2. (a) T2 axial Magnetic Resonance Imaging shows bilateral globus pallidi involvement in methyl malonic acidemia. (b) T2 axial MR image showing bilateral caudate and putamen involvement in a child with propionic acidemia. (c) T2 axial MR image shows bilateral caudate and putamen involvement in a child with biotin responsive basal ganglia disease. (d) MR diffusion weighted imaging sequence showing diffusion restriction in bilateral basal ganglia and thalami. (e) MR diffusion weighted imaging sequence showing diffusion restriction in posterior limbs of both internal capsules. (f) T2 axial Magnetic Resonance Imaging shows hypomyelination in a child with gangliosidosis. (g) MR saggital FLAIR sequence depicting dysgenesis of corpus callosum in a child with pyridoxin dependency. (h) T2 coronal Magnetic Resonance Image showing cerebral and cerebellar atrophy in neuronal ceroid lipofuscinosis\n\nFigure 3: Figure 3. (a) Magnetic Resonance Spectroscopy showing lactate peak in a child with mitochondrial disorder. (b) MRS depicting absence of creatine peak in a child with Guanidino Acetate Methyl Transferase (GAMT) deficiency —a cerebral creatine deficiency disorder. (c) Normal MRS for comparison\n\nFigure 4: Figure 4. An approach to children with suspected metabolic epilepsy"
      }
    ]
  },
  {
    "id": "PMC10186734_multi",
    "image": [
      "images/PMC10186734-f1.png",
      "images/PMC10186734-f2.png",
      "images/PMC10186734-f3.png",
      "images/PMC10186734-f4.png",
      "images/PMC10186734-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Multivariate analysis and model building for classifying patients in the peroxisomal disorders X-linked adrenoleukodystrophy and Zellweger syndrome in Chinese pediatric patients\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Unsupervised multivariate analysis of patient targeted metabolite panel data. (a) t-SNE visualization of 16-features in patient samples for the ZS (yellow), X-ALD (dark blue), DDE (red), and control (black) groups; (b,c) PCA analysis of targeted metabolite panel data in healthy controls, non-PD neurological patients (DDE), X-linked adrenoleukodystrophy (X-ALD), and Zellweger syndrome (ZS) patients. Score plots along the 3 principal components are shown.\n\nFigure 2: Figure 2. Assessing exploratory PLS-DA model performance and evaluating latent component and features to retain for sparse PLS-DA modeling. (a, c, e) Assessing PLS-DA model performance in the 4-class setting (Control vs. DDE vs. X-ALD vs. ZS) and the 2-class setting (X-ALD vs. ZDC; ZS vs. XDC) and selection of distance metric and number of latent components. Repeated stratified cross-validation (100 × 5–fold CV) is used to evaluate the PLS-DA classification performance (measured by balanced error rate) for each prediction distance (max.dist, centroids.dist, and mahalanobis.dist). The balanced error rate appears to decrease negligibly after four latent components in the 4-class setting, and the balanced error rate reaches minimal value in 2-class setting with 1 latent component. (b) Cross-validation and error evaluation of the PLS-DA model in 4-class setting with 4 latent components and all 16 features. Optimal, error minimizing set of features per component are indicated with a diamond. Yellow diamond points to a 3-latent component model with 1, 15, and 1 retained feature(s) per latent components LC1, LC2, and LC3 respectively. (d) Cross-validation and error evaluation of the PLS-DA model in X-ALD vs. ZDC 2-class setting with 1 latent component and all 16 features. blue diamond points to a 1 latent component model with 8 retained features. (f) Cross-validation and error evaluation of the PLS-DA model in ZS vs. XDC 2-class setting with 1 latent component and all 16 features. Blue diamond points to a 1 latent component model with 15 retained features\n\nFigure 3: Figure 3. Sparse PLS-DA model 3LC-1-15-1 (4-class setting). (a1-2): Sample plots of the targeted metabolite panel data after a parsimonious PLS-DA model was operated on the data, depicting the patient samples with the confidence ellipses for the class labels. (b1-3) One-vs.-Others ROC curves assessing the classification performance of the PLS-DA model with 3 latent components and 1, 15, and 1 feature(s) per component (c). Feature stability per component evaluation in 5-fold – 100x cross validation\n\nFigure 4: Figure 4. Sparse PLS-DA models in the 2-class settings. (a). ROC curve assessing the classification performance of the PLS-DA model with 1 latent components and 8 features in the X-ALD vs. ZDC 2-class setting. (b). Feature stability evaluation in 5-fold – 100x cross validation in the X-ALD vs. ZDC 2-class setting. (c). ROC curve assessing the classification performance of the sparse PLS-DA model with 1 latent component and 15 features in the ZS vs. XDC 2-class setting. (d). Feature stability per in 5-fold – 100x cross validation in the ZS vs. XDC 2-class setting\n\nFigure 5: Figure 5. PLS-DA VIP model in the 4-class setting. (a1-2) Sample plots after the PLS-DA model with the VIP features was operated on the data, depicting the patient samples with the confidence ellipses for the class labels (b1-3) One-vs.-Others ROC curves assessing the classification performance of the PLS-DA model with 3 Latent Components and VIP features"
      }
    ]
  },
  {
    "id": "PMC10226518_multi",
    "image": [
      "images/PMC10226518-f1.png",
      "images/PMC10226518-f2.png",
      "images/PMC10226518-f3.png",
      "images/PMC10226518-f4.png",
      "images/PMC10226518-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Transcriptomic characterization of Lonrf1 at the single-cell level under pathophysiological conditions\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Lonrf1 is ubiquitously expressed in mouse tissues. (A) Structure of LONRF proteins from Mus musculus (mouse) and Homo sapiens (human). Domain structures are indicated. TPR is a protein–protein interaction domain, the RING finger is a domain that binds ubiquitination enzymes and their substrates and functions as a ligase, and the LonSB is associated with the turnover of misfolded or denatured proteins. (B) ProteoStat staining of HCA2 cells treated with (MG132) or without (mock) MG132 (5 mM) for 12 h. Representative images (scale bar: 50 mm) and quantifications (%) are shown (left panels). ProteoStat staining of HCA2 cells treated with (Senescence) or without (Untreated) doxorubicin for 24 h and then with BI2536 for 48 h. (right panels). Green: ProteoStat, blue: Hoechst. (C) qPCR analysis with the indicated primers using a panel of RNAs from mouse tissues. The relative expression of Lonrf1 to Gapdh is shown. Data are presented as mean ± SEM of independent experiments. n = 3\n\nFigure 2: Figure 2. scRNA analysis of Lonrf1 in liver from the Tabula Muris dataset. (A) UMAP visualization showing cell types in the Tabula Muris liver scRNA dataset containing 6,480 transcriptomes, including B cell, Kupffer cell, NK cell, liver sinusoidal endothelial cell (LSEC), HSC, hepatocyte, ML and PDC. (B) UMAP visualization showing the age of the mouse sample. (C) UMAP visualization showing the distribution of Lonrf1high and Lonrf1low cells in scRNA dataset. The threshold of Lonrf1-normalized UMI count used to determine high and low was 0.2. (D) Line graph showing the age-dependent changes in the percentage of Lonrf1high cells in each cell type. (E) Violin plot showing the Lonrf1 expression in each cell type. The expression level is represented by normalized UMI counts. (F) Violin plot showing the Lonrf1 expression in each age of the samples in all cell types. (G) Volcano plot showing the DEGs between Lonrf1high and Lonrf1low Kupffer cells in all the time points of mice. DEGs were identified by FDR < 0.05. Orange dots: significantly up-regulated or down-regulated DEGs. (H) Dot plot showing the top 30 enriched GO terms of up-regulated DEGs in Lonrf1high vs. Lonrf1low Kupffer cells. GO terms were identified with adjusted P-value<0.05 through B-H method. (I) Dot plot showing the top 30 enriched GO terms of downregulated DEGs in Lonrf1high compared with Lonrf1low Kupffer cells.\n\nFigure 3: Figure 3. scRNA analysis of Lonrf1 in the liver of 7-month-old p16-Tom mice. (A) UMAP visualization (upper-left panel) showing cell types in liver from 7-month-old p16-Tom mice dataset containing 5199 transcriptomes, including LSEC, macrophage (Mf), Kupffer cell, B cell, T cell, and monocyte. Violin plot showing the expression levels of cell type markers in each cell type (lower-left panel). The number of cells in each group is shown in the table (right panel). The thresholds for Lonrf1 and Tom expression levels were 0.2. (B) UMAP visualization showing the of distribution of Tomhigh and Tomlow cells. (C) Violin plot showing the Lonrf1 expression in each cell type. The expression level is represented by normalized UMI counts. (D) UMAP visualization showing the distribution of Lonrf1high and Lonrf1low cells in Tomhigh (left panel) and Tomlow cells (right panel), respectively. (E) Violin plot showing the Lonrf1 expression in Tomhigh and Tomlow cells in all cell types. (F) Dot plot showing the enriched GSEA terms from the Hallmark database in Lonrf1high/Tomlow compared with Lonrf1low/Tomlow LSECs. GSEA terms were identified with adjusted P < 0.05 by B-H method. (G) Dot plot showing the enriched GSEA terms from KEGG database in Lonrf1high/Tomlow compared with Lonrf1low/Tomlow LSECs. (H) Dot plot showing the enriched GSEA terms from Reactome database in Lonrf1high/Tomhigh compared with Lonrf1low/Tomhigh LSECs.\n\nFigure 4: Figure 4. scRNA analysis of Lonrf1 in NASH liver of 7-mo-old p16-Tom mice. (A) UMAP visualization (upper-left panel) showing cell types in NASH liver from 7-mo-old p16-Tom mice dataset containing 8,508 transcriptomes. Violin plot showing the expression levels of cell-type markers in each cell type (lower-left panel). The number of cells in each group is shown in the table (right panel). The thresholds for Lonrf1 and Tom expression levels were 0.2. (B) UMAP visualization showing the distribution of Tomhigh and Tomlow cells. (C) UMAP visualization showing the distribution of Lonrf1high and Lonrf1low cells in Tomhigh (left panel) and Tomlow cells (right panel), respectively. (D) Violin plot showing the Lonrf1 expression in each cell type. The expression level is represented by normalized UMI counts. (E) Violin plot showing the Lonrf1 expression in Tomhigh and Tomlow cells in all cell types. (F) Dot plot showing the enriched GSEA terms from the Hallmark database in Lonrf1high/Tomlow compared with Lonrf1low/Tomlow LSECs. GSEA terms were identified with adjusted P < 0.05 by B-H method. (G) Dot plot showing the enriched GSEA terms from KEGG database in Lonrf1high/Tomhigh compared with Lonrf1low/Tomhigh LSECs. (H) Dot plot showing the enriched GSEA terms from Reactome database in Lonrf1high/Tomhigh compared with Lonrf1low/Tomhigh LSECs.\n\nFigure 5: Figure 5. Tom high cells specifically increased in the injured area after wounding. (A) Experimental schedule of analysis during wound healing process. (B) Representative images of skin section 7 d after wounding or without wounding (mock). Injured and uninjured areas are indicated. Scale bar: 500 mm. (C) The proportion of Tomhigh cells was determined by calculating Tom-positive cells/Hoechst-positive cells in mock, injured, and uninjured areas. Data are presented as mean ± SEM of independent experiments (n = 6, 4, 4). One-way ANOVA followed by Tukey HSD test was performed. ****P < 0.0001"
      }
    ]
  },
  {
    "id": "PMC10231715_multi",
    "image": [
      "images/PMC10231715-f2.png",
      "images/PMC10231715-f3.png",
      "images/PMC10231715-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Uncombable Hair in a Case of Zellweger Syndrome – A New Association\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. Unevenness and gritty texture of scalp hair\n\nFigure 3: Figure 3. Dermoscopy showing irregular twisting, narrowing, empty follicles, decreased pigmentation of a few hairs [Derm lite DL4, (DermLite LLC, California, USA) Polarized mode, 10× magnification]\n\nFigure 4: Figure 4. (a) SEM x 500 showing exposure of cortex. (b) SEM x 500 showing triangular cross-section of hair"
      }
    ]
  },
  {
    "id": "PMC10309183_multi",
    "image": [
      "images/PMC10309183-f1.png",
      "images/PMC10309183-f2.png",
      "images/PMC10309183-f3.png",
      "images/PMC10309183-f4.png",
      "images/PMC10309183-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ether lipids and a peroxisomal riddle in sperm\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic representation of the different steps involved in sperm production, maturation, and fertilization. The described roles for the different types of ether lipids in these steps are included in the table. Abbreviations: AR, acrosomal reaction; PLs, phospholipids; PAF, platelet activating factor; SGG, sulfogalactosylglycerolipid; GPI, glycosylphosphatidylinositol.\n\nFigure 2: Figure 2. Chemical structures of ether and diacyl glycerophospholipids and their precursors. The acyl precursor of diacyl phospholipids, 1-acyl-G3P (also known as lysophosphatidic acid) is shown for comparison. This precursor is mainly made in the endoplasmic reticulum. Blue box points to the ester bond at the sn-1 position of the glycerol backbone (A). The precursor of all ether lipids is 1-alkyl-glycerol-3-phosphate (1-alkyl-G3P) which is synthesized in peroxisomes. Red box points to ether linkage at the sn-1 position of the glycerol backbone (B). Structures of representative ether lipid species discussed in this review are shown with the ether linkage boxed in red (C). Note that in the case of plasmenyl glycerophospholipids a vinyl ether bond is found at the sn-1 position.\n\nFigure 3: Figure 3. Key steps in the synthesis of GPI-APs. The lipid precursor is phosphatidylinositol (PI, green) containing two acyl tails with mostly unsaturated fatty acids in sn-2. 1) A diacyl to alkyl/acyl occurs through lipid remodelling involving a peroxisomal precursor. In addition the inositol ring gets palmitoylated. 2) The deacylase PGAP1 removes the acyl tail. 3) Further acyl tail remodeling occurs to introduce a saturated fatty acid in position sn-2. Once mature, the GPI-AP can be delivered to the plasma membrane. Modified from (Kinoshita, 2020).\n\nFigure 4: Figure 4. Peroxisomal core ether lipid biosynthetic pathway is present in sperm. In somatic cells, ether lipid biosynthesis is initiated in peroxisomes (A) and is finalized in the endoplasmic reticulum (B) where enzymes may be able to use both acyl and alkyl precursors (question mark). Boxed enzymes and pathways labelled in gold are found in sperm according to Chauvin et al., 2012; Amaral et al., 2013, 2014; Castillo et al., 2018; Martín-Cano et al., 2020 and Greither et al., 2023. Note peroxisome and ER compartments are believed to be missing in sperm. DHAP, Dihydroxyacetone phosphate; G3P, glycerol 3-phosphate; PA, phosphatidic acid; DAG, diacylglycerol; GNPAT, DHAP acyltransferase; AGPS, alkyl-DHAP synthase; DHRS7B, acyl/alkyl DHAP reductase; FAR; fatty acyl-CoA reductase; FALDH fatty aldehyde dehydrogenase; GPAT, G3-P acyltransferase; AGPAT, 1-acyl G3-P acyltransferase; LPIN, lipin PA phosphatase.\n\nFigure 5: Figure 5. Metabolic lipid pathways present in sperm. Proposed localization of the core peroxisomal pathway to a remnant peroxisomal compartment in close contact with mitochondria, for the synthesis ether lipid precursors with a main fatty alcohol detoxifying role. Abbreviations: Cyt c, cytochrome c; FFA, free fatty acid; FA, fatty acid; TCA, tri-carboxylic acids; CoA, coenzyme A. Created with BioRender.com."
      }
    ]
  },
  {
    "id": "PMC10318832_multi",
    "image": [
      "images/PMC10318832-f1.png",
      "images/PMC10318832-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"A de novo heterozygous variant in ACOX1 gene cause Mitchell syndrome: the first case in China and literature review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Patient’s photographs: A-C diffuse desquamatory rash D gait instability\n\nFigure 2: Figure 2. Clinical trios whole-exome sequencing chromatogram: Red box indicates the heterozygous missense mutation in ACOX1 gene in the proband (c.710 A > G, p.Asp237Ser"
      }
    ]
  },
  {
    "id": "PMC10356137_multi",
    "image": [
      "images/PMC10356137-f1.png",
      "images/PMC10356137-f1-2.png",
      "images/PMC10356137-f2.png",
      "images/PMC10356137-f2-2.png",
      "images/PMC10356137-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Dynamic regulation of inter-organelle communication by ubiquitylation controls skeletal muscle development and disease onset\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic diagram depicting the position of CRISPR-mediated mutant alleles and truncated proteins on the Kelch protein domain in klhl40abwg200 and klhl40bbwg202 knockout zebrafish. CRISPR-induced mutations in klhl40abwg200 and klhl40bbwg202 knockout zebrafish result in premature termination codons in BTB and BACK domain coding exons, respectively. (B) Sanger sequencing pherograms for control and klhl40a bwg200 and klhl40b bwg202 mutant zebrafish with an insertion of A in klhl40abwg200 and an insertion of C in klhl40bbwg202 coding regions. (C) Lateral view of the juvenile and adult zebrafish. klhl40a mutant zebrafish develop leaner bodies from transition to juvenile (1.5 months old) to the onset of the adult stage (3 months old) and exhibit reduced body length and body diameter. No obvious skeletal muscle phenotype is observed in the klhl40b allele compared to control (+/+) siblings. klhl40a/ klhl40b double mutant fish exhibit similar skeletal phenotype as observed in the klhl40a allele. (D) Endurance swimming behavior of klhl40a allele at juvenile state (1.5 months) and adult stage (3 months) (n=7–8). (E) The Kaplan-Meier survival curve of the different zebrafish groups was analyzed for 20 months (n=20 in each group). Data are mean ± S.E.M (unpaired t-test, parametric) for each experiment. Note: the survival curve of klhl40b mutant fish overlaps with the control fish.\n\nFigure 1: Figure 1. (A) RT-PCR analysis of control and klhl40abwg200 skeletal muscle (B) RT-PCR analysis of control and klhl40bbwg202 skeletal muscle. (C) Western blot analysis of protein extracts from control, klhl40abwg200, klhl40bbwg202, and klhl40abwg200/klhl40bbwg202 skeletal muscle. Figure 1—figure supplement 1—source data 1.Raw DNA gel and immunoblots. Figure 1—figure supplement 1—source data 2.Raw DNA gel and immunoblots. Figure 1—figure supplement 1—source data 3.Raw DNA gel and immunoblots. Figure 1—figure supplement 1—source data 4.Annotated gels.\n\nFigure 2: Figure 2. Transmission electron microscopy (TEM) showing the ultrastructure of control (+/+) and klhl40a KO in 3 months animals. (A–B) Longitudinal muscle section of control and klhl40a KO mutant muscle showing accumulation of membranous structures in SR-ER region (arrow) and reduced sarcomere width (w) and height (h). (C–D) Cross-section view showing mitochondrial in klhl40a KO mutant muscle contain electron-dense matrix (arrow) compared to control muscle (normal mitochondria). (E–F) The longitudinal view of skeletal muscle shows structural damage to the extracellular matrix (arrow) in the klhl40a KO mutant compared to the control. Electron microscopy was performed in three different control and klhl40a KO mutant fish. N=150–175 sarcomeres analyzed in each sample for quantification. N=75–100 mitochondria and 200–250 triads analyzed in each sample for quantification of the ER. Data are mean ± S.E.M; with one-way analysis of variance (ANOVA) and Tukey’s HSD test (****p<0.001).\n\nFigure 2: Figure 2. (A) Transmission electron microscopic images of the longitudinal skeletal muscle sections and quantification of the sarcomere size. N=150–175 sarcomeres were analyzed in each sample for quantification. Data are mean ± S.E.M; with one-way analysis of variance (ANOVA) and Tukey’s HSD test (****p<0.001). (B) Immunofluorescence of control and klhl40a mutant myofibers to visualize ER (PDI) and the Golgi (Golga2).\n\nFigure 3: Figure 3. (A) Experimental workflow for proteome and ubiquitylome quantification in klhl40a allele. (B) Heatmap showing protein abundances (log2 TMT ratios) across experimental samples. Only proteins with a significant differential response between control and klhl40a KO samples are shown (adjusted P-value <0.05). Proteins (rows) were clustered to show abundance patterns across experimental groups. (C) Heatmap showing ubiquitin sites following trypsin digestion (KGG)-site abundances (log2 TMT ratios) across experimental samples. Only proteins with a significant differential response between control and klhl40a KO samples are shown (adjusted P-value <0.05). KGG sites (rows) were clustered to show abundance patterns across experimental groups. (D) Correlation of protein response to klhl40a KO across juvenile (1.5 months) and adult animals (3 months). Plots show log2 fold changes for proteins quantified at both ages. Proteins are colored if they show differential abundance (adjusted p-value <0.05) at one age only (yellow), both ages with the same direction (green), and both ages with opposite directions (purple). (E) Correlation of ubiquitylome response to klhl40a KO across juvenile (1.5 months) and adult animals (3 months). Plots show log2 fold-changes for KGG-sites quantified at both ages. KGG sites are colored if they show differential abundance (adjusted p-value <0.05) at one age only (yellow), both ages with the same direction (green), and both ages with opposite directions (purple)."
      }
    ]
  },
  {
    "id": "PMC10356137_multi_2",
    "image": [
      "images/PMC10356137-f3-2.png",
      "images/PMC10356137-f4.png",
      "images/PMC10356137-f5.png",
      "images/PMC10356137-f6.png",
      "images/PMC10356137-f6-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Dynamic regulation of inter-organelle communication by ubiquitylation controls skeletal muscle development and disease onset\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 3: Figure 3. Differential proteins identified between control and klhl40abwg200 mutants at 3 months were compared with differential RNA-seq data from control klhl40abwg200 mutant skeletal muscle tissue (3 months) by GeneVenn.\n\nFigure 4: Figure 4. (A) Network visualization of pathway enrichment results from klhl40a KO differential proteins compared to controls. Nodes (circles) indicate pathways significantly enriched in proteins that increase at 1.5 months, decrease at 1.5 months, increase at 3 months, or decrease at 3 months. Edges (connections) show nodes with overlapping genes. Clusters of nodes summarize pathways with similar biological functions. (B) Network visualization of pathway enrichment results from klhl40a KO differential KGG-sites compared to control. Nodes (circles) indicate pathways significantly enriched in KGG sites that increase at 1.5 months, decrease at 1.5 months, increase at 3 months, or decrease at 3 months. Edges (connections) indicate nodes with overlapping genes. Clusters of nodes summarize pathways with similar biological functions. (C) Fold-changes of KGG-sites and their cognate protein in response to klhl40a KO in 1.5 months animals compared to controls. Data points are colored if both the KGG-site and the cognate protein show differential abundance in KO vs. (+/+) control and have the same direction (green) or opposite directions (purple). (D) Fold-changes of KGG-sites and their cognate protein in response to klhl40a KO in 3 months animals compared to controls. Data points are colored if both the KGG-site and the cognate protein show differential abundance in KO vs. (+/+) control and have the same direction (green) or opposite directions (purple).\n\nFigure 5: Figure 5. (A) ER-Golgi vesicle trafficking proteins exhibit altered levels in klhl40a mutant muscle compared to control (+/+) in proteome analysis; ns indicates no significant difference (B) Western blot showing ER-exit site protein Sar1a is upregulated in klhl40a mutant muscle, and downstream COPII and Golgi proteins are downregulated in mutant muscle (3mo) (C) Quantification of the protein by Western blot in klhl40a and control zebrafish. N=3 in each group. Data are mean ± S.E.M; with one-way ANOVA and Tukey’s HSD test (****p<0.001). (D) Transmission electron microscopy (TEM) of zebrafish larva (4 dpf) with SAR1A mRNA overexpression demonstrating abnormal membrane structures in the SR-ER region. (E) Immunofluorescence of control and SAR1A overexpressing myofibers (5 dpf); n=25–30 myofibers in each group. Figure 5—source data 1.Full unedited Sar1a immunoblot. Figure 5—source data 2.Full unedited Sec24d immunoblot. Figure 5—source data 3.Full unedited Golga2 immunoblot. Figure 5—source data 4.Full unedited α-tubulin immunoblot. Figure 5—source data 5.Annotated immunoblots. Figure 5—source data 6.Proteomic data for autophagy markers.\n\nFigure 6: Figure 6. Sar1a is increased and co-localized with PDI in Klhl40a deficiency. The number of PDI-positive foci is also increased in the absence of Klhl40a. The fraction of Sec23 and Tango1 positive foci is decreased in klhl40a mutant myofibers. Disruption of the Golgi architecture was observed in a fraction of Klhl40a deficient myofibers. Data are mean ± S.E.M (unpaired t-test, parametric) for each quantification.\n\nFigure 6: Figure 6. (A) Examination of autophagy markers in the proteome of controls and klhl41a mutant skeletal muscle at 1.5 months and 3 months of age (ns: nonsignificant). (B) Western blot of control and klhl40a skeletal muscle extracts with LC3B antibody. (C) Quantification of the LC-II/LC-I ratio by Western blot analysis. (D) RT-PCR assay for xbp1 transcripts in control and klhl41a mutant skeletal muscle. (E) Western Blot and protein quantification of Perk and P-Perk in control and klhl41a mutant skeletal muscle. Data are mean ± S.E.M (unpaired t-test, parametric). Figure 6—figure supplement 1—source data 1.Raw immunoblots. Figure 6—figure supplement 1—source data 2.Raw immunoblots. Figure 6—figure supplement 1—source data 3.Raw immunoblots. Figure 6—figure supplement 1—source data 4.Raw immunoblots. Figure 6—figure supplement 1—source data 5.Raw immunoblots. Figure 6—figure supplement 1—source data 6.Raw immunoblots. Figure 6—figure supplement 1—source data 7.Annotated gels. Figure 6—figure supplement 1—source data 8.Raw proteomics data for autophagy markers."
      }
    ]
  },
  {
    "id": "PMC10356137_multi_3",
    "image": [
      "images/PMC10356137-f7.png",
      "images/PMC10356137-f7-2.png",
      "images/PMC10356137-f8.png",
      "images/PMC10356137-f9.png",
      "images/PMC10356137-f9-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Dynamic regulation of inter-organelle communication by ubiquitylation controls skeletal muscle development and disease onset\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. (A) Coimmunoprecipitation in C2C12 cells showing KLHL40 directly interacts with SAR1A. (B) Co-overexpression of decreasing KLHL40-FLAG and constant SAR1A-V5 in C2C12 myoblasts demonstrates that KLHL40 is a regulator of Sar1A protein. (C) Co-overexpression of decreasing amounts of KLHL40-FLAG and constant amount of SAR1A-V5 in C2C12 myoblasts in the presence of UPS inhibitor MG132 increases the SAR1A protein levels in comparison to MG132- condition. (D) Alignment of the amino acid sequence of the SAR1A ubiquitylation site demonstrates high conservation in vertebrates (K182 in all species, marked by the asterisk). (E) Localization of different disease-causing variants in KLHL40 in the protein domains. (F) In vitro ubiquitylation of human SAR1A by CUL3 protein complex in the presence of wild-type and disease-causing KLHL40 proteins. (G) Quantifying the relative human SAR1A ubiquitylation by wild-type and disease-causing KLHL40-CUL3 complex. (H) Ubiquitylation of overexpressed SAR1A in the presence of KLHL40 in C2C12 myoblasts. Data are mean ± S.E.M; with one-way analysis of variance (ANOVA) with Dunnett’s multiple comparisons test and Brown-Forsythe test (****p<0.001; n.s. non significant) n=3. Figure 7—source data 1.Full unedited 7A immunoblot with FLAG antibody. Figure 7—source data 2.Full unedited 7A immunoblot with V5 antibody. Figure 7—source data 3.Full unedited 7B immunoblot with FLAG antibody. Figure 7—source data 4.Full unedited 7B immunoblot with V5 antibody. Figure 7—source data 5.Full unedited 7B immunoblot with GAPDH antibody. Figure 7—source data 6.Full unedited 7C immunoblot with FLAG antibody. Figure 7—source data 7.Full unedited 7C immunoblot with V5 antibody. Figure 7—source data 8.Full unedited 7C immunoblot with GAPDH antibody. Figure 7—source data 9.Full unedited 7F immunoblot with SAR1A antibody. Figure 7—source data 10.Full unedited 7F protein gel. Figure 7—source data 11.Full unedited 7H immunoblot with FLAG antibody. Figure 7—source data 12.Full unedited 7H immunoblot with SAR1A antibody. Figure 7—source data 13.Annotated immunoblots and gel.\n\nFigure 7: Figure 7. (A) Promoter competition analysis of KLHL40-FLAG and SAR1AV5 in C2C12 cells. (B) SAR1A is not ubiquitinylated in the presence of GST only (Left: Coomassie blue staining of SDS-PAGE of SAR1A ubiquitylation reaction; Right: Western blot of SAR1A ubiquitylation reaction in the presence of GST protein). Figure 7—figure supplement 1—source data 1.Raw immunoblots. Figure 7—figure supplement 1—source data 2.Raw immunoblots. Figure 7—figure supplement 1—source data 3.Raw immunoblots. Figure 7—figure supplement 1—source data 4.Raw immunoblots. Figure 7—figure supplement 1—source data 5.Raw immunoblots. Figure 7—figure supplement 1—source data 6.Annotated gels.\n\nFigure 8: Figure 8. (A) Immunofluorescence of control and klhl40a KO zebrafish muscle (3 months). Mutant muscle displays the intracellular accumulation of procollagen (as seen with co-labeling with sarcomeric α-actinin; white arrow) in klhl40a KO muscle compared to +/+control. Mutant muscle showed reduced levels of collagen compared to controls (white arrow). Integrinβ1 level is also reduced in the ECM in the mutant muscle. (B) Retention using selective hooks (RUSH) assay for ER-Golgi trafficking of procollagens and (C) sialyltransferase (ST) in control and KLHL40 knockout human myoblasts. The Golgi apparatus is marked with a yellow dashed line. N=33–45 cells in each group; data are mean ± S.E.M; and Tukey’s HSD test (p<0.01).\n\nFigure 9: Figure 9. (A) Immunofluorescence in control and a KLHL40 patient muscle biopsy showing increased SAR1A protein in the patient muscle (white arrows). Moreover, collagen accumulation is seen in the patient muscle (white arrowhead). (B) Transmission electron microscopy of KLHL40 patient muscle showed vesicle accumulation (arrows) and disorganized and damaged extracellular matrix between myofibers (arrows).\n\nFigure 9: Figure 9. (A–B) Quantification of SAR1A protein levels in centronuclear myopathy patients and control (Control-H). Wild-type (Control-Z) and klhl40a zebrafish skeletal muscle extracts were used as controls. N=3 technical replicates; data are mean ± S.E.M; and Tukey’s HSD test (****p<0.001, ns; nonsignificant). Figure 9—figure supplement 1—source data 1.Raw immunoblots. Figure 9—figure supplement 1—source data 2.Raw immunoblots. Figure 9—figure supplement 1—source data 3.Annotated gels."
      }
    ]
  },
  {
    "id": "PMC10379620_multi",
    "image": [
      "images/PMC10379620-f1.png",
      "images/PMC10379620-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"A Description of the Yield of Genetic Reinvestigation in Patients with Inherited Retinal Dystrophies and Previous Inconclusive Genetic Testing\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Showing the frequency of mutated genes that were found in the study.\n\nFigure 2: Figure 2. Showing the frequency of the most prevalent mutated genes in patients aged 0–25 years with established genotype in the retinitis pigmentosa research registry."
      }
    ]
  },
  {
    "id": "PMC10410513_multi",
    "image": [
      "images/PMC10410513-f1.png",
      "images/PMC10410513-f2.png",
      "images/PMC10410513-f3.png",
      "images/PMC10410513-f4.png",
      "images/PMC10410513-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Differential roles for ACBD4 and ACBD5 in peroxisome–ER interactions and lipid metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. ACBD4 resembles ACBD5 and can interact with VAPB to mediate peroxisome-ER contacts but loss of ACBD4 does not reduce contacts.A, protein architecture of ACBD5 and ACBD4 with known and predicted domains indicated. B, both FLAG-ACBD4 and Myc-VAPB were expressed in COS-7 cells and Myc-VAPB was immunoprecipitated and bound FLAG-ACBD4 detected by immunoblotting using FLAG/MYC antibodies (IP). Inputs represent 1% of total lysate. C, analysis of the mean population of peroxisomes associated with the ER (<15 nm) in COS-7 cells expressing the indicated proteins. D, assessment of the mean peroxisomal surface in contact with the ER in COS-7 cells expressing the indicated proteins. E, assessment of the mean peroxisomal surface in contact with the ER in control ACBD4 and ACBD5 KO HEK293 cells. F, analysis of the mean population of peroxisomes associated with the ER (<15 nm) in ACBD4/5 KO HEK293 cells. G, representative electron micrographs of peroxisome-ER interactions in the ACBD5 KO HEK293 FlpIn cells complemented with the indicted constructs. H, assessment of the mean peroxisomal surface in contact with the ER in ACBD5 KO HEK293 cells expressing the indicated proteins. I, analysis of the mean population of peroxisomes associated with the ER (<15 nm) in ACBD5 KO HEK293 cells expressing the indicated proteins. Data were analyzed by one-way ANOVA with Tukey’s multiple comparison test; ns, not significant; ∗∗p ≤ 0.01; ∗∗∗p ≤ 0.001. Error bars represent SD, with three to six experiments per condition and 56 ± 2 peroxisomes analyzed per experiment. Scale bars, (G) 200 nm. KO, CRISPR knock-out; Mito, mitochondrion; PO, peroxisomes.\n\nFigure 2: Figure 2. VLCFA analysis in ACBD5 and ACBD4 KO HEK293 cells.A, analysis of levels of C26:0 and C26:0-lysoPC in control, ACBD4 and ACBD5 KO HEK293 cells. B, analysis of C26:0 and C16:0 β-oxidation (as a percentage relative to controls) in ACBD4, ACBD5 KO, and control HEK293 cells. C, D3-C22 loading assay with analysis of D3C26:0, D3C16:0, and the ratio of D3C16:0/D3C26:0 in control ACBD4 and ACBD5 KO HEK293 cells. Data analyzed by two-tailed unpaired t test; ns, not significant; ∗p ≤ 0.0332; ∗∗p ≤ 0.0021; ∗∗∗p ≤ 0.0002; ∗∗∗∗p ≤ 0.0001. Error bars represent SD, with three experiments per condition. KO, CRISPR knock-out.\n\nFigure 3: Figure 3. Lipidomic analyses in ACBD5 and ACBD4 KO HEK293 cells. Overview of major lipid species (e.g., contains more than 40 lipid species) (A), and specific LPC (B), PC (C) and PC(O) (D) species of different chain lengths, plotted for ACBD5 or ACBD4 as ratio of control cells. For PC and PC(O) the lipid species with a chain length between 34 and 46 carbon atoms and with a maximum of three double bounds are displayed. The dotted line indicates the control value. KO, CRISPR knock-out.\n\nFigure 4: Figure 4. VLCFA complementation analysis in ACBD5 and ACBD4 KO HEK293 cells.A, analysis of levels of C26:0 and (B) C26:0-lysoPC in control, ACBD4 and ACBD5 KO HEK293 cells complemented with the indicated proteins. D3-C22 loading assay with analysis of (C) D3C16:0, (D) D3C26:0, and (E) the ratio of D3C16:0/D3C26:0 in control, ACBD4 and ACBD5 KO HEK293 cells complemented with the indicated proteins. Data analysed by two-tailed unpaired t test; ns, not significant; ∗p ≤ 0.0332; ∗∗p ≤ 0.0021; ∗∗∗p ≤ 0.0002; ∗∗∗∗p ≤ 0.0001. Error bars represent SD, with three experiments per condition. Note: Control-2 cells contained the FlpIn site whilst Control-1 does not. A5, ACBD5; AcB, mutations in AcB domain; FFAT, mutations in FFAT motif; KO, CRISPR knock-out; WT, wild-type.\n\nFigure 5: Figure 5. Substrate preference of ACBD4 and ACBD5.A, binding activity was measured with 2 μM protein and increasing concentrations of 14C-C18:1-CoA (0.5–20 μM). Error bars represent the standard deviations of at least three measurements. Competition of the binding of 14C-C18:1-CoA (5 μM) was performed with increasing concentrations of C16-CoA, C18:1-CoA and C24-CoA (0.2–20 μM), as indicated to (B) ACBD4 and (C) ACBD5. Control reactions were performed in the absence of the competitors and values obtained in their presence are presented relative to the values obtained in their absence. Error bars in the four plots represent the standard deviations of three measurements."
      }
    ]
  },
  {
    "id": "PMC10410513_multi_2",
    "image": [
      "images/PMC10410513-f6.png",
      "images/PMC10410513-f7.png",
      "images/PMC10410513-f8.png",
      "images/PMC10410513-f9.png",
      "images/PMC10410513-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Differential roles for ACBD4 and ACBD5 in peroxisome–ER interactions and lipid metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Interactions between ACBD4 and ACBD5.A, FLAG-ACBD5, WT and FFAT mutants, and Myc-ACBD5, (B) FLAG-ACBD4, WT and FFAT mutants, and Myc-ACBD4, (C) FLAG-ACBD5, WT and CC mutants, and Myc-ACBD5, (D) FLAG-ACBD4, WT and CC mutants, and Myc-ACBD4 were expressed in COS-7 cells. Myc-ACBD4/5 was immunoprecipitated and bound FLAG-proteins detected by immunoblotting using FLAG/MYC antibodies. E, FLAG-ACBD4, WT, CC, and FFAT mutants, and Myc-ACBD5 were expressed in COS-7 cells. Myc-ACBD5 was immunoprecipitated and bound FLAG-proteins were detected by immunoblotting using FLAG/MYC antibodies. Inputs represent 1% of total lysate. CC, coiled-coil mutant; FFAT, FFAT mutant; IP, immunoprecipitation.\n\nFigure 7: Figure 7. Model for potential differential roles of ACBD4 and ACBD5. At the peroxisome–ER interface, VLCFAs can be delivered to peroxisomes for beta-oxidation or retained on the ER membrane for elongation. Peroxisomal ACBD5 can act as a recruitment factor to deliver VLCFA-CoAs to the ABCD1 transporter for transfer to the peroxisomal lumen. Here, β-oxidation can generate medium chain-CoA substrates that can then be delivered back to the ER for desaturation. When ACBD5 is in complex with ACBD4, VLCFA-CoA recruitment may be inhibited. ACBD5 interaction with VAPB mediates tethering to the ER but the extent to which this interaction contributes to lipid flux between the organelles remains unclear.\n\nFigure 8: Figure 8. Sequence alignment of human ACBD4 and ACBD5 and VAPB interaction of ACBD4 in vitro.A, alignment of human ACBD4 and ACBD5 with regions of interest highlighted. TMD: transmembrane domain, Tail: region following the TMD inside the organelle lumen. B, in-vitro binding of purified ACBD4 and VAPB. Recombinant versions of both proteins, lacking the TMD, were expressed in E.coli and purified. ACBD4 (10 μM) was bound onto Ni-NTA beads and incubated with indicated concentrations of VAPBmsp. Bound fractions were analysed by immunoblotting with His and VAPB antibodies.\n\nFigure 9: Figure 9. Protein expression levels in HEK293 KO FlpIn cell lines. Immunoblot analysis using indicated antibodies of (A) ACBD5 KO HEK293 cells complemented with wild-type ACBD5 and mutant ACBD5 proteins integrated with FlpIn system and (B) ACBD4 and ACBD5 KO HEK293 cells complemented with wild-type ACBD4 via FlpIn integration. β-actin was used as a loading control.\n\nFigure 10: Figure 10. ACBD4 and ACBD5 tissue expression pattern.A, expression data in different human tissues for VAPA, VAPB, ACBD4 and ACBD5 from the ISOEXPRESSO Database. B, coomassie blue stained SDS-PAGE gel of purified, recombinant MBP-His-ACBD5 and MBP-His-ACBD4 used for in-vitro binding experiments."
      }
    ]
  },
  {
    "id": "PMC10415929_multi",
    "image": [
      "images/PMC10415929-f1.png",
      "images/PMC10415929-f2.png",
      "images/PMC10415929-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Fetal metabolic adaptations to cardiovascular stress in twin-twin transfusion syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Untargeted amniotic fluid metabolomics identifies metabolic changes in TTTS fetuses with cardiovascular stress (A) Overview of study groups. (B) Stage III TTTS is defined by abnormal Doppler studies of the umbilical artery, ductus venosus, or umbilical vein. Representative images of normal and abnormal Doppler patterns from TTTS cases included in the study are shown. IVC, inferior vena cava. (C) Dilution of amniotic fluid protein in TTTS recipients due to polyhydramnios. Mean (SD), two-tailed unpaired t test, ∗∗∗p ≤ 0.001. (D) Principal component analysis (PCA) of amniotic fluid metabolomics data using top 10% most variable metabolites. (E) Volcano plot showing differential metabolites in TTTS vs. control, including enrichment of fatty acids, arachidonic acid metabolites, and steroid hormones. Fold change threshold ≥2, FDR ≤0.001. See also Table S2 and Figure S3.\n\nFigure 2: Figure 2. Distinct clusters of TTTS are defined by glycolytic metabolites, redox stress, and altered nitrogen metabolism (A) PCA of metabolite profiles using top 10% most variable metabolites within TTTS samples. (B) Volcano plot of differential metabolites between TTTS cluster 2 and TTTS cluster 1 showing accumulation of amino acids, carnitines, 8-epi-PGF2α, ATP and NAD+ metabolites. Fold-change threshold ≥2, FDR ≤0.001. See also Table S4. (C) Schematic overview of glycolysis and fatty acid oxidation pathways. (D–F) Normalized mass spectrometry peak intensities for glucose and glycolytic metabolites: glucose, lactate, and alanine. See also Figures S2A and S2B. (G) Reduced:oxidized glutathione (GSH:GSSG) suggest increased oxidative stress and redox imbalance in TTTS cluster 2 compared with TTTS cluster 1 and control. See also Figures S2C–S2G. (H–J) Normalized mass spectrometry peak intensities for urea cycle intermediates: argininosuccinate, urea, and ornithine. See also Figures S2H–S2J. One-way ANOVA with Tukey’s multiple comparisons test, ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001.\n\nFigure 3: Figure 3. Perinatal outcomes by TTTS cluster (A–C) Similar frequency of perinatal death, early preterm birth (prior to 34 weeks of gestation), and preterm premature rupture of membranes between clusters. See also Table S5. (D and E) Similar median gestational age at birth and interval between laser surgery and birth (latency in days). See also Table S5. (F) Amniotic fluid protein levels stratified by cluster (data also shown in Figure 1C). (G) Normalized amniotic fluid NT-proBNP concentration determined by ELISA. (H) Model of fetal metabolic adaptation to cardiac stress. Data are % or median (IQR). Fisher’s exact test or Mann-Whitney test."
      }
    ]
  },
  {
    "id": "PMC10434984_multi",
    "image": [
      "images/PMC10434984-f1.png",
      "images/PMC10434984-f2.png",
      "images/PMC10434984-f3.png",
      "images/PMC10434984-f4.png",
      "images/PMC10434984-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"E4 ubiquitin ligase promotes mitofusin turnover and mitochondrial stress response\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Ufd2 controls mitofusin and mitochondrial fusion (A) Destabilization of Fzo1 upon CCCP treatment. Total cell extracts of WT cells after treatment with 10μM CCCP after 0, 10, 30, and 60 min were analyzed by sodium dodecyl sulfate- polyacrylamide gel electrophoresis (SDS-PAGE) and Western blot using an Fzo1-specific antibody. (B) Stress-induced low Fzo1 levels depend on Ufd2. Protein steady state levels of WT or Δufd2 cells expressing hemagglutinin (HA)-Fzo1 upon treatment with 50μM CCCP, 1M NaCl, 5mM DTT, pH2.4, 0.2% oleate for 1h or 42°C for 20 min. Upper: total cell extracts, analyzed as in (A) but using an HA-specific antibody. Lower: quantification of Fzo1 levels from four independent experiments, depicted as mean (bars) and individual values (circles, squares, triangles, and inverted triangles), relative to the corresponding untreated samples. The Ponceau S (PoS) staining was used as a loading control. (C) Ufd2 facilitates mitochondrial fragmentation upon stress. Mitochondrial morphology of WT or Δufd2 cells upon treatment with 5 μM CCCP. Cells expressing mitochondrial-targeted mCherry were analyzed for mitochondrial (mCherry) and cellular (Nomarski) morphology by fluorescence microscopy (left). Quantification of three independent experiments with at least 200 cells each, showing the mean percentage of tubular mitochondria (bars) and individual values (circles, squares, and triangles) (upper middle). Automated quantification of the average mitochondrial size (upper right, mitochondrial aspect ratio (lower middle), and number of mitochondria (lower right) of at least 50 randomly selected cells, shown as Tukey boxplot. Scale bar: 5 μm. (D) Stress-induced fragmentation depends on the proteasome. Mitochondrial morphology of Δpdr5 cells upon treatment with 5 μM CCCP after pre-treatment with the proteasomal inhibitor MG132 for 1h, analyzed as in (C). Scale bar: 5 μm. All statistical significances were determined by ANOVA test. ns > 0.05, ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001.\n\nFigure 2: Figure 2. Ufd2 ubiquitylates Fzo1 and targets it for proteasomal degradation (A) Higher molecular weight forms of Fzo1 in the cdc48-2 mutant background depend on Ufd2. Total cell extracts from the indicated strains expressing HA-Fzo1 were analyzed by SDS-PAGE and Western blot using an HA-specific antibody. Unmodified Fzo1, E3-dependent constitutive ubiquitin forms and E4-dependent degradative ubiquitin forms on Fzo1 are marked with an arrow, “E3-Ub” or “E4-Ub”, respectively. (B) Ufd2 specific ubiquitylation of HA-Fzo1 depends on SCFMdm30. cdc48-2Δpdr5 or cdc48-2Δpdr5Δmdm30 cells expressing genomically integrated HA-Fzo1 were treated with MG132 for 1h. Total cell extracts were analyzed as in (A). (C) Higher molecular weight forms of Fzo1 accumulate by proteasomal inhibition. The indicated strains expressing HA-Fzo1 were treated with 50μM MG132 or an equivalent amount of DMSO for 1h. Total cell extracts were analyzed as in (A) using HA- and ubiquitin (P4D1)-specific antibodies. (D) Higher molecular weight forms on Fzo1 represent ubiquitylation. Crude mitochondrial extracts were prepared from cdc48-2Δpdr5 cells expressing genomically integrated HA-Fzo1, previously treated with 50μM MG132 for 1h. Extracts were treated with the indicated concentrations of the purified catalytic domain of USP2 for 15 min at 37°C. Proteins were subsequently precipitated with trichloroacetic acid (TCA) and analyzed as in (A). (E) HA-Fzo1 levels in cdc48-2 depend on the catalytic activity of Ufd2. Total cell extracts from cdc48-2Δpdr5 or cdc48-2Δpdr5Δufd2 cells expressing genomically integrated HA-Fzo1 and the indicated variants of Ufd2-Myc were analyzed as in (A). (F) Ufd2P923A physically interacts with HA-Fzo1. Crude mitochondrial extracts from Δfzo1Δufd2 cells expressing HA-Fzo1, Ufd2P923A-Myc or the corresponding empty vectors, as indicated, were treated or not with DSP and subsequently solubilized, subjected to immunoprecipitation, and analyzed by SDS-PAGE and Western blot using HA- and Ufd2 specific antibodies.\n\nFigure 3: Figure 3. Turnover of unstable Fzo1 variants requires Ufd2 (A) Ufd2 confers instability to Fzo1C805S. HA-tagged Fzo1 (black lines) or Fzo1C805S (red lines) were expressed in Δfzo1 (continuous lines) or Δfzo1Δufd2 (dotted lines) cells and the protein levels analyzed after treatment with the translation inhibitor cycloheximide (CHX). Total cell extracts were prepared 0, 1, or 3 h after synthesis shut off and analyzed by SDS-PAGE and Western blot using HA- and Ubc6-specific antibodies. Quantification of Fzo1 levels from three independent experiments is presented relative to corresponding untreated control labeled as “0”. Shown are mean and SEM of the individual time points. The PoS staining was used as a loading control. (B and C) Suppression of Fzo1C805S steady-state levels enables mitochondrial tubulation. Protein levels of Δfzo1 or Δfzo1Δufd2 cells expressing an empty vector, HA-Fzo1, or HA-Fzo1C805S were analyzed as in Figure 1B using an HA-specific antibody (in B). Mitochondrial morphology of the same cells expressing mitochondrial targeted GFP was analyzed as in Figure 1C, with at least 200 cells from three independent experiments (in C). (D) Ubiquitylation of HA-Fzo1C805S depends on Mdm30. The indicated cells were analyzed as in Figure 2A with at least 200 cells from three independent experiments. (E) Suppression of mitochondrial morphology of cells expressing HA-Fzo1C805S in absence of Ufd2 depends on SCFMdm30. Mitochondrial morphology of the indicated cells was analyzed as in (B), with at least 200 cells from three independent experiments. Scale bar: 5 μm. All statistical significances were determined by ANOVA test. ns > 0.05, ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001.\n\nFigure 4: Figure 4. Non-functional Fzo1 and Ufd2 trap each other at mitochondria (A) Destabilization of Fzo1C805S depends on the catalytic activity of Ufd2 and its U-box functionality. HA-Fzo1C805S protein levels of WT or Δufd2 cells expressing the empty vector, Myc-tagged Ufd2, or Myc-tagged catalytic inactive (P923A) Ufd2 were analyzed as in Figure 1B using HA- and Myc-specific antibodies. (B) Mitochondrial fragmentation in cells expressing Fzo1C805S occurs independently of the catalytic activity of Ufd2. Mitochondrial morphology of Δfzo1 or Δfzo1Δufd2 cells expressing the indicated variants of HA-Fzo1 and Ufd2-Myc was analyzed as in Figure 1C with at 200 cells from three independent experiments. (C) Foci formation of Fzo1C805S-GFP in presence of catalytic-inactive Ufd2. Δfzo1Δdnm1Δufd2 cells expressing Fzo1-GFP or Fzo1C805S-GFP, Ufd2-Myc or Ufd2P923A-Myc and mitochondrial-targeted mCherry were analyzed using fluorescence microscopy. Shown are cellular morphology (Merge), mitochondrial morphology (Su9-mCherry), and Fzo1 localization (Fzo1-GFP). At least 100 cells were quantified per experiment. The number of Fzo1 foci, quantified in four independent experiments, is depicted as mean percentage (bars) and individual values (circles, squares, triangles and inverted triangles). Significant changes per “# of foci” category, in comparison to the control condition (WT Fzo1-GFP + WT Ufd2) of the same category, are represented. Scale bar: 5 μm. (D) Ufd2 P923A is recruited to Fzo1C805S foci. Δfzo1Δdnm1Δufd2 cells expression GFP-Fzo1 or GFP-Fzo1C805S, Ufd2P923A-mCherry and mitochondrial-targeted BFP were analyzed using fluorescence microscopy. Shown are the localization of Ufd2 P923A (Ufd2 P923A-mCherry), Fzo1 (GFP-Fzo1) or Fzo1C805S (GFP-Fzo1C805S), mitochondrial morphology (mtBFP), and cellular morphology (Nomarski). At least 200 cells were quantified per experiment. Colocalization of Ufd2 P923A with either the mitochondrial marker or with Fzo1 was quantified in three independent experiments using CellProfiler 4 77, and is depicted as mean (bars) and individual values (circles, squares, and triangles). Scale bar: 5 μm. All statistical significances were determined by ANOVA test. ns > 0.05, ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001.\n\nFigure 5: Figure 5. Ufd2 controls the stability of CMT2A mutants (A) Ufd2 facilitates low levels of CMT2A mutant variants on Fzo1. Total cell extracts of WT or Δufd2 cells expressing the indicated variants of HA-Fzo1 were analyzed as in Figure 1B using an HA-specific antibody. Quantifications are shown as a relative to HA-Fzo1 in WT cells from three independent experiments and depicted as mean (bars) and individual values (circles, squares, and triangles). The PoS staining was used as a loading control. (B) Mitochondrial fragmentation of cells expressing CMT2A mutant variants depends on Ufd2. Mitochondrial morphology of Δfzo1 or Δfzo1Δufd2 cells expressing the indicated variants of HA-Fzo1 was analyzed as in Figure 1C with at 200 cells from three independent experiments. (C) Ufd2 dependent instability of Fzo1V183P requires the presence of WT Fzo1. Steady state levels of WT, Δufd2, Δfzo1, or Δfzo1Δufd2 cells expressing the indicated variants of HA-Fzo1 were analyzed as in (A) (upper). (D) Deletion of UFD2 increases respiratory growth of CMT2A mutant variants. Δfzo1 or Δfzo1Δufd2 cells expressing the indicated HA-Fzo1 variants after backcrossing with WT cells were spotted on fermentable (glucose) or non-fermentable (glycerol) carbon sources to evaluate their growth capacity. Quantification from four independent experiments of the growth on non-fermentable media normalized to growth on fermentable media, as a relative to the growth of Δfzo1 cells expressing the WT HA-Fzo1, depicted as mean (bars) and individual values (circles, squares, triangles, and inverted triangles). (E) Proteasomal inhibition prevents the degradation of Fzo1L302P and mitochondrial fragmentation. Δfzo1Δpdr5 cells expressing the indicated variants of HA-Fzo1 were treated with 50μM MG132 or Bortezomib (BTZ). Mitochondrial morphology (top) and protein steady-state levels (bottom) were analyzed as in Figures 1C and 1B, respectively. (F) Overview of Ufd2 sensitivity of CMT2A mutant variants of Fzo1. A total of 25 mutations were analyzed for protein stability in WT and Δufd2 cells and for mitochondrial morphology in Δfzo1 and Δfzo1Δufd2. Out of 12 mutant variants in the GTPase domain, 3 were Ufd2 sensitive for both protein levels and mitochondrial morphology. Out of 5 mutant variants in HB1, 1 was Ufd2-sensitive for protein levels, but not for mitochondrial morphology. Out of 6 mutant variants in HB2, 1 was Ufd2-sensitive for both protein levels and mitochondrial morphology. Out of 2 mutant variants in the TM, none were sensitive to Ufd2. All statistical significances were determined by ANOVA test. ns > 0.05, ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001."
      }
    ]
  },
  {
    "id": "PMC10434984_multi_2",
    "image": [
      "images/PMC10434984-f6.png",
      "images/PMC10434984-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"E4 ubiquitin ligase promotes mitofusin turnover and mitochondrial stress response\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. MFN2 CMT2A variants are degraded dependent on UBE4B and the UPS (A) Stability of MFN2 WT and CMT2A variants. HEK293 cells transiently transfected with MFN2wtFlag or the indicated variants were left untreated (−) or treated for 3 h with CHX before cell harvesting. Total cellular extracts were analyzed by T/G-SDS-PAGE and immunoblotting using a Flag-specific antibody. The quantification of MFN2-variant levels below represents the mean from four independent experiments and the individual values of each experiment (circles, squares, triangles, and inverted triangles), normalized to the corresponding transiently transfected but untreated cells. PoS staining was used as a loading control. Statistical significance was determined by ANOVA test. (B) Proteasome sensitivity of MFN2 CMT2A variants. HEK293 cells transiently transfected with MFN2L92P-Flag, MFN2R104w-Flag or MFN2T706P-Flag, as indicated, were left untreated (−) or treated for 2 h with Epoxomicin before cell harvesting. Total cellular extracts were analyzed by T/G-SDS-PAGE and immunoblotting using an MFN2-specific antibody. The quantification of MFN2-variant levels below represents the mean from three independent experiments and the individual values of each experiment (circles, squares, and triangles), normalized to each transiently transfected untreated sample. PoS staining was used as a loading control. Statistical significance was determined by Student’s t-test. (C) Regulation of MFN2 CMT2A protein levels by UBE4B. HEK293 cells were treated for a total of 72h with scrambled (scr) or UBE4B siRNA (siUBE4B), as indicated. 48h after downregulation, cells were transiently transfected with MFN2L92P-Flag, MFN2R104w-Flag, or MFN2T706P-Flag and finally collected after 24h. Total cellular extracts were analyzed by T/G-SDS-PAGE and immunoblotting using a Flag-specific antibody. The quantification of MFN2-variant levels below represents the mean from at least four independent experiments and the individual values of each experiment (circles, squares, triangles, and inverted triangles), normalized to each transiently transfected scr-treated sample. PoS staining was used as a loading control. Statistical significance was determined by ANOVA test. (D) Mutation of lysine 532 blocks the degradation of MFN2T706P. HEK293 cells transiently transfected with MFN2T706P-3xFlag and MFN2K532R; T706P-3xFlag were analyzed and treated as in (A). The quantification of MFN2-variant levels was relative to the corresponding transiently transfected untreated cells. Four independent experiments were performed and the mean-MFN2 level (in bars) and individual values of each experiment (circles, squares, triangles, and inverted triangles) thereof is depicted. Statistical significance was determined by ANOVA test. ns > 0.05, ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001.\n\nFigure 7: Figure 7. Model of mitofusin regulation by E4 ubiquitin ligases External stresses, including mitochondrial depolarization and CMT2A related mutations, trigger proteasomal turnover of mitofusins. This stress response requires the E4 ubiquitin ligase Ufd2/UBE4B, which extends ubiquitin chains previously added by E3 ubiquitin ligases. Degradation of mitofusins prevents their fusion activity and results in mitochondrial fragmentation by ongoing fission events. This impairs mitochondrial functions and may be at the base of MFN2-linked diseases. Inhibition of the E4 UBE4B or of the proteasome might rescue mitochondrial performance and provide a study target for therapeutic intervention."
      }
    ]
  },
  {
    "id": "PMC10435624_multi",
    "image": [
      "images/PMC10435624-f1.png",
      "images/PMC10435624-f2.png",
      "images/PMC10435624-f3.png",
      "images/PMC10435624-f4.png",
      "images/PMC10435624-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cathepsin S activity controls chronic stress-induced muscle atrophy and dysfunction in mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Chronic stress accelerated skeletal muscle mass loss and dysfunction. a: The mouse immobilized stress model. At the indicated time points after being subjected to variable stress, mice were sacrificed for biochemical and morphological analyses. b: Left panel: The body weight changes of CTSS+/+ mice with non-stress (Control) and a 14-day stress period (Stress) (n = 7 each). Middle panel: Grip strength analysis of Control and Stress mice (n = 7). Right panel: Gastrocnemius (GAS) muscle weights of Control and Stress mice (n = 7). c: Representative images of GAS muscle shape after sampling. d: Representative images of hematoxylin and eosin (H&E) staining of the GAS muscle sections of wildtype (CTSS+/+) mice. Scale bar: 75 µm and quantitative data showing the cross-sectional area of a GAS fiber (n = 5). e: Representative immunoblotting images and quantitative data for CTSS in GAS muscles at Days 7 and 14 after stress (n = 3). f: RT-qPCR analysis of CTSS in GAS muscle (n = 7, each group). The data are mean ± SEM, and p-values were determined by a two-way repeated measures ANOVA and Bonferroni’s post hoc tests (b: left panel and middle panel, e,f). One-way ANOVA followed by Tukey’s post hoc tests (b: right panel) or unpaired Student’s t-test (d). Control: CTSS+/+ control mice, Stress: CTSS+/+ 14-day-stressed mice. *p < 0.05; **p < 0.01; N.S, not significant\n\nFigure 2: Figure 2. CTSS deficiency protected against stress-related muscle damage. a: The body weights and (b) GAS muscle weights of the four groups of mice (CW: CTSS+/+ control mice, CK: CTSS−/− control mice, SW: 14-day-stressed CTSS+/+ mice, SK: 14-day-stressed CTSS−/− mice; n = 8 each) on the 14th day after stress. c: The measurements of all four limbs’ grip strength in the four groups of mice at the indicated points (n = 8, each group). d: Representative H&E images of GAS muscle sections. e–f: Quantitative data showing the cross-sectional area of a GAS fiber (n = 5). g: The FITC-labeled type I collagen wee applied to evaluate the levels of CTSS-mediated collagenolytic activity using a specific CTSS inhibitor (CTSS-I) in the skeletal muscles of the non-stressed and stressed mice. Scale bar: 75 µm. The data are mean ± SEM, and p-values were determined by two-way repeated measures ANOVA and Bonferroni’s post hoc tests (c) or a one-way ANOVA followed by Tukey’s post hoc tests (a,b,f). *p < 0.05; **p < 0.01; N.S, not significant\n\nFigure 3: Figure 3. CTSS deletion alleviated muscle microstructure repair in mice subjected to stress. a, b: Representative immunofluorescence images and quantitative data for the intensity of desmin protein expression in the four experimental groups at day 14 after stress (n = 5). Scale bar: 75 µm. c: Representative immunoblotting images and quantitative data for Desmin and GAPDH protein in the lysates from the four groups (n = 3). The data are mean ± SEM, and p-values were determined by a one-way ANOVA followed by Tukey’s post hoc tests (b). CW: CTSS+/+ control mice, CK: CTSS−/− control mice, SW: 14-day-stressed CTSS+/+ mice, SK: 14-day-stressed CTSS−/− mice. *p < 0.05; **p < 0.01; N.S, not significant\n\nFigure 4: Figure 4. CTSS deficiency ameliorated stress-related anabolic and catabolic molecular alterations. a–e: Representative immunoblotting images and quantitative data for CTSS, IGF-1, IRS-2, p-PI3K, p-Akt, p-mTOR, p-FoxO1α, MuRF-1, MAFbx1, PGC-1α, PPAR-γ, C-caspase-3, and Bcl-2 in GAS muscles at Day 14 after stress (n = 3). Data are mean ± SEM, and p-values were determined by a one-way ANOVA followed by Bonferroni post hoc tests (b–e). CW: CTSS+/+ control mice, CK: CTSS−/− control mice, SW: 14-day-stressed CTSS+/+ mice, SK: 14-day-stressed CTSS−/− mice. *p < 0.05; **p < 0.01; N.S, not significant\n\nFigure 5: Figure 5. CTSS deletion alleviated muscle apoptosis and mitochondrial morphological changes in mice subjected to stress. a: Representative TUNEL staining used to assess the content of apoptotic cells. Yellow arrows: TUNEL-positive cells. c: Quantitative data for TUNEL-positive cells (n = 6). Scale bar: 75 µm. c–e: Representative images. b: Transmission electron microscopic images combined with quantitative data showing the percentage of damaged mitochondria (d) and the number of lipid droplets (e). Scale bars: 1.0 µm and 200 nm (n = 5). Data are mean ± SEM, and p-values were determined by one-way ANOVA followed by Tukey’s post hoc tests (b,d,e). CW, etc. are explained in the earlier figure legends. *p < 0.05; **p < 0.01; NS, not significant"
      }
    ]
  },
  {
    "id": "PMC10435624_multi_2",
    "image": [
      "images/PMC10435624-f6.png",
      "images/PMC10435624-f7.png",
      "images/PMC10435624-f8.png",
      "images/PMC10435624-f9.png",
      "images/PMC10435624-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cathepsin S activity controls chronic stress-induced muscle atrophy and dysfunction in mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The cathepsin S inhibitor (CTSS-I) alleviated stress-related skeletal muscle injury and dysfunction. a, b: The body weights and GAS muscle weights of the four groups of mice (n = 8, each group). c: The measurements of all four limbs’ grip strength in four groups of mice at the indicated time points (n = 8 each). d, e: Representative H&E images and quantitative data for the cross sections of GAS muscle fibers harvested from the four groups of mice on Day 14. Scale bar: 75 µm. The data are mean ± SEM, and p-values were determined by a one-way ANOVA followed by Tukey’s post hoc tests (a, b), unpaired Student’s t test (E right panel), or two-way repeated measures ANOVA and Bonferroni’s post hoc tests (c). VC: CTSS+/+ loaded vehicle + non-stress, IC: CTSS+/+ loaded CTSS-I + non-stress, VS: CTSS+/+ loaded vehicle + stress, IS: CTSS+/+ loaded CTSS-I + stress. *p < 0.05; **p < 0.01; N.S, not significant\n\nFigure 7: Figure 7. CTSS deletion mitigated S-serum-induced C2C12 myoblast ROS produced, reduction in mitochondrial respiration, cell apoptosis and myotube atrophy. C2C12 cells were treated with siCTSS and non-targeting control RNA for 48 h and then cultured in 5% NS-serum or 5% S-serum for 24 h. a: Representative fluorescent microscopy images showing intracellular ROS in four experimental groups. Scale bar: 1000 µm. b: The oxygen consumption rate measured using the Seahorse XFp assay in four groups of cells. c: Representative image of TUNEL immunofluorescence (c) and combined quantitative data (d) show the numbers of TUNEL+ apoptotic cells in the four experimental groups (n = 5). Yellow arrows: TUNEL+ cells. Scale bar: 200 µm. e: Myotubes treated with siCTSS or non-targeting control were cultured in 5% S-serum or NS-serum for 72 h and then subjected to immunofluorescence staining for MHC (NS, SS, siNS, siSS). f: Quantification of the mean diameter of four groups. g: Representative immunoblotting images and (h) quantitative data for LC3B-II/I in the lysates from the four groups (n = 3). Data are mean ± SEM, and p-values were determined by one-way ANOVA followed by Tukey’s post hoc tests (b,d,f,h). NS: C2C12 cells treated non-targeting control RNA were cultured in 5% NS-serum for 24 h, siNS: CTSS-silenced C2C12 cells cultured in 5% NS-serum for 24 h, SS: C2C12 cells treated non-targeting control RNA were cultured in 5% S-serum for 24 h, siSS: CTSS-silenced C2C12 cells cultured in 5% S-serum for 24 h. *p < 0.05; **p < 0.01; N.S, not significant\n\nFigure 8: Figure 8. CTSS deletion ameliorated S-serum-induced C2C12 myoblast anabolic and catabolic molecular alterations. a-d: Representative immunoblotting images and quantitative data for CTSS, IRS-2, p-PI3K, p-Akt, p-mTOR, p-FoxO1α, MuRF-1, MAFbx1, PGC-1α, PPAR-γ, C-caspase-3, and Bcl-2 in the lysates from the four groups (n = 3). Data are mean ± SEM, and p-values were determined by one-way ANOVA followed by Tukey’s post hoc tests (b–d). NS: C2C12 cells treated non-targeting control RNA were cultured in 5% NS-serum for 24 h, siNS: CTSS-silenced C2C12 cells cultured in 5% NS-serum for 24 h, SS: C2C12 cells treated non-targeting control RNA were cultured in 5% S-serum for 24 h, siSS: CTSS-silenced C2C12 cells cultured in 5% S-serum for 24 h. *p < 0.05; **p < 0.01\n\nFigure 9: Figure 9. CTSS overexpression stimulated S-serum-induced C2C12 cell ROS produced, reduction in mitochondrial respiration, cell apoptosis and myotube atrophy. C2C12 cells were treated with pl-CTSS and empty plasmid for 48 h, cultured in 5% NS-serum or 5% S-serum for 24 h, and then subjected to Detection of ROS. a: Representative fluorescent microscopy images showing intracellular ROS in the four experimental groups. Scale bar: 1000 µm. b: The oxygen consumption rate measured using the Seahorse XFp assay in four groups of cells. c, d: Representative image of TUNEL immunofluorescence (c) and combined quantitative data (d) show the numbers of TUNEL+ apoptotic cells in the four experimental groups (n = 5). Yellow arrows: TUNEL+ cells. Scale bar: 200 µm. e: Myotubes treated with pl-CSTT or empty control plasmid were cultured in 5% S-serum for 72 h and then subjected to immunofluorescence staining for MHC (NS, SS, plNS, plSS). f: Quantification of the mean diameter of four groups. g: Representative immunoblotting images and (h) quantitative data for LC3B-II/I in the lysates from the four groups (n = 3). Data are mean ± SEM, and p-values were determined by one-way ANOVA followed by Tukey’s post hoc tests (b, d, f, h). NS: C2C12 cells treated non-targeting control RNA were cultured in 5% NS-serum for 24 h, siNS: CTSS-silenced C2C12 cells cultured in 5% NS-serum for 24 h, SS: C2C12 cells treated non-targeting control RNA were cultured in 5% S-serum for 24 h, siSS: CTSS-silenced C2C12 cells cultured in 5% S-serum for 24 h. *p < 0.05; **p < 0.01; NS, not significant\n\nFigure 10: Figure 10. CTSS overexpression stimulated S-serum-induced C2C12 myoblast anabolic and catabolic molecular alterations. a-d: Representative immunoblotting images and quantitative data for CTSS, IRS-2, p-PI3K, p-Akt, p-mTOR, p-FoxO1α, MuRF-1, MAFbx1, PGC-1α, PPAR-γ, C-caspase-3, and Bcl-2 in the whole-cell lysates of the groups (n = 3). The data are mean ± SEM, and p-values were determined by one-way ANOVA followed by Tukey’s post hoc tests (b–d). NS: C2C12 cells treated with empty control plasmid were cultured in 5% NS-serum for 24 h, plNS: CTSS-overexpressed C2C12 cells cultured in 5% NS-serum for 24 h, SS: C2C12 cells treated with empty control plasmid were cultured 5% S-serum for 24 h, plSS: CTSS-overexpressed C2C12 cells cultured in 5% S-serum for 24 h. *p < 0.05; **p < 0.01"
      }
    ]
  },
  {
    "id": "PMC10515011_multi",
    "image": [
      "images/PMC10515011-f1.png",
      "images/PMC10515011-f2.png",
      "images/PMC10515011-f3.png",
      "images/PMC10515011-f4.png",
      "images/PMC10515011-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Depletion of LONP2 unmasks differential requirements for peroxisomal function between cell types and in cholesterol metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. LONP2 knockdown triggered the accumulation of its substrate TYSND1, alterations in peroxisome size and numbers, and luminal protein import failure. a–d Immunoblotting (a, c) and representative confocal images and quantification of peroxisome size and numbers (b, d) in non-targeting (NT)- and LONP2-silenced COS-7 cells (a, b) and U2OS cells (c, d) after 144 h. TYSND1-F and TYSND1-C indicate full-length TYSND1 and the self-cleaved C-terminal region of TYSND1, respectively. Scale bar, 5 µm. e, f Representative confocal images (e) and quantification (f) of the colocalization between peroxisomes (PMP70) and transiently expressed peroxisome luminal protein (CFP-SKL) in NT- and LONP2-silenced COS-7 cells after 144 h. Scale bar, 2 µm. g Representative confocal images showing the colocalization between peroxisomes (PMP70) and transiently expressed peroxisome membrane protein (PEX3-YFP) in NT- and LONP2-silenced COS-7 cells after 144 h. Scale bar, 5 µm. h Immunoblotting for autophagy-related proteins, vinculin was used as a loading control. i Representative confocal images of COS-7 cells grown in HBSS for 24 h (left) and quantification (right) showing the number of LC3-P62 puncta on peroxisomes of NT- and LONP2-silenced COS-7 cells and U2OS cells after 144 h. Cells were grown in either DMEM or HBSS for 24 h and LC3-P62 puncta on peroxisome was visualized with transiently expressed GFP-LC3 and the immunofluorescence of p62 and PMP70. Scale bar, 2 µm. j Representative confocal images and quantification showing the size and mean branch length of mitochondria in NT- and LONP2-silenced COS-7 cells after 144 h. Scale bar, 5 µm. On all plots, dots represent individual cells from n = 3 technically independent experiments depicted in different colours, and triangles represent the mean within an independent experiment. The mean values were used to calculate the average (horizontal bar), s.d. (error bars), and P-values (using a two-tailed unpaired Student’s t-test)\n\nFigure 2: Figure 2. Cell-specific ISR activation upon silencing of LONP2. RNA sequencing (n = 3 independent experiments per condition), LONP2 silencing for 7 days. a Principal component (PC) score plot. b Volcano plots showing all identified transcripts. c Transcripts encoding integrated stress response (ISR) factors. d Immunoblotting for ISR-related proteins, vinculin was used as a loading control. e Translation assay: cells were incubated with puromycin for 10 min., and incorporation of puromycin into newly synthesized proteins was revealed with anti-puromycin antibodies. GAPDH was used as a loading control. f Transcripts encoding ribosomal biogenesis-related rRNA, snoRNA and mRNA genes. g Immunoblot of ribosomal biogenesis regulator RRS1 in NT- and LONP2-silenced COS-7 cells and U2OS cells\n\nFigure 3: Figure 3. LONP2 silencing leads to impaired retinoic acid signaling. a Gene ontology of RNA sequencing data (dataset is described in Fig. 2). Numbers on Venn diagram indicate the number of genes in each category. b Immunoblotting of retinoic acid regulating proteins, vinculin used as a loading control. c COS-7 or U2OS cells were incubated in the presence or absence of 5 µM retinoic acid for 24 h and mRNA transcript levels for LONP2 (left two panels) and TGM2 (right two panels) quantified with qRT-PCR. n = 3 independent experiments, means are depicted in different colours. The mean values were used to calculate the average (horizontal bar), s.d. (error bars) and P-values (using a two-tailed unpaired Student’s t-test)\n\nFigure 4: Figure 4. Lipid profiles of COS-7 and U2OS cells differ drastically and are differentially affected by LONP2 silencing. Untargeted lipidomic analysis of n = 5 independent cell experiments for each group under the basal condition of after LONP2-silencing for which the final dataset included 2,094 lipid features (Table S2). a Principal component (PC) score plot. b Log2 (fold changes) of 206 lipid features annotated by MS/MS and data alignment using our in-house database, and grouped by lipid subclass, whereby red and black dots indicate lipids that reach or not our selected significance threshold for the indicated comparison, Pcorr-value < 0.1. c Box plots of unique lipids annotated by MS/MS from the 100 most significant lipid features discriminating LONP2-silenced COS-7 cells (top) and U2OS cells (bottom) from NT-silenced cells. The midline represents the median fold change vs. NT-silenced cells, the box represents the interquartile range between the first and third quartile, and the whiskers represent the lowest or highest values. d Immunoblotting of cholesterol sensor INSIG1, vinculin used as a loading control. Abbreviations: sphingolipid (SP), sterol lipid (ST), glycerolipid (GL), glycerophospholipid (GP), fatty acyls (FA), sphingomyelin (SM), ceramide (Cer), glucosylceramide (GlcCer), cholesterol (Chol), cholesterol ester (CE), triacylglycerol (TG), diacylglycerol (DG), 1-alkyl, 2-acylglycerophosphocholine (PCO-), 1-(1Z-alkenyl), 2-acylglycerophosphocholine (PCP-), 1-alkyl, 2-acylglycerophosphoethanolamine (PEO-), 1-(1Z-alkenyl), 2-acylglycerophosphoethanolamine (PEP-), diacylglycerophosphocholine (PC), diacylglycerophosphoethanolamine (PE), diacylglycerophosphoinositol (PI), monoacylglycerophosphocholine (LPC), monoacylglycerophosphoethanolamine (LPE), diacylglycerophosphoglycerol (PG), free fatty acid (FFA) and acylcarnitine (CAR). All lipid features were categorized into subclasses and labeled based on the LIPID MAPS® Structure Database\n\nFigure 5: Figure 5. LONP2 knockdown induced lipid storage, including aberrant cholesterol accumulation in lysosomes. a Representative confocal images (left) and quantification (right) of lipid droplets (Nile Red) in NT- and LONP2-silenced COS-7 cells after 6 days. Scale bar, 5 µm. b Representative confocal images showing the Filipin-stained intracellular cholesterol (green), Nile Red-stained lipid droplets (magenta) and endolysosomes (blue) visualized with the immunofluorescence of LAMP1. Scale bar, 2 µm. c, d Free cholesterol overload experiment in NT- and LONP2-silenced COS-7 cells (c) and U2OS cells (d) after 7 days. Representative confocal images (left) and quantifications (right) of the colocalization between cholesterol (Filipin) and endolysosomes (LAMP1). Scale bar, 2 µm. e Transmission electron microscopy micrographs of NT- and LONP2-silenced COS-7 cells. Scale bar, 500 nm. f Immunoblotting (left) and image quantification (right) of cholesterol overload experiment in NT- and LONP2-silenced COS-7 cells rescued with transient expression of siRNA-resistant LONP2 cDNA for 48 h. Data from n = 3 technically independent experiments, and their respective means are depicted in different colours. The mean values were used to calculate the average (horizontal bar), s.d. (error bars) and P-values (using a two-tailed unpaired Student’s t-test)"
      }
    ]
  },
  {
    "id": "PMC10526550_multi",
    "image": [
      "images/PMC10526550-f1.png",
      "images/PMC10526550-f2.png",
      "images/PMC10526550-f3.png",
      "images/PMC10526550-f4.png",
      "images/PMC10526550-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"ABCD1 Transporter Deficiency Results in Altered Cholesterol Homeostasis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Cholesterol ester-fatty acid species are increased in primary human X-ALD fibroblasts and in the CNS of Abcd1 KO mice. (A–D) Lipidomic analyses were performed on control and X-ALD fibroblasts (n = 8 each) and on the brain and spinal cord of WT and Abcd1 KO mice (n = 6 each) using ultrahigh resolution liquid chromatography-mass spectrometry. The comparisons of total cellular cholesterol ester (CE) content (A) and CE-fatty acid composition (B) of control and X-ALD fibroblasts are displayed as a boxplot and volcano plot, respectively. The accumulation of CE-VLCFA species, represented by CE(26:0) in (C) and CE(26:1) in (D), was determined in human fibroblasts and murine CNS tissues and displayed as boxplots. All CE and CE(FA) levels were normalised to CE(16:0). Unpaired two-sided Student’s t-test was performed in (A). For (B–D), Qlucore Omics Explorer 3.5 software was used to analyse the lipidomic data statistically by conducting a two-group comparison test. The obtained p-values and log2-fold change values were used to create a volcano plot. The box plots (in (A,C,D)) show all the individual values and the median. * p < 0.05; *** p < 0.001.\n\nFigure 2: Figure 2. Imbalanced cholesterol homeostasis in X-ALD-derived fibroblasts leads to increased cholesterol efflux upon prolonged cholesterol loading. (A) Simplified schematic representation of cellular cholesterol turnover (FC, free cholesterol; LDs, lipid droplets). (B–E) Primary human control or X-ALD-derived fibroblasts (n = 6 each) were cultured for 5 days in lipid-depleted medium (LDM), RPMI with FBS (complete medium) or LDM supplemented with 10 μg/mL cholesterol (LDM + chol). RT-qPCR was carried out to determine the relative mRNA levels (normalised to HPRT1) of genes involved in cholesterol synthesis, HMGCR (B); cholesterol esterification, SOAT1 (C); cholesterol ester hydrolysis, NCEH1 (D); and cholesterol export, ABCA1 (E). (F) Cholesterol efflux was measured after 5 days of loading cholesterol in LDM + chol (control, n = 6; X-ALD, n = 9). The box plots in (B–F) show all individual values and the median. One-way ANOVA with Sidak’s multiple comparisons test was performed for statistical analysis of the data in (B–E). Unpaired two-sided Student’s t-test was performed in (F). The image in (A) was created using BioRender.com.\n\nFigure 3: Figure 3. Increased lipid droplet induction upon prolonged cholesterol loading in X-ALD vs. control fibroblasts. (A–E) Control and X-ALD-derived primary fibroblasts were starved for 72 h in LDM and then incubated for 5 days with 10 or 20 µg/mL cholesterol in LDM. (A) The time course of LD formation induced by 20 µg/mL cholesterol treatment was monitored in four cell lines/genotype using the neutral lipid stain, BODIPY™ 493/503, and Incucyte® live-cell imaging. Cells were recorded from 24 h through to 120 h after adding cholesterol. The results are expressed as the fraction green fluorescence area/cell area. NC, normal control fibroblast line in LDM with 2% ethanol and BODIPY™ 493/503. The data are depicted as mean ± SD. Two-way ANOVA with Dunnett’s multiple comparisons test: * p < 0.05; ** p < 0.01; *** p < 0.001. (B–E) Fibroblasts (n = 6 per genotype) were exposed to 10 µg/mL cholesterol for 5 days before analysis. Representative confocal microscopy pictures (B) of control (left panel, green dot) and X-ALD (middle panel, red square) cells stained with BODIPY™ 493/503 (LDs, green fluorescence) and DAPI (nuclei, blue). Light microscopy pictures (C) of control and X-ALD cells stained with Oil Red O and haematoxylin. Images in (B,C) were analysed using ImageJ software and the results were expressed as LD area/cell (right panels). The microscopy views correspond to the colour-coded samples in the graphs. (D) Relative Perilipin 2 (PLIN2) mRNA levels, normalised to HPRT1, determined by RT-qPCR. (E) PLIN2 protein expression normalised to β-actin was assessed by western blot analysis: Original images could be found in Supplementary File—original-images. (E). In (B–E), the box plots show individual data points and the median; statistically significant differences determined using unpaired two-sided Student’s t-test are displayed as exact p-values.\n\nFigure 4: Figure 4. Low interaction between peroxisomes and lipid droplets under cholesterol-loading conditions in both control and X-ALD fibroblasts. (A) Western blot analysis depicting various levels of stable ABCD1 protein and GAPDH for normalisation of loading in the cell lines used for the co-localisation study in standard RPMI medium. The samples are colour-coded according to their ABCD1 content (blue, >20%; orange, 5–20%; red, <5%). A cut in the image is indicated by a dashed line; for the full set and quantification of ABCD1 protein levels, see Supplementary Figure S7. (B–D) Control (n = 3) and X-ALD-derived fibroblasts (n = 7) were starved in LDM, loaded with 20 µg/mL cholesterol for 72 h and stained with BODIPY™ 493/503 (for LDs) and anti-PMP70 antibody (for peroxisomes). Representative ultra-high resolution confocal images of LDs (green) and peroxisomes (red) and their interactions (yellow) in cholesterol-treated cells (control C1 and X-ALD A9) Original images could be found in Supplementary File—original-images (B). The extent of interaction between LDs and peroxisomes is expressed as Manders’ co-localisation coefficients, M1 (% of green pixel with red component) and M2 (% of red pixel with green component) (C), one-way ANOVA with Sidak’s multiple comparisons test. Linear regression analysis of the relationship between M1 or M2 and the level of mutated ABCD1 protein in X-ALD cells revealed no significant correlation (D).\n\nFigure 5: Figure 5. Dysregulation of the cholesterol-related gene expression and increased numbers of LD-positive neurons in the spinal cord Abcd1 KO mice. (A–C) Spinal cord tissue was dissected from 12-month-old WT or Abcd1 KO mice (n = 7 each) for RNA extraction or cryosectioning and Oil Red O (ORO) staining of LDs. Representative light microscopy views from the ventral horn of ORO-stained WT (green circle) and Abcd1 KO (red square) lumbar spinal cord, counterstained with haematoxylin (blue cell nuclei and, in neurons, rough ER) (A) show the somas of several motor neurons with LDs (black arrows). For quantification of neutral lipid accumulation, the number of LD-loaded motor neurons was normalised to the tissue area (ventral horn grey matter) (B). The coloured data points correspond to the samples shown in (A). The relative mRNA levels of the cholesterol-related genes: Hmgcr (synthesis), Soat1 (esterification), Abca1 and Apoe (export), and for normalisation, Hprt, were determined by RT-qPCR (C). The box plots display all individual values and the median. The red dot indicates an extreme outlier (>3 × IQR), excluded from the statistical analysis. The unpaired two-sided Student’s t-test in was performed in (B) and one-way ANOVA with Sidak’s multiple comparisons test in (C)."
      }
    ]
  },
  {
    "id": "PMC10526880_multi",
    "image": [
      "images/PMC10526880-f1.png",
      "images/PMC10526880-f2.png",
      "images/PMC10526880-f3.png",
      "images/PMC10526880-f4.png",
      "images/PMC10526880-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal NAD(H) Homeostasis in the Yeast Debaryomyces hansenii Depends on Two Redox Shuttles and the NAD+ Carrier, Pmp47\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. D. hansenii peroxisomes are required for the utilisation of fatty acids as a carbon source via β-oxidation. (A) Peroxisome number increased when D. hansenii cells were grown on oleate-based medium. Representative epifluorescence microscopy images of wild-type and pex3Δ cells expressing mCherry-PTS1 and grown on glucose medium to exponential growth phase or grown on oleate medium for 6 h. Red channel images are merged z-stacks. Peroxisome numbers were quantified for >50 budding wild-type cells per replica (n = 3, individual replicas are labelled as GR (glucose medium replica) and OR (oleate medium replica)). Bars in the graph indicate the median with 95% confidence intervals for mean. Statistical significance analysis was performed using Kruskal–Wallis test. Scale bar: 5 μm. (B) Growth analysis of wild type, fox2Δ (three independent strains) and pex3Δ D. hansenii cells, on media containing glucose, glycerol or oleate as sole carbon sources. (C,D) β-oxidation activity was higher in oleate-induced cells compared to glucose-grown cells, and loss of Fox2 affected β-oxidation activity in D. hansenii cells. NAD+ availability in D. hansenii was not solely dependent upon the Mdh3 and Gpd1 redox shuttles but also on Pmp47. The presented data relate to Section 3.1, Section 3.2 and Section 3.3 of this manuscript. β-oxidation activity in wild-type and mutant S. cerevisiae and D. hansenii cells, grown on (C) glucose-based medium or (D) oleate-based medium (oleate-induced cells), were measured using [1-14C]-labelled octanoate (C8:0) as substrate. The results are shown as mean ± standard deviation (n = 4). One-way ANOVA with Dunnett’s multiple comparisons test was performed to determine if differences were significant when compared with the corresponding wild-type cells. ns, not significant; **** p < 0.0001.\n\nFigure 2: Figure 2. The malate and glycerol-3-phosphate dehydrogenase redox shuttles are not essential for β-oxidation in D. hansenii. (A,B) Representative epifluorescence microscopy images of wild-type and pex3Δ cells expressing mCherry-PTS1 and either (A) GFP-Mdh3 or (B) Gpd1-GFP expressed from their chromosomal loci. Cells were grown on oleate medium for 6 h. Red and green channel images are merged z-stacks. Merge is an overlay of the red and green merged z-stacks. Bright-field (BF) images were collected in one plane and were processed to highlight the cell circumference in blue in other panels. Scale bar: 5 μm. (C) Growth analysis of wild-type and mutant D. hansenii cells on media containing glucose, glycerol or oleate as sole carbon sources.\n\nFigure 3: Figure 3. Pmp47 is a peroxisomal protein that contributes to fatty acid β-oxidation in D. hansenii. (A) Representative epifluorescence microscopy images of wild-type D. hansenii cells expressing mCherry-PTS1 and Pmp47-GFP expressed from its chromosomal locus. Cells were grown on oleate medium for 6 h. Red and green channel images are merged z-stacks. Merge is an overlay of the red and green merged z-stacks. Bright-field (BF) images were collected in one plane and are processed to highlight the cell circumference in blue in other panels. The white rectangles are enlarged below to show the ring-like GFP signal of Pmp47-GFP, which surrounds the peroxisomal lumen stained with mCherry-PTS1. Scale bar: 5 μm. (B) Western blot analysis of lysates of wild-type D. hansenii cells expressing Gpd1-GFP or Pmp47-GFP under control of their endogenous promoter grown on glucose (glu) or oleate (ole) media using anti-GFP and anti-actin (loading control). Protein ladder (M) was used as size standard. (C) Growth analysis of wild-type and mutant D. hansenii cells on media containing glucose, glycerol or oleate as sole carbon sources.\n\nFigure 4: Figure 4. DhPmp47 is a peroxisomal NAD+ carrier involved in the maintenance of peroxisomal NAD+ required for β-oxidation. (A) DhPmp47-GFP was localised to the peroxisomal membrane upon expression in S. cerevisiae cells. Representative epifluorescence microscopy images of wild-type S. cerevisiae cells expressing the peroxisomal membrane marker, Pex11-mRFP, and DhPmp47 fused with GFP (DhPmp47-GFP). Red and green channel images are merged z-stacks. Merge is an overlay of the red and green merged z-stacks. Bright-field (BF) images were collected in one plane and were processed to highlight the cell circumference in blue in other panels. Scale bar: 5 μm. (B,C,E) DhPmp47 was expressed in wild-type or mutant S. cerevisiae cells behind an oleate-inducible CTA1 promoter. (B) Heterologous expression of DhPmp47 rescued the β-oxidation activity of mdh3Δ, mdh3Δgpd1Δ and mdh3Δnpy1Δ S. cerevisiae cells. S. cerevisiae cells were oleate-induced (grown overnight on oleate medium), and β-oxidation rates were measured using [1-14C]-labelled octanoate as substrate. The results are shown as mean ± standard deviation (n = 4). One-way ANOVA with Tukey’s multiple comparisons test was performed to determine if differences were significant. Cells transformed with empty plasmid and fox1Δ cells, deficient of the first enzyme of the β-oxidation pathway, were used as controls. (C) Heterologous expression of DhPmp47 rescued the ability of mdh3Δ and mdh3Δgpd1Δ S. cerevisiae cells to utilise oleate. Growth analysis of the indicated S. cerevisiae strains either expressing DhPmp47 or transformed with an empty plasmid on media containing glucose or oleate as sole carbon source. (D) Schematic representation of the peroxisomal steps of fatty acid β-oxidation and main redox shuttle in S. cerevisiae. Deletion of peroxisomal malate dehydrogenase (Mdh3), red cross, that is part of the peroxisomal malate redox shuttle, results in accumulation of the β-oxidation intermediate 3-hydroxy acyl-CoA. To estimate the level of 3-hydroxy acyl-CoA produced in peroxisomes, acyl-CoA esters were converted to the more stable carnitine esters by heterologous expression of human carnitine O-palmitoyltransferase 2 (HsCPT2) that was artificially targeted to peroxisomes by deletion of its mitochondrial targeting signal and addition of a peroxisomal targeting signal type 1. Heterologous expression of DhPmp47 provides an alternative mechanism to supply S. cerevisiae peroxisomes with NAD+. (E) Heterologous expression of DhPmp47 reduced 3-hydroxy octadecenoyl-carnitine levels in oleate-induced (grown overnight on oleate medium) mdh3Δ cells. DhPmp47 and peroxisome-targeted carnitine O-palmitoyltransferase 2 (HsCPT2PTS1) were expressed in wild-type and mdh3Δ S. cerevisiae cells, as indicated. Cells expressing HsCPT2 lacking a PTS1 that localizes to the cytosol (HsCPT2cyt) and cells transformed with empty plasmid were used as negative controls. Accumulation of the 3-hydroxy octadecenoyl-carnitine was measured using HPLC-tandem MS. The results are shown as mean ± standard deviation of 3 technical replicates. One-way ANOVA with Tukey’s multiple comparisons test was performed to determine if differences are significant. ns, not significant; * p = 0.01 to 0.05; **** p < 0.0001.\n\nFigure 5: Figure 5. Heterologous expression of DhPmp47 supplies S. cerevisiae peroxisomes with NAD+ required for lysine biosynthesis. (A) Schematic representation of the peroxisomal step of lysine biosynthesis pathway in S. cerevisiae. A deletion of Mdh3 and Gpd1 enzymes, that are part of the peroxisomal malate and glycerol-3-phosphate redox shuttles, results in a deficiency in lysine biosynthesis. (B) Lysine bradytrophy (slow-growth phenotype on lysine-free medium) was repressed by heterologous expression of DhPmp47, DhMdh3 and DhGpd1 in S. cerevisiae mdh3Δgpd1Δ cells. Growth analysis on glucose medium in the absence or presence of lysine. Wild-type and mdh3Δgpd1Δ cells were transformed with plasmids encoding DhPmp47, DhMdh3, DhGpd1-GFP, ScGpd1-GFP or empty plasmid."
      }
    ]
  },
  {
    "id": "PMC10619197_multi",
    "image": [
      "images/PMC10619197-f1.png",
      "images/PMC10619197-f2.png",
      "images/PMC10619197-f3.png",
      "images/PMC10619197-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Branched-chain fatty acids affect the expression of fatty acid synthase and C-reactive protein genes in the hepatocyte cell line\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) HepG2 cells non-treated with BCFA. (B) HepG2 cells after treatment with 10 µM 14-MPA. (C) HepG2 cells after treatment with 10 µM 12-MTA. (D) Cell viability after treatment with 14-MPA. (E) Cell viability after treatment with 12-MTA. ○ - individual data points. Three independent experiments were performed and a total number of repetitions (n), summed from all experiments, is indicated in the bars.\n\nFigure 2: Figure 2. Concentration of BCFAs in HepG2 cells collected after 48 h of incubation with 10 µM 14-MPA or 10 µM 12-MTA. The analysis conducted in the samples prepared by pooling three individual cell cultures from a single experiment.\n\nFigure 3: Figure 3. (A) Cells treated with 14-MPA. (B) Cells treated with 12-MTA. Data in (A,B) are presented as means ± SEM; statistical test used: single-factor ANOVA with Tukey post-hoc test for unequal group size; *P-value<0.05 in comparison with control cells, ♦P-value<0.05 in comparison with cells treated with 1 μM BCFA; *P-value<0.05 in comparison with cells treated with 2 μM BCFA; ○ - individual data points. Three independent experiments were performed and a total number of repetitions (n), summed from all experiments, is indicated in the bars. Concentrations 1 and 2 μM of 14-MPA were used in two of the independent experiments only, with one repetition per experiment.\n\nFigure 4: Figure 4. (A) CRP mRNA levels. (B) IL-6 mRNA levels. Data in (A,B) are presented as means ± SEM; statistical test used: single-factor ANOVA with Tukey post-hoc test for unequal group size; *P-value<0.05 in comparison with control cells, ♦P-value<0.05 in comparison with cells treated with 1 μM BCFA; *P-value<0.05 in comparison with cells treated with 2 μM BCFA. Three independent experiments were performed and a total number of repetitions (n), summed from all experiments, is indicated in the bars. For IL-6 gene expression analysis, one repetition for 1 μM of 14-MTA was excluded (outlier), so the total number of repetitions in this case is two."
      }
    ]
  },
  {
    "id": "PMC10652488_multi",
    "image": [
      "images/PMC10652488-f1.png",
      "images/PMC10652488-f2.png",
      "images/PMC10652488-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Abnormal activation of MAPKs pathways and inhibition of autophagy in a group of patients with Zellweger spectrum disorders and X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. p-p38 is upregulated in PBMC of ZSDs and X-ALD patients. Representative immunoblots for p-p38 in control (CTL) and in ZSD and X-ALD patients. Protein levels are normalized respect to GAPDH. The histograms below show the p-p38 levels relative to CTL\n\nFigure 2: Figure 2. p-JNK is upregulated in PBMC of ZSDs and X-ALD patients. Representative immunoblots for p-JNK in control (CTL) and in ZSD and X-ALD patients. Protein levels are normalized respect to GAPDH. The histograms below show the p-JNK levels relative to CTL\n\nFigure 3: Figure 3. LC3. Autophagy is downregulated in PBMC of ZSDs and X-ALD patients. Representative immunoblots for LC3-I and LC3-II in control (CTL) and in X-ALD and ZSDs patients. Protein levels are normalized respect to GAPDH. The histograms below show the LC3-II/LC3-I ratio levels relative to CTL"
      }
    ]
  },
  {
    "id": "PMC10659266_multi",
    "image": [
      "images/PMC10659266-f1.png",
      "images/PMC10659266-f2.png",
      "images/PMC10659266-f3.png",
      "images/PMC10659266-f4.png",
      "images/PMC10659266-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A novel mouse model of cerebral adrenoleukodystrophy highlights NLRP3 activity in lesion pathogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A, E) Axial MR imaging from two children with cALD highlight areas of demyelination (T2 FLAIR intensities) and vascular breakdown (contrast enhancement). Red boxes indicate representative areas sampled for histopathological images. (B-K) LFB + H&E histology of postmortem tissue from cALD patients with varying severity of demyelination in lesions. Histology highlights regions of extensive, active demyelination (C, G) and early gliosis (D, H) compared to healthy, unaffected control (I-K). B, F, I: 2X magnification of representative sections, scale bar: 400um. C, D, G, H, J, K: 20X magnificent of respective sections, scale bar: 100um. (L) Immunohistochemistry of representative demyelinated cALD lesion shows infiltration of microglia/ macrophages (CD163), and to a lesser extent T-cells (CD3) within the lesion. B cells (CD20) are present in lower abundance. Scale bar for 2X magnification represents 400µm; black boxes indicate corresponding areas shown at 20X magnification. Scale bar for 20X magnification represents 100µm\n\nFigure 2: Figure 2. (A) IL-18 levels are significantly higher in the CSF of children with cALD compared to unaffected, age-matched controls (**: p < 0.001). (B) Within areas of early brain demyelination in cALD (green arrowheads), the distribution of IL-18+ cells align with microglia (Iba1) rather than astrocytes (GFAP). Black boxes indicate corresponding areas shown at 20X magnification. (C) Immunofluorescence highlights co-localization of IL-18 with perivascular microglia/macrophages (Iba1+) and, to a lesser extent, intraparenchymal astrocytes (GFAP). Insets highlight co-localization at 60X magnification. 2X magnification scale bar: 400µm. 20X magnification scale bar: 100µm.\n\nFigure 3: Figure 3. (A) A graphical overview summarizes the treatment regimens and timelines for the four experimental arms applied to both Abcd1-null and wild-type C57BL/6J mice. (B) Clinical disability scores were higher among mice in CPZ/EAE arm (n=12–13/genotype) compared with EAE (n=6–7/genotype); mice in the CPZ arm (n=6) had no measurable disability. (C) Clinical scores in wild-type and Abcd1y/- mice in CPZ/EAE models (n=12–13 male mice in each group). (D, E) Abcd1y/− mice induced with CPZ/EAE had significantly higher disability than mice treated with EAE alone. The bar graph represents the mean ± SEM of motor disability scores. The unpaired t-test determined the significant difference between the two groups; p*<0.05 was considered significant. CPZ: Cuprizone; EAE: experimental autoimmune encephalomyelitis; ROI: region of interest\n\nFigure 4: Figure 4. (A) Representative coronal MRI images demonstrate high T2 signal in the MCC (red square) of Abcd1y/− induced with CPZ/EAE resembling. the characteristic pattern seen in human cALD MRI (far right). (B) A comparison of quantitative analyses of T2-weighted MRI of the MCC shows a higher T2 signal in the MCC (highlighted by red box) of Abcd1y/− mice induced with CPZ/EAE, similar to early lesions in human cALD. (C) Representative histologic sections of MBP staining in the MCC depict differing levels of demyelination across experimental arms. White box denotes representative areas of quantitative analysis. Scale bars, 50µm. (D) Quantitative analysis of MBP intensity in the MCC shows high levels of demyelination in Abcd1y/− mice induced with CPZ/EAE. (E) Representative images of post-gadolinium T1-weighted MRI in show focal areas of gadolinium enhancement (yellow arrows) in Abcd1y/− mice treated with CPZ/EAE, similar to characteristic findings in human cALD. (F, G) Representative images and quantitative measures of immunostaining for fibrinogen, a marker of BBB disruption, show high levels in Abcd1y/− mice induced with CPZ/EAE. (H, I) Similarly, representative and quantitative analysis of immunostaining for gp91-phox, a marker of oxidative stress, are highest a in Abcd1y/− mice induced with CPZ/EAE. Scale bars, 200 µm. All bar graphs display the mean ± SD. Statistical comparisons via one-way. MCC: medial corpus callosum; MBP: myelin basic protein; CPZ: cuprizone; EAE: experimental autoimmune encephalomyelitis.\n\nFigure 5: Figure 5. (A) The cartoons illustrate the spatial distribution of perivascular cuffs in a representative mouse, as determined by DAPI staining, across experimental arms. Representative histologic images depict perivascular infiltration of (B) macrophage/microglia (CD68 staining) (C) T cells (CD3e staining) and B cells (B220 staining) in the Abcd1y/− mice induced with CPZ/EAE similar to human cALD. Scale bars, 50 µm. Quantitative assessment shows high levels of (D) total immune cells, (E) macrophages/microglia, (F) T cells, and (G) B cells in Abcd1y/− mice induced with CPZ/EAE. Bar graphs display the mean ± SD. Brown-Forsythe Welch ANOVA test determined the significance between the groups. CPZ: cuprizone; EAE: experimental autoimmune encephalomyelitis."
      }
    ]
  },
  {
    "id": "PMC10659266_multi_2",
    "image": [
      "images/PMC10659266-f6.png",
      "images/PMC10659266-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"A novel mouse model of cerebral adrenoleukodystrophy highlights NLRP3 activity in lesion pathogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Representative histologic sections show (A) CD68 and (B) GFAP staining across the four experimental arms. The white square highlights the MCC. Quantitative analysis of the MCC shows elevated (C) CD68+ cell count and (D) GFAP grading in the CPZ and CPZ/EAE experimental arms. Bar graphs display the mean ± SD. Statistics calculated via one-way ANOVA. Scale bar: 400µm. CPZ: cuprizone; EAE: experimental autoimmune encephalomyelitis; MCC: medial corpus callosum.\n\nFigure 7: Figure 7. Co-staining with CD68 (macrophage/microglia) and PLP (myelin) indicate macrophage/microglia infiltration and demyelination in perivascular white matter. The images represent (A) grade II and (B) grade IV perivascular infiltration of macrophage/microglia with associated demyelination. White arrows indicate perivascular regions with associated loss of myelin. (C) The images display phagocytosis of myelin by macrophage/microglia. Inset depicts higher magnification of myelin phagocytosis in the corresponding region. (D) IL-18 expression in perivascular macrophage/microglia, similar to human cALD. Arrows indicate colocalization. Inset depicts a higher magnification of IL18 and CD68 colocalization in the corresponding region. Scale bar: 50µm. CPZ: cuprizone, EAE; experimental autoimmune encephalomyelitis; PLP: proteolipid protein."
      }
    ]
  },
  {
    "id": "PMC10660695_multi",
    "image": [
      "images/PMC10660695-f1.png",
      "images/PMC10660695-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Diagnosing X-Linked Adrenoleukodystrophy after Implementation of Newborn Screening: A Reference Laboratory Perspective\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A visual summary of VLCFA testing results reported by our reference laboratory between 1 January 2012 and 30 July 2022. PBD-ZSD = peroxisome biogenesis defects-Zellweger spectrum disorders; PD = peroxisomal disorders; (*) samples sent to monitor VLCFA levels in known patients.\n\nFigure 2: Figure 2. Age distribution of patients with ALDP deficiency (A,B) or PBD-ZSD (C,D) based on reason for referral."
      }
    ]
  },
  {
    "id": "PMC10691693_multi",
    "image": [
      "images/PMC10691693-f1.png",
      "images/PMC10691693-f2.png",
      "images/PMC10691693-f3.png",
      "images/PMC10691693-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The subset of peroxisomal tail-anchored proteins do not reach peroxisomes via ER, instead mitochondria can be involved\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Immunoblotting analysis of PEX3 KO or PEX19 KO HEK293T cells generated by CRISPR Cas9 approach. WT, wild type, parental HEK293T cells were used as a control. Actin was used as a loading control. (B) Confocal immunofluorescence imaging showed the absence of peroxisomes in PEX3 KO or PEX19 KO HEK293T cells. WT, wild type, parental HEK293T cells were used as a control. Anti-catalase antibody was used to visualize peroxisomes (magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (C) Schematic view of the OPG-fused constructs used in glycosylation assays. EGFP-YgiM(TA) without OPG was used as a control. (D) Intracellular localization of the constructs used in glycosylation assay analyzed by confocal immunofluorescence imaging. WT HEK293T were transiently transfected with EGFP-SEC61β-OPG, EGFP-YgiM(TA) or EGFP-YgiM(TA)-OPG constructs for 24 h. Anti-GFP antibody was used to visualize the EGFP constructs (green). Calnexin was used to visualize ER (magenta), catalase was used to visualize peroxisomes (PO, magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (E) TA substrates with or without OPG tag were transfected to WT, PEX3 KO or PEX19 KO HEK293T cells. Cell lysates were analyzed by immunoblotting using anti-GFP antibody. Glycosylation bands are indicated by asterisk. Glycosylation was confirmed by loss of the band after addition of glycosidase, PNGase-F. Ponceau staining was used as a loading control.\n\nFigure 2: Figure 2. (A and B) Localization of EGFP-YgiM(TA) stably expressed in WT, PEX3 KO or PEX19 KO HEK293T cells. (A) Confocal immunofluorescence imaging showing EGFP-YgiM(TA) localization. Anti-GFP antibody was used to visualize EGFP-YgiM(TA) (green). Anti-catalase antibody was used to label peroxisomes (PO, magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (B) Confocal immunofluorescence imaging showing EGFP-YgiM(TA) localization. Anti-GFP antibody was used to visualize EGFP-YgiM(TA) (green). Anti-ATPIF1 antibody was used to label mitochondria (MITO, magenta) and anti-calnexin antibody was used to label ER (magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (C) Colocalization of EGFP-YgiM(TA) with catalase, calnexin or ATPIF1 was analyzed by Mander’s overlap coefficient using confocal microscopy images. For each sample 5–6 fields of view were analyzed, each view captured approximately 50 cells. The data are presented as mean ± SD. **P < 0.01, ***P < 0.001 as compared to WT cells (unpaired t-tests, n = 5–6). (D) Electron microscopy imaging of WT, PEX3 KO or PEX19 KO HEK293T cells stably expressing EGFP-YgiM(TA). Anti-GFP immunogold staining was used to visualize EGFP-YgiM(TA). Scale bars, 500 nm. (E) Stereological analysis of electron microscopy images was used to identify relative labeling index of YgiM(TA) in peroxisomes or mitochondria. If no association with mitochondria or peroxisomes was observed, the gold particle label was assigned to the ’other’ category. The ’other’ category includes all other organelles (except mitochondria and peroxisomes) and cytosol. NC, negative control, cells not expressing EGFP-YgiM(TA) construct used for quantitation of background signal from immunogold labeling. Area above the green surface depicts non-randomly distributed gold particles. For each cell line 15 cells were analyzed (2 images per cell with the area of 300 μm2).\n\nFigure 3: Figure 3. (A–C) Localization of ACBD5 in WT, PEX3 KO or PEX19 KO HEK293T cells. (A) Confocal immunofluorescence imaging showing ACBD5 localization. Anti-ACBD5 antibody was used to visualize ACBD5 (green), anti-catalase antibody was used to label peroxisomes (PO, magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (B) Confocal immunofluorescence imaging showing ACBD5 localization. Anti-ACBD5 antibody was used to visualize ACBD5 (green), anti-calnexin antibody was used to label ER (magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (C) Confocal immunofluorescence imaging showing ACBD5 localization. Anti-ACBD5 antibody was used to visualize ACBD5 (green), anti-SDHA antibody was used to label mitochondria (MITO, magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (D) Colocalization of ACBD5 with catalase, calnexin or SDHA was analyzed by Mander’s overlap coefficient using confocal microscopy images. For each sample 5–6 fields of view were analyzed, each view captured approximately 50 cells. The data are presented as mean ± SD. **P < 0.01, ***P < 0.001, ns, not significant as compared to WT cells (unpaired t-tests, n = 5–6). (E) Immunoblotting analysis of ACBD5 in WT, PEX3 KO or PEX19 KO HEK293T cells. Actin was used as a loading control.\n\nFigure 4: Figure 4. (A) Schematic representation of the biotinylation experiment. TA constructs fused to AviTag are transfected to the cells expressing BirA in endoplasmic reticulum (ER), peroxisomes (PO) or mitochondria (MITO). Once TA inserts to the specific organelle labeled with BirA, biotin acceptor sequence of the TA, AviTag, is biotinylated by BirA. (B) Schematic view of the constructs used to generate BirA-expressing cell lines and TA constructs fused to AviTag. (C) Doxycycline-inducible BirA constructs targeted to ER (ER-BirA), mitochondrial intramembrane space (IMS-BirA) or peroxisomes (PO-BirA) were stably introduced into Flp-In™ T-REx™-293 cells. The expression of the constructs was induced by adding of 10 μg / mL doxycycline for 24 h. The intracellular localization of doxycycline-inducible BirA constructs targeted to the specific organelle was analyzed by confocal immunofluorescence imaging. Anti-BirA antibody was used to visualize BirA construct (green), anti-calnexin antibody was used to label ER (magenta), anti-ATPIF1 antibody was used to visualize mitochondria (magenta), anti-catalase antibody was used to label peroxisomes (PO, magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (D) Flp-In™ T-Rex™-293 cells were transiently transfected with EGFP-SEC61β-AviTag or EGFP-YgiM(TA)-AviTag for 24 h. The intracellular localization of AviTag constructs was analyzed by confocal immunofluorescence imaging. Anti-GFP antibody was used to visualize AviTag constructs (green), anti-calnexin antibody was used to label ER (magenta), anti-catalase antibody was used to label peroxisomes (PO, magenta). DAPI (cyan) shows nuclei. Scale bars, 10 μm. (E) Flp-In T-Rex™ HEK293 cells expressing ER-BirA, IMS-BirA or PO-BirA were transiently transfected with ER-targeted TA construct, SEC61β-AviTag, or with peroxisome-targeted TA construct, YgiM(TA)-AviTag. Cell lysates were analyzed by immunoblotting using streptavidin. Bands of ~33 kDa and 39 kDa indicate biotinylated AviTag constructs. Endogenous biotinylated mitochondrial proteins are shown by asterisks. Actin was used as a loading control. NT, non-transfected control. Fig (A) was created with BioRender.com."
      }
    ]
  },
  {
    "id": "PMC10698565_multi",
    "image": [
      "images/PMC10698565-f1.png",
      "images/PMC10698565-f2.png",
      "images/PMC10698565-f3.png",
      "images/PMC10698565-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cholic acid increases plasma cholesterol in Smith-Lemli-Opitz syndrome: A pilot study\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Abbreviated biochemical pathway for cholesterol metabolism. Dashed arrows indicate regulatory relationships for feedback inhibition of cholesterol synthesis or bile acid synthesis. Bile acids stimulate dietary cholesterol absorption.\n\nFigure 2: Figure 2. Change in plasma sterols on cholic acid supplementation. Asterisks designates Subject 1.\n\nFigure 3: Figure 3. Change in plasma oxysterols on cholic acid supplementation. Asterisks designates Subject 1.\n\nFigure 4: Figure 4. Body weight change on cholic acid. Baseline body weight varied from 8.9 kg to 84.1 kg."
      }
    ]
  },
  {
    "id": "PMC10702803_multi",
    "image": [
      "images/PMC10702803-f1.png",
      "images/PMC10702803-f2.png",
      "images/PMC10702803-f2-2.png",
      "images/PMC10702803-f4.png",
      "images/PMC10702803-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MAPL loss dysregulates bile and liver metabolism in mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. HEK 293T‐REX (tetracycline‐regulatable expression) cells stably expressing an inducible Tet‐ON fusion construct MAPL‐Flag‐BirA, or Flag‐BirA only, were treated with Dox for 24 h in the presence of biotin, and biotinylated proteins were isolated with streptavidin beads for identification by mass spectrometry. Top hits, by peptide count, are shown.Starting material (SM) and MAPL immunoprecipitated (IP) fractions obtained from crude liver extracts were probed for ABCD3, MAPL and Hsp60.Cytosol and heavy membrane fractions isolated from MAPLf/f and MAPL−/− livers were solubilized and incubated with SIM beads, and elution fractions probed for ABCD3, DRP1, Hsp70 and MAPL (Cyt = cytosolic fraction, HM = heavy membrane fraction).Heavy membrane fractions isolated from livers of MAPLf/f and MAPL−/− animals' tail‐vein injected with adenovirus expressing MAPL‐Flag, MAPL‐ΔRING‐Flag or empty virus (Ad‐rtTA) were solubilized and incubated with SIM beads. Elution fractions were probed for ABCD3, SUMO1 and MAPL (top panel). Quantification from three independent experiments of ABCD3 signals of the heavy membrane SIM‐beads elution fraction from livers isolated from rescued mice (lower panel).Two hundred fifty microgram of solubilized protein (from MAPLf/f and MAPL−/− livers) were separated on a 10–50% (w/v) sucrose gradient. Twelve different fractions, as well as the resuspended pellet (P) were analyzed by immunoblot. ABCD3 signals from MAPLf/f and MAPL−/− livers in the different fractions were quantified and plotted as percentage of the total signal, from three biological replicates. *P < 0.05 in a one‐way ANOVA. Data are represented as mean ± SEM. HEK 293T‐REX (tetracycline‐regulatable expression) cells stably expressing an inducible Tet‐ON fusion construct MAPL‐Flag‐BirA, or Flag‐BirA only, were treated with Dox for 24 h in the presence of biotin, and biotinylated proteins were isolated with streptavidin beads for identification by mass spectrometry. Top hits, by peptide count, are shown. Starting material (SM) and MAPL immunoprecipitated (IP) fractions obtained from crude liver extracts were probed for ABCD3, MAPL and Hsp60. Cytosol and heavy membrane fractions isolated from MAPLf/f and MAPL−/− livers were solubilized and incubated with SIM beads, and elution fractions probed for ABCD3, DRP1, Hsp70 and MAPL (Cyt = cytosolic fraction, HM = heavy membrane fraction). Heavy membrane fractions isolated from livers of MAPLf/f and MAPL−/− animals' tail‐vein injected with adenovirus expressing MAPL‐Flag, MAPL‐ΔRING‐Flag or empty virus (Ad‐rtTA) were solubilized and incubated with SIM beads. Elution fractions were probed for ABCD3, SUMO1 and MAPL (top panel). Quantification from three independent experiments of ABCD3 signals of the heavy membrane SIM‐beads elution fraction from livers isolated from rescued mice (lower panel). Two hundred fifty microgram of solubilized protein (from MAPLf/f and MAPL−/− livers) were separated on a 10–50% (w/v) sucrose gradient. Twelve different fractions, as well as the resuspended pellet (P) were analyzed by immunoblot. ABCD3 signals from MAPLf/f and MAPL−/− livers in the different fractions were quantified and plotted as percentage of the total signal, from three biological replicates. *P < 0.05 in a one‐way ANOVA. Data are represented as mean ± SEM. Source data are available online for this figure.\n\nFigure 2: Figure 2. Representative immunoblot of total lysate and streptavidin‐beads pull‐down fractions of HEK‐293T‐REX cells expressing Flag‐MAPL‐BirA or Flag‐BirA (as control) incubated with biotin and probed for ABCD3, DRP1, MAPL and beta‐actin.Quantification from three independent experiments of ABCD3 signals of the heavy membrane SIM‐beads elution fraction (Fig 1C). *P < 0.05 in an unpaired two‐tailed t‐test.qRT‐PCR investigating ABCD3 mRNA levels in livers of four different mice (2‐month‐old males).Representative immunoblots from whole‐cell liver extracts probed for ABCD3, DRP1 and Mfn2 (Left panel). ABCD3, Drp1 and Mfn2 signals were quantified (n = 3 for each genotype, right panel).Representative immunoblots from whole‐cell liver extracts probed for PEX14, ACOX1 and SCP2 (Left panel). PEX14, ACOX1 and SCP2 signals were quantified (n = 3 for each genotype, right panel). Representative immunoblot of total lysate and streptavidin‐beads pull‐down fractions of HEK‐293T‐REX cells expressing Flag‐MAPL‐BirA or Flag‐BirA (as control) incubated with biotin and probed for ABCD3, DRP1, MAPL and beta‐actin. Quantification from three independent experiments of ABCD3 signals of the heavy membrane SIM‐beads elution fraction (Fig 1C). *P < 0.05 in an unpaired two‐tailed t‐test. qRT‐PCR investigating ABCD3 mRNA levels in livers of four different mice (2‐month‐old males). Representative immunoblots from whole‐cell liver extracts probed for ABCD3, DRP1 and Mfn2 (Left panel). ABCD3, Drp1 and Mfn2 signals were quantified (n = 3 for each genotype, right panel). Representative immunoblots from whole‐cell liver extracts probed for PEX14, ACOX1 and SCP2 (Left panel). PEX14, ACOX1 and SCP2 signals were quantified (n = 3 for each genotype, right panel). Data are represented as mean ± SEM.\n\nFigure 2: Figure 2. Total serum bile acids were quantified as described in materials and methods (n = 8 for each genotype, six females (circles) and two males (squares), 2–6 months old). **P < 0.01 in an unpaired two‐tailed t‐test.Total serum bile acids in tail vein injected animals were quantified as described in materials and methods (n = 6 with four females and two males, n = 7 with four females and three males, n = 4 with two females and two males and n = 5 with two females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old).Bile acid precursors, as well as unconjugated and conjugated primary and secondary bile acids, were quantified from liver (n = 8 for each genotype, 2‐month‐old males). THCA and DHCA: tri‐ and dihydroxycholestanoic acid; CA: cholic acid; a‐MCA, b‐MCA, w‐MCA and d‐MCA: α‐, β‐, γ‐ and δ‐muricholic acid; DCA: deoxycholic acid; MCA: muricholic acid; HDCA: hyodeoxycholic acid; TDCA: taurodeoxycholic acid; td‐MCA: tauro‐δ‐muricholic acid. *P < 0.05 in an unpaired two‐tailed t‐test.Representative pictures of livers from MAPL f/f and MAPL −/− mice. Hematoxylin and eosin staining. 40× objective. Scale bar: 100 μm.Levels of alanine transaminase (ALT) and aspartate transaminase (AST) (n = 6, 6 month old males).Total bile acid production (μM) in cultured primary hepatocytes isolated from MAPLf/f and MAPL−/− mice. Media was collected after 48 h of culture. N = 5 independent experiments. ***P < 0.001 in an unpaired two‐tailed t‐test.Total bile acid production (μM) in cultured primary hepatocytes isolated from MAPLf/f and MAPL−/− mice. Hepatocytes were transduced with adenoviruses encoding for rTta, MAPL‐Flag or MAPL‐ΔRing‐Flag. N = 3 independent experiments. **P < 0.01 in a one‐way ANOVA test. Total serum bile acids were quantified as described in materials and methods (n = 8 for each genotype, six females (circles) and two males (squares), 2–6 months old). **P < 0.01 in an unpaired two‐tailed t‐test. Total serum bile acids in tail vein injected animals were quantified as described in materials and methods (n = 6 with four females and two males, n = 7 with four females and three males, n = 4 with two females and two males and n = 5 with two females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). Bile acid precursors, as well as unconjugated and conjugated primary and secondary bile acids, were quantified from liver (n = 8 for each genotype, 2‐month‐old males). THCA and DHCA: tri‐ and dihydroxycholestanoic acid; CA: cholic acid; a‐MCA, b‐MCA, w‐MCA and d‐MCA: α‐, β‐, γ‐ and δ‐muricholic acid; DCA: deoxycholic acid; MCA: muricholic acid; HDCA: hyodeoxycholic acid; TDCA: taurodeoxycholic acid; td‐MCA: tauro‐δ‐muricholic acid. *P < 0.05 in an unpaired two‐tailed t‐test. Representative pictures of livers from MAPL f/f and MAPL −/− mice. Hematoxylin and eosin staining. 40× objective. Scale bar: 100 μm. Levels of alanine transaminase (ALT) and aspartate transaminase (AST) (n = 6, 6 month old males). Total bile acid production (μM) in cultured primary hepatocytes isolated from MAPLf/f and MAPL−/− mice. Media was collected after 48 h of culture. N = 5 independent experiments. ***P < 0.001 in an unpaired two‐tailed t‐test. Total bile acid production (μM) in cultured primary hepatocytes isolated from MAPLf/f and MAPL−/− mice. Hepatocytes were transduced with adenoviruses encoding for rTta, MAPL‐Flag or MAPL‐ΔRing‐Flag. N = 3 independent experiments. **P < 0.01 in a one‐way ANOVA test. Data are represented as mean ± SEM. Squares represent males whereas circles represent females. Source data are available online for this figure.\n\nFigure 4: Figure 4. A model depicting the generation of the main murine bile acids from THCA and DHCA (tri‐ and dihydroxycholestanoic acids) (G: glyco‐; T: Tauro‐).Levels of alanine transaminase (ALT) and aspartate transaminase (AST), markers of liver damage, were quantified and plotted from serum collected from 6‐month‐old females (n = 5 and n = 6 for MAPL f/f and MAPL −/− , respectively for ALT quantification and n = 6 and n = 7 for MAPL f/f and MAPL −/− , respectively for AST quantification). **P < 0.01 in an unpaired two‐tailed t‐test.The amount of energy present in 3‐month animal feces has been measured using an oxygen bomb calorimeter, as described in material and methods (n = 7 with four females and three males for each genotype). **P < 0.01 in an unpaired two‐tailed t‐test. A model depicting the generation of the main murine bile acids from THCA and DHCA (tri‐ and dihydroxycholestanoic acids) (G: glyco‐; T: Tauro‐). Levels of alanine transaminase (ALT) and aspartate transaminase (AST), markers of liver damage, were quantified and plotted from serum collected from 6‐month‐old females (n = 5 and n = 6 for MAPL f/f and MAPL −/− , respectively for ALT quantification and n = 6 and n = 7 for MAPL f/f and MAPL −/− , respectively for AST quantification). **P < 0.01 in an unpaired two‐tailed t‐test. The amount of energy present in 3‐month animal feces has been measured using an oxygen bomb calorimeter, as described in material and methods (n = 7 with four females and three males for each genotype). **P < 0.01 in an unpaired two‐tailed t‐test. Data are represented as mean ± SEM. Squares represent males whereas circles represent females.\n\nFigure 3: Figure 3. A model depicting the required flux of metabolites between the ER, mitochondria and peroxisomes to facilitate bile acid synthesis in the liver. The initial step of the classical (neutral) pathway is represented with solid arrows, while the alternative (acidic) pathway is represented with dashed arrows. Downstream reactions of the two pathways converge on the same set of enzymes.Immunoblots for CYP27A1, CYP7A1, MAPL and ACTB from liver extracts from three animals of each genotypes (two females, one male), as indicated. Bottom panel is the quantification by densitometry. *P < 0.05 in an unpaired two‐tailed t‐test.mRNA expression of bile acid biosynthesis enzymes in the liver of MAPL−/− mice.qRT‐PCR measuring Hsd3b5 mRNA levels in livers of rescued mice (in triplicate, n = 5 with four females and one male, n = 7 with four females and three males, n = 5 with three females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old).Immunoblots for CYP3A11, CYP4A14 and ACTB from liver extracts from three animals of each genotypes (two females, one male), as indicated. Bottom panel is the quantification by densitometry. *P < 0.05 in an unpaired two‐tailed t‐test.mRNA expression of bile acid detoxification enzymes in the liver of MAPL KO mice.Representative immunoblot of Cyp4A14 protein levels in livers isolated from rescued mice. A model depicting the required flux of metabolites between the ER, mitochondria and peroxisomes to facilitate bile acid synthesis in the liver. The initial step of the classical (neutral) pathway is represented with solid arrows, while the alternative (acidic) pathway is represented with dashed arrows. Downstream reactions of the two pathways converge on the same set of enzymes. Immunoblots for CYP27A1, CYP7A1, MAPL and ACTB from liver extracts from three animals of each genotypes (two females, one male), as indicated. Bottom panel is the quantification by densitometry. *P < 0.05 in an unpaired two‐tailed t‐test. mRNA expression of bile acid biosynthesis enzymes in the liver of MAPL−/− mice. qRT‐PCR measuring Hsd3b5 mRNA levels in livers of rescued mice (in triplicate, n = 5 with four females and one male, n = 7 with four females and three males, n = 5 with three females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). Immunoblots for CYP3A11, CYP4A14 and ACTB from liver extracts from three animals of each genotypes (two females, one male), as indicated. Bottom panel is the quantification by densitometry. *P < 0.05 in an unpaired two‐tailed t‐test. mRNA expression of bile acid detoxification enzymes in the liver of MAPL KO mice. Representative immunoblot of Cyp4A14 protein levels in livers isolated from rescued mice. Data are represented as mean ± SEM. (C, F) Liver RNAseq, n = 5 per group. log2(FC) of MAPL KO versus Control mice is plotted, genes with P‐adjusted value < 0.05 are marked with pink. See also Fig 5 and Dataset EV1. Data are represented as mean ± SEM. Squares represent males whereas circles represent females. Source data are available online for this figure."
      }
    ]
  },
  {
    "id": "PMC10702803_multi_2",
    "image": [
      "images/PMC10702803-f4-2.png",
      "images/PMC10702803-f5.png",
      "images/PMC10702803-f8.png",
      "images/PMC10702803-f6.png",
      "images/PMC10702803-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MAPL loss dysregulates bile and liver metabolism in mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 4: Figure 4. Serum FGF15 measured by ELISA (n = 5 and n = 6 for MAPLf/f and MAPL−/− respectively, 2‐month‐old males).qRT‐PCR measuring Nr1h4 mRNA levels (FXR) in livers of four different mice (2‐month‐old males).Nuclear receptors target gene expression by qRT‐PCR. Livers were harvested from male and female mice fasted (4 h) or fed for 2 h after an overnight fast. N = 4–7 per sex, genotype and timepoint. Representative of two independent cohorts. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001 in a 2way ANOVA test followed by a Sidak posthoc test.Representative immunoblot of ABCB11 protein levels in livers isolated from three animals of each genotype (one female, two males), as indicated.Liver gene expression of muricholic acid‐producing enzyme Cyp2c70. N = 4–7 per sex, genotype and timepoint. Representative of two independent cohorts.Liver gene expression of bile transporters Slco1a1, Slco10a1, Slco1b2. N = 4–7 per sex, genotype and timepoint. Representative of two independent cohorts. *P < 0.05, **P < 0.01, ****P < 0.0001 in a 2way ANOVA test followed by a Sidak posthoc test. Serum FGF15 measured by ELISA (n = 5 and n = 6 for MAPLf/f and MAPL−/− respectively, 2‐month‐old males). qRT‐PCR measuring Nr1h4 mRNA levels (FXR) in livers of four different mice (2‐month‐old males). Nuclear receptors target gene expression by qRT‐PCR. Livers were harvested from male and female mice fasted (4 h) or fed for 2 h after an overnight fast. N = 4–7 per sex, genotype and timepoint. Representative of two independent cohorts. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001 in a 2way ANOVA test followed by a Sidak posthoc test. Representative immunoblot of ABCB11 protein levels in livers isolated from three animals of each genotype (one female, two males), as indicated. Liver gene expression of muricholic acid‐producing enzyme Cyp2c70. N = 4–7 per sex, genotype and timepoint. Representative of two independent cohorts. Liver gene expression of bile transporters Slco1a1, Slco10a1, Slco1b2. N = 4–7 per sex, genotype and timepoint. Representative of two independent cohorts. *P < 0.05, **P < 0.01, ****P < 0.0001 in a 2way ANOVA test followed by a Sidak posthoc test. Data are represented as mean ± SEM. Squares represent males whereas circles represent females. Source data are available online for this figure.\n\nFigure 5: Figure 5. Liver RNAseq of MAPLf/f and MAPL−/− mice, n = 5 per group. See also Dataset EV1. PCA analysis of the dataset.Venn diagram of genes changed in the dataset (log2(FC) > 0.5, P‐adjusted < 0.05).Heatmap of top changes in the dataset (top15 changed (P‐adjusted < 0.05) genes were selected by |log2(FC)| in female and male groups, and non‐overlapping genes from the selection are plotted).Pathway analysis of the top500 up‐ or down‐regulated genes. Terms related to cell cycle process (GO:0022402) are marked with orange, to steroid metabolic process (GO:0008202) in dark blue, and to response to topologically incorrect protein (GO:0035966) in purple.Volcano plot of genes changed in the dataset (log2(FC) > 0.5, P‐adjusted < 0.05). Genes of the cell cycle process (GO:0022402) are marked with orange, of the steroid metabolic process (GO:0008202) in dark blue, and of the response to topologically incorrect protein (GO:0035966) in purple.Expression of APC first‐level interactors (Biogrid gene network database). Genes with P‐adjusted < 0.05 in MAPL−/− compared to MAPLf/f mice are highlighted with color, where intensity corresponds to |log2(FC)|, and blue and red spectrums indicate down‐ and up‐regulated genes, respectively. PCA analysis of the dataset. Venn diagram of genes changed in the dataset (log2(FC) > 0.5, P‐adjusted < 0.05). Heatmap of top changes in the dataset (top15 changed (P‐adjusted < 0.05) genes were selected by |log2(FC)| in female and male groups, and non‐overlapping genes from the selection are plotted). Pathway analysis of the top500 up‐ or down‐regulated genes. Terms related to cell cycle process (GO:0022402) are marked with orange, to steroid metabolic process (GO:0008202) in dark blue, and to response to topologically incorrect protein (GO:0035966) in purple. Volcano plot of genes changed in the dataset (log2(FC) > 0.5, P‐adjusted < 0.05). Genes of the cell cycle process (GO:0022402) are marked with orange, of the steroid metabolic process (GO:0008202) in dark blue, and of the response to topologically incorrect protein (GO:0035966) in purple. Expression of APC first‐level interactors (Biogrid gene network database). Genes with P‐adjusted < 0.05 in MAPL−/− compared to MAPLf/f mice are highlighted with color, where intensity corresponds to |log2(FC)|, and blue and red spectrums indicate down‐ and up‐regulated genes, respectively.\n\nFigure 8: Figure 8. From liver RNAseq (N = 5 per sex and genotype). Volcano plots (left panels) and heat maps (right panels) of peroxisomal (top panels) and mitochondrial (bottom panels) gene expression in the liver of MAPL−/− mice.\n\nFigure 6: Figure 6. Representative immunoblots from liver extracts from three animals of each genotype: PERK auto‐phosphorylation along with the total protein and BIP and CHOP expressions are shown (*: unspecific signal).Representative immunoblots of eIF2α phosphorylation in liver extracts (n = 3).mRNA expression by RNAseq of integrated stress response (ISR) genes in the liver of MAPL−/− mice. Fgf21 mRNA expression measured by qRT‐PCR performed on 3 different mouse tissues isolated from MAPLf/f and MAPL−/− males. N = 3 different mice per genotype. *P < 0.05, **P < 0.01, ***P < 0.001 in an unpaired two‐tailed t‐test.Representative immunoblots of increased FGF21 protein levels in liver from three pairs of mice from each strain.Serum FGF21 was quantified by ELISA (n = 5 for each genotype, 2‐month‐old males). **P < 0.01 in an unpaired two‐tailed t‐test.Representative immunoblots from different tissues whole‐cell extracts from one male of each genotype: PERK auto‐phosphorylation, as well as BIP and CHOP expression are shown (Sto: stomach, *: remaining beta‐actin signal).Serum FGF21 was quantified by ELISA from tail vein injected adenoviral rescued mice (n = 4 with two females and two males, n = 4 with two females and two males, n = 3 with two females and one male and n = 3 with one female and two males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). *P < 0.05 in a one‐way ANOVA test.Liver Fgf21 gene expression by qRT‐PCR on livers of rescued mice (in triplicate, n = 7 with four females and three males, n = 7 with four females and three males, n = 5 with three females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). **P < 0.01 in a Kruskal‐Wallis test.Representative immunoblot from rescued liver extracts probed for Fgf21, CHOP, P‐eIF2α and eIF2α as indicated (*: unspecific signal). Representative immunoblots from liver extracts from three animals of each genotype: PERK auto‐phosphorylation along with the total protein and BIP and CHOP expressions are shown (*: unspecific signal). Representative immunoblots of eIF2α phosphorylation in liver extracts (n = 3). mRNA expression by RNAseq of integrated stress response (ISR) genes in the liver of MAPL−/− mice. Fgf21 mRNA expression measured by qRT‐PCR performed on 3 different mouse tissues isolated from MAPLf/f and MAPL−/− males. N = 3 different mice per genotype. *P < 0.05, **P < 0.01, ***P < 0.001 in an unpaired two‐tailed t‐test. Representative immunoblots of increased FGF21 protein levels in liver from three pairs of mice from each strain. Serum FGF21 was quantified by ELISA (n = 5 for each genotype, 2‐month‐old males). **P < 0.01 in an unpaired two‐tailed t‐test. Representative immunoblots from different tissues whole‐cell extracts from one male of each genotype: PERK auto‐phosphorylation, as well as BIP and CHOP expression are shown (Sto: stomach, *: remaining beta‐actin signal). Serum FGF21 was quantified by ELISA from tail vein injected adenoviral rescued mice (n = 4 with two females and two males, n = 4 with two females and two males, n = 3 with two females and one male and n = 3 with one female and two males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). *P < 0.05 in a one‐way ANOVA test. Liver Fgf21 gene expression by qRT‐PCR on livers of rescued mice (in triplicate, n = 7 with four females and three males, n = 7 with four females and three males, n = 5 with three females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). **P < 0.01 in a Kruskal‐Wallis test. Representative immunoblot from rescued liver extracts probed for Fgf21, CHOP, P‐eIF2α and eIF2α as indicated (*: unspecific signal). Data are represented as mean ± SEM. Squares represent males whereas circles represent females. Source data are available online for this figure.\n\nFigure 10: Figure 10. Quantification of phospho‐PERK, CHOP and phospho‐eIF2α signals presented in Fig 6A and B immunoblots (n = 3 different mouse for each genotype). *P < 0.05, **P < 0.01 in an unpaired two‐tailed t‐test.Quantification of Fgf21 signals presented in Fig 6E (n = 3 for each genotype).Circulating and liver corticosterone levels were quantified as described in materials and methods (n = 8 for each genotpye, 2‐month‐old males). ***P < 0.001 in an unpaired two‐tailed t‐test.Quantification of FGF21, CHOP, phospho‐eIF2α and eIF2α signals presented in Fig 6J (n = 5, 5, 3 and 4 for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). *P < 0.05, **P < 0.01 in a Kruskal‐Wallis test.Representative immunoblot of CHOP protein expression of livers isolated from MAPLf/f and MAPL−/− animals injected or not with the empty virus rtTA. Quantification of phospho‐PERK, CHOP and phospho‐eIF2α signals presented in Fig 6A and B immunoblots (n = 3 different mouse for each genotype). *P < 0.05, **P < 0.01 in an unpaired two‐tailed t‐test. Quantification of Fgf21 signals presented in Fig 6E (n = 3 for each genotype). Circulating and liver corticosterone levels were quantified as described in materials and methods (n = 8 for each genotpye, 2‐month‐old males). ***P < 0.001 in an unpaired two‐tailed t‐test. Quantification of FGF21, CHOP, phospho‐eIF2α and eIF2α signals presented in Fig 6J (n = 5, 5, 3 and 4 for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). *P < 0.05, **P < 0.01 in a Kruskal‐Wallis test. Representative immunoblot of CHOP protein expression of livers isolated from MAPLf/f and MAPL−/− animals injected or not with the empty virus rtTA. Data are represented as mean ± SEM. Squares represent males whereas circles represent females."
      }
    ]
  },
  {
    "id": "PMC10702803_multi_3",
    "image": [
      "images/PMC10702803-f7.png",
      "images/PMC10702803-f12.png",
      "images/PMC10702803-f8-2.png",
      "images/PMC10702803-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MAPL loss dysregulates bile and liver metabolism in mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. Body weight (g) of male mice fed with normal chow; MAPLf/f (n = 6), and MAPL−/− (n = 9).Body weight (g) of MAPLf/f (n = 8) and MAPL−/− (n = 7) male mice. They were fed normal chow for 5 months (dotted lines), or for 3 months followed by 2 months of a 60% fat diet (solid lines, diet change indicated by HFD arrow).Body weight (g, left panel) or length (cm, right panel) of 7‐month‐old MAPLf/f (n = 4 for both parameter) or MAPL−/− (n = 7 for body weight and n = 4 for length) male mice. ****P < 0.0001 in an unpaired two‐tailed t‐test.Wet weight of organs including liver, kidney, gastrocnemius muscle, epididymal white fat (WAT) and interscapular brown fat (BAT) isolated from 7‐month‐old male MAPLf/f (n = 4) or MAPL−/− (n = 7) mice. **P < 0.01 in an unpaired two‐tailed t‐test.Representative pictures of white adipocytes from MAPLf/f and MAPL−/− mice. Hematoxylin and eosin staining, 40× objective. Scale bar: 100 μm.Representative immunoblots of Ucp1 from WAT and BAT whole‐cell extracts from three different pairs of mice (n = 3).Insulin tolerance test in male MAPLf/f (n = 7) and MAPL−/− (n = 7) mice. Insulin (0.5 U/kg) was injected intraperitoneally following a 4 h fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA analysis showed a statistically significant difference between genotypes (P = 0.005).Glucose tolerance test in male MAPLf/f (n = 8) and MAPL−/− (n = 8) mice. Glucose (2 g/kg) was injected intraperitoneally following an overnight fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA analysis showed a statistically significant difference between genotypes (P = 0.0043).Insulinemia (ng/ml) measured by ELISA in MAPLf/f (n = 4 females and n = 4 males) and MAPL−/− (n = 4 females and n = 4 males) mice. **P < 0.01 in an unpaired two‐tailed t‐test.Insulinemia (ng/ml) measured by ELISA from tail vein injected adenoviral rescued mice (n = 6 with three females and three males, n = 7 with four females and three males, n = 5 with three females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). Body weight (g) of male mice fed with normal chow; MAPLf/f (n = 6), and MAPL−/− (n = 9). Body weight (g) of MAPLf/f (n = 8) and MAPL−/− (n = 7) male mice. They were fed normal chow for 5 months (dotted lines), or for 3 months followed by 2 months of a 60% fat diet (solid lines, diet change indicated by HFD arrow). Body weight (g, left panel) or length (cm, right panel) of 7‐month‐old MAPLf/f (n = 4 for both parameter) or MAPL−/− (n = 7 for body weight and n = 4 for length) male mice. ****P < 0.0001 in an unpaired two‐tailed t‐test. Wet weight of organs including liver, kidney, gastrocnemius muscle, epididymal white fat (WAT) and interscapular brown fat (BAT) isolated from 7‐month‐old male MAPLf/f (n = 4) or MAPL−/− (n = 7) mice. **P < 0.01 in an unpaired two‐tailed t‐test. Representative pictures of white adipocytes from MAPLf/f and MAPL−/− mice. Hematoxylin and eosin staining, 40× objective. Scale bar: 100 μm. Representative immunoblots of Ucp1 from WAT and BAT whole‐cell extracts from three different pairs of mice (n = 3). Insulin tolerance test in male MAPLf/f (n = 7) and MAPL−/− (n = 7) mice. Insulin (0.5 U/kg) was injected intraperitoneally following a 4 h fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA analysis showed a statistically significant difference between genotypes (P = 0.005). Glucose tolerance test in male MAPLf/f (n = 8) and MAPL−/− (n = 8) mice. Glucose (2 g/kg) was injected intraperitoneally following an overnight fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA analysis showed a statistically significant difference between genotypes (P = 0.0043). Insulinemia (ng/ml) measured by ELISA in MAPLf/f (n = 4 females and n = 4 males) and MAPL−/− (n = 4 females and n = 4 males) mice. **P < 0.01 in an unpaired two‐tailed t‐test. Insulinemia (ng/ml) measured by ELISA from tail vein injected adenoviral rescued mice (n = 6 with three females and three males, n = 7 with four females and three males, n = 5 with three females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). Data are represented as mean ± SEM. Squares represent males whereas circles represent females. Source data are available online for this figure.\n\nFigure 12: Figure 12. Female mice fed with normal chow were weighed weekly; MAPLf/f (n = 7) and MAPL−/− (n = 10).MAPLf/f and MAPL−/− (n = 8 for each genotype) females were fed with normal chow for 5 months (dotted lines), or for 3 months followed by 2 months of 60% fat chow (solid lines, diet change indicated by HFD arrow).Body weight (g, left panel) and length (cm, right panel) of 7‐month‐old MAPLf/f (n = 4 for body weight and n = 3 for length) and MAPL−/− (n = 2) female mice. **P < 0.01 in an unpaired two‐tailed t‐test.Wet weight of organs including liver, kidney, gastrocnemius muscle, epididymal white fat (WAT) and interscapular brown fat (BAT) isolated from 7‐month‐old MAPLf/f (n = 4) or MAPL−/− (n = 2) female mice.White adipose tissue gene expression performed by qRT‐PCR. N = 3, in triplicate, 2‐month‐old MAPLfl/fl and MAPL−/− male mice.Insulin tolerance test in MAPLf/f (n = 8), MAPL−/− (n = 8) female mice. Insulin (0.5 U/kg) was injected intraperitoneally after a 2 h fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA analysis for a difference between genotypes P = 0.0135.Glucose tolerance test in MAPLf/f (n = 8), MAPL−/− (n = 8) female mice. Glucose (2 g/kg) was injected intraperitoneally after an overnight fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA for a difference between genotypes P = 0.0903.Liver glycogen measured enzymatically in male MAPL f/f (n = 3), MAPL −/− (n = 3) mice. **P < 0.01 in an unpaired two‐tailed t‐test.Survival curve of MAPLf/f (n = 11) and MAPL−/− (n = 10) female mice.Cancer‐free survival curve of MAPLf/f (n = 11) and MAPL−/− (n = 10) female mice. Female mice fed with normal chow were weighed weekly; MAPLf/f (n = 7) and MAPL−/− (n = 10). MAPLf/f and MAPL−/− (n = 8 for each genotype) females were fed with normal chow for 5 months (dotted lines), or for 3 months followed by 2 months of 60% fat chow (solid lines, diet change indicated by HFD arrow). Body weight (g, left panel) and length (cm, right panel) of 7‐month‐old MAPLf/f (n = 4 for body weight and n = 3 for length) and MAPL−/− (n = 2) female mice. **P < 0.01 in an unpaired two‐tailed t‐test. Wet weight of organs including liver, kidney, gastrocnemius muscle, epididymal white fat (WAT) and interscapular brown fat (BAT) isolated from 7‐month‐old MAPLf/f (n = 4) or MAPL−/− (n = 2) female mice. White adipose tissue gene expression performed by qRT‐PCR. N = 3, in triplicate, 2‐month‐old MAPLfl/fl and MAPL−/− male mice. Insulin tolerance test in MAPLf/f (n = 8), MAPL−/− (n = 8) female mice. Insulin (0.5 U/kg) was injected intraperitoneally after a 2 h fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA analysis for a difference between genotypes P = 0.0135. Glucose tolerance test in MAPLf/f (n = 8), MAPL−/− (n = 8) female mice. Glucose (2 g/kg) was injected intraperitoneally after an overnight fast and blood glucose was measured at indicated times. Repeated Measures 2way ANOVA for a difference between genotypes P = 0.0903. Liver glycogen measured enzymatically in male MAPL f/f (n = 3), MAPL −/− (n = 3) mice. **P < 0.01 in an unpaired two‐tailed t‐test. Survival curve of MAPLf/f (n = 11) and MAPL−/− (n = 10) female mice. Cancer‐free survival curve of MAPLf/f (n = 11) and MAPL−/− (n = 10) female mice. Data are represented as mean ± SEM. Squares represent males whereas circles represent females.\n\nFigure 8: Figure 8. Representative pictures of Ki67 liver staining (top panel) and its quantification (lower panel) in MAPLf/f and MAPL−/− mice (n = 6 males, 2‐ to 6‐month‐old animals). 20× objective. Scale bar: 200 μm. ***P < 0.001 in an unpaired two‐tailed t‐test.qRT‐PCR investigating H19 mRNA levels in livers of rescued mice (in triplicate, n = 7 with four females and three males, n = 7 with four females and three males, n = 6 with four females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). *P < 0.05 in a Kruskal‐Wallis test.Representative pictures of Ki67 duodenum staining (top panel) and its quantification of crypt length from duodenum, jejunum and ileum (lower panel) in MAPLf/f and MAPL−/− mice (n = 2 females n = 1–2 males, 2‐ to 6‐month‐old animals). 20× objective. Scale bar: 200 μm. *P < 0.05, ***P < 0.001 in an unpaired two‐tailed t‐test.Representative results (left panel) of [18F]FDG micro‐PET analysis performed on 6‐month‐old males fed with normal chow as described in material and methods (n = 4 for each genotype). Standard uptake value is the ratio of the tissue radioactivity concentration and the injected radioactivity, divided by the body weight. LV: left ventricle, SM: skeletal muscle (right panel). *P < 0.05 in an unpaired two‐tailed t‐test. Representative pictures of Ki67 liver staining (top panel) and its quantification (lower panel) in MAPLf/f and MAPL−/− mice (n = 6 males, 2‐ to 6‐month‐old animals). 20× objective. Scale bar: 200 μm. ***P < 0.001 in an unpaired two‐tailed t‐test. qRT‐PCR investigating H19 mRNA levels in livers of rescued mice (in triplicate, n = 7 with four females and three males, n = 7 with four females and three males, n = 6 with four females and two males and n = 6 with three females and three males, for MAPLf/f + rtTA, MAPL−/− + rtTA, MAPL−/− + MAPL‐Flag and MAPL−/− + MAPL‐ΔRING‐Flag, respectively, 2–3 months old). *P < 0.05 in a Kruskal‐Wallis test. Representative pictures of Ki67 duodenum staining (top panel) and its quantification of crypt length from duodenum, jejunum and ileum (lower panel) in MAPLf/f and MAPL−/− mice (n = 2 females n = 1–2 males, 2‐ to 6‐month‐old animals). 20× objective. Scale bar: 200 μm. *P < 0.05, ***P < 0.001 in an unpaired two‐tailed t‐test. Representative results (left panel) of [18F]FDG micro‐PET analysis performed on 6‐month‐old males fed with normal chow as described in material and methods (n = 4 for each genotype). Standard uptake value is the ratio of the tissue radioactivity concentration and the injected radioactivity, divided by the body weight. LV: left ventricle, SM: skeletal muscle (right panel). *P < 0.05 in an unpaired two‐tailed t‐test. Data are represented as mean ± SEM. Squares represent males whereas circles represent females. Source data are available online for this figure.\n\nFigure 9: Figure 9. Survival curve of MAPLf/f (n = 8) and MAPL−/− (n = 9) males.Cancer‐free survival curve of MAPLf/f (n = 8) and MAPL−/− N (n = 9) males.Pathological analysis of liver tumors in MAPLf/f and MAPL−/− mice.Survival of Huh7 cells infected with adenoviruses expressing rTta, MAPL‐flag, or MAPL‐ΔRING‐flag constructs. N = 2 independent experiments with three biological replicates each.Immunoblots of cleaved caspase 3 and 7 from Huh7 cells infected with adenoviruses expressing rTta, MAPL‐flag, or MAPL‐ΔRING‐flag constructs.Ras foci in Rat2 fibroblast cells transfected with empty pcDNA3 or overexpressing MAPL plasmids (left panel). N = 2 independent experiments with three biological replicates each. Immunoblots of PARP, MAPL and beta‐actin in Rat2 fibroblasts transfected with empty pcDNA3 or overexpressing MAPL plasmids (left panel). Immunoblots of PARP, MAPL and beta‐actin in Rat2 fibroblasts treated with DMSO or Staurosporine (STS, 1 μM, 3 h).Survival of MAPLf/f and MAPL−/− primary hepatocytes infected with adenoviruses expressing rTta or truncated BID (tBID) (left panel). Survival of MAPLf/f and MAPL−/− primary hepatocytes treated with camptothecin (1 μM, 15 h) or vehicle. Survival curve of MAPLf/f (n = 8) and MAPL−/− (n = 9) males. Cancer‐free survival curve of MAPLf/f (n = 8) and MAPL−/− N (n = 9) males. Pathological analysis of liver tumors in MAPLf/f and MAPL−/− mice. Survival of Huh7 cells infected with adenoviruses expressing rTta, MAPL‐flag, or MAPL‐ΔRING‐flag constructs. N = 2 independent experiments with three biological replicates each. Immunoblots of cleaved caspase 3 and 7 from Huh7 cells infected with adenoviruses expressing rTta, MAPL‐flag, or MAPL‐ΔRING‐flag constructs. Ras foci in Rat2 fibroblast cells transfected with empty pcDNA3 or overexpressing MAPL plasmids (left panel). N = 2 independent experiments with three biological replicates each. Immunoblots of PARP, MAPL and beta‐actin in Rat2 fibroblasts transfected with empty pcDNA3 or overexpressing MAPL plasmids (left panel). Immunoblots of PARP, MAPL and beta‐actin in Rat2 fibroblasts treated with DMSO or Staurosporine (STS, 1 μM, 3 h). Survival of MAPLf/f and MAPL−/− primary hepatocytes infected with adenoviruses expressing rTta or truncated BID (tBID) (left panel). Survival of MAPLf/f and MAPL−/− primary hepatocytes treated with camptothecin (1 μM, 15 h) or vehicle. Data are represented as mean ± SEM. Source data are available online for this figure."
      }
    ]
  },
  {
    "id": "PMC10708490_multi",
    "image": [
      "images/PMC10708490-f2.png",
      "images/PMC10708490-f3.png",
      "images/PMC10708490-f4.png",
      "images/PMC10708490-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Impact of Ring Finger Protein 20 and Its Downstream Regulation on Renal Tubular Injury in a Unilateral Nephrectomy Mouse Model Fed a High-Fat Diet\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. Results of GO and KEGG analyses. (A) Clustering heatmap after DEGs between groups (B) Number of upregulated and downregulated DEGs. (C) GO analysis to identify the molecular function genes associated with high-fat-induced kidney injury in the unilateral kidney. (D) KEGG analysis to identify DEGs between groups. n = 3 for each group.\n\nFigure 3: Figure 3. Changes in protein expression by kidney cell types due to unilateral kidney injury and high-fat diet. (A) Representative histological photomicrograph of periodic acid–Schiff (PAS), osmium (40×), and RNF20 (20×) staining in kidney tissue. * Indicates vacuoles in PAS staining. Black indicates lipid droplets in osmium staining. (B) Representative Western blot and densitometric analysis of RNF20, PPARα, PPARγ, SREBP1c, SREBP2, AQP2, ENaC, and Na+/K+ ATPase α-1 protein levels in kidney tissues. Relative protein expression was determined using densitometry. The difference among the groups was analyzed using one-way nonparametric ANOVA followed by Tukey’s multiple comparison test. Each bar represents mean ± SEM. * p < 0.05, ** p < 0.01 versus ND. n = 3–5 for each group.\n\nFigure 4: Figure 4. Lipid accumulation due to RNF20-related lipid metabolism changes in PT cells. (A) Representative images of Oil-red O staining of HK2 cells. (B) Representative Western blot and densitometric analysis of RNF20, PPARα, PPARγ, CD36, ABCA1, and CPT1A protein levels in HK2 cells with/without PA. (C) Representative Western blot and densitometric analysis of SREBP1c, SREBP2, p-ACC, and FAS protein levels in HK2 cells with/without PA. The difference among the groups was analyzed using one-way nonparametric ANOVA followed by Tukey’s multiple comparison test. Each bar represents mean ± SEM. * p < 0.05, ** p < 0.01, *** p < 0.001 versus control. n = 3–5 for each group.\n\nFigure 5: Figure 5. Lipid-induced changes in nuclear receptor factors and water channel-related proteins in CD cells. (A) Representative images of Oil-red O staining of M1 cells. (B) Representative Western blot and densitometric analysis of PPARα, PPARγ, LXRα, AQP2, ENaC, and Na+/K+ ATPase α-1 protein levels in M1 cells with/without PA. (C) Representative Western blot and densitometric analysis of CD36, CPT1A, SREBP1c, SREBP2, ACC, p-ACC, and FAS protein levels in M1 cells with/without PA. The difference among the groups was analyzed using one-way nonparametric ANOVA followed by Tukey’s multiple comparison test. Each bar represents mean ± SEM. * p < 0.05, ** p < 0.01 versus control; # p < 0.05, ## p < 0.01 versus BSA; $$ p < 0.01 versus PA 25 μM. n = 3–5 for each group."
      }
    ]
  },
  {
    "id": "PMC10724518_multi",
    "image": [
      "images/PMC10724518-f1.png",
      "images/PMC10724518-f2.png",
      "images/PMC10724518-f3.png",
      "images/PMC10724518-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Expanding the allelic spectrum of ELOVL4‐related autosomal recessive neuro‐ichthyosis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigrees of families 1–4. (a) Extended 5‐generation pedigree of the proband of Family 1. Note that two autosomal recessive neurodevelopmental disorders have been detected in this family and confirmed to be caused by two different genes accounting for the intrafamilial variability. (b) Extended 5‐generation pedigree of Family 2. Note the single loop of consanguinity as the parents are second‐degree cousins. The black‐colored square and circles depict the affected children in the family. (c) A 3‐generation pedigree of Family 3 showing the proband's extended family members, her two healthy older brothers, and her youngest affected sister. The proband and her younger affected sister are depicted with black‐colored circle. (d) A 4‐generation pedigree of Family 4 showing the proband and his affected twin sibling which are products of a first‐degree cousin marriage. The proband and his affected twin sister are depicted in black‐colored squares.\n\nFigure 2: Figure 2. Photos and magnetic resonance imaging (MRI) and electroencephalogram (EEG) images of patients from Families 1 and 2. (Ai–Aiii) Photographs of proband of Family 1 (Subject S1) showing seborrheic dermatitis of the scalp, limb contractures, and ichthyosis. (Aiv–Av) MRI brain (axial T2‐weighted and sagittal T1‐weighted images) of proband of Family 1 (Subject S1) showing diffuse cerebral volume loss, delayed myelination for age, and thin corpus callosum (orange arrow). (Avi A) screenshot of the proband's (Family 1/Subject S1) EEG 10‐second epoch (bipolar montage; sensitivity 15 μV/mm) showing slow background and multifocal epileptiform activity. (Bi–Bii) Photograph of proband's first sister of Family 2 (V‐2, Subject S3) showing chest deformity, ulcerative skin lesions, dry shiny skin in the lower limbs with skin peeling, and contractures. (Biii) A photograph of the proband's second sister (V‐3) of Family 2 (Subject S4) showing dry shiny skin. (Biv–Bv) MRI brain (axial T2‐weighted and sagittal T1‐weighted images) of proband of Family 2 (V‐1, Subject S2) shows ulegyria, volume loss, and abnormal hyperintensity in the parietooccipital white matter and of the depths of the sulci, diffuse atrophy, and marked thinning of the body and splenium of the corpus callosum (orange arrow). No atrophy of the cerebellum or brainstem. (Bvi) A screenshot of the proband's first sister's (Subject S3's) EEG 10‐second epoch (bipolar montage; sensitivity 7 μV/mm) showing bilateral independent posterior spike slow wave discharges seen bilaterally but more on the right side. There is also poorly formed and poorly organized background. Findings are suggestive of epileptic encephalopathy with epileptiform discharges more abundant in the right hemisphere.\n\nFigure 3: Figure 3. Genomic data from proband of Family 1 (Subject S1) including array CGH and BAM files around the deletion and PCR confirmation. (a) A microarray result of 5.14 Kb deletion (Chr6:80652752–80657887) involving exon 1 of ELOVL4 in the proband from Family 1 (Subject S1) is shown. The image was obtained from microarray CytoSure® Interpret Software, Oxford Gene Technology. (b) Whole‐exome sequencing of the same proband from Family 1 (Subject S1) which show no coverage of exon 1 of ELOVL4 indicating there is homozygous deletion of exon 1. As for the control samples of the same region, the coverage of exon 1 was observed. The image was obtained from Integrative Genomics Viewer (IGV) bam files of the proband and a control. (c) Polymerase chain reaction (PCR) was used to amplify both exon 1 and 2 of ELOVL4. (Left side) No amplification of exon 1 in the proband from Family 1 (33147) was detected; however, there is amplification in control (product size: 956 bp). (Right side) Amplification of exon 2 of ELOVL4 was successful in both control and proband from Family 1 (33147) (product size:399 bp). (d) Real‐time PCR of proband from Family 1 (Subject S1) targeting ELOVL4 exon 1, ELOVL4 exon 2, and reference gene MMACHC exon 2 is shown. The graph shows the ratio of the quantitative PCR, patient in orange, control sample in blue, and two relative samples (unaffected parents).\n\nFigure 4: Figure 4. Very long‐chain fatty acid‐containing LysoPC levels (C26:0, C28:0) in subject S5 (Family 3) and subjects S7 (Family 4) with ISQMR compared to control and subjects with Zellweger syndrome (ZS). (a) Measurements of C26:0‐LysoPC in dried blood spots in subjects S5 (Family 3 proband) and S7 (Family 4 proband) show that the C26:0‐LysoPC level is normal in both. (b) Measurements of C28:0‐LysoPC in dried blood spots in subjects S5 (Family 3 proband) and S7 (Family 4 proband) show that the C28:0‐LysoPC level is reduced in both. (c) Measurement of C28/26 ratios in dried blood spots in subjects S5 (Family 3 proband) and S7 (Family 4 proband) show that C28/C26 ratio is reduced in both subjects compared to controls and subjects with ZS."
      }
    ]
  },
  {
    "id": "PMC10757945_multi",
    "image": [
      "images/PMC10757945-f1.png",
      "images/PMC10757945-f2.png",
      "images/PMC10757945-f3.png",
      "images/PMC10757945-f4.png",
      "images/PMC10757945-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Immune response of BV-2 microglial cells is impacted by peroxisomal beta-oxidation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Transcriptomic analysis of the LPS response of WT and mutant (Abcd1−/−Abcd2−/− and Acox1−/−) BV-2 cells (n = 3 for each genotype). (A) Pie chart displaying the number of up- or downregulated DEGs after a 24-h LPS treatment (DataSet GSE237635). The significant genes (number and percentage) were selected using a cutoff adjusted p-value (DESeq2 Wald test with Benjamini and Hochberg p-value adjustment) lower than 0.05 and an absolute log2 FC higher than 1. Additional comparison to test if the effect of the LPS treatment is different between the mutant and the WT genotypes, which permitted to highlight the proportion of significantly (AdjP Value < 0.05) more repressed (dark blue) (Log2FC < 1) or induced (dark red) (Log2FC > 1) DEGs, indicated by the left and right bars, respectively. (B) Gene set enrichment analysis in each genotype presenting a selection of the three main gene ontology biological process (up) and KEGG pathway (down) terms selected by FDR (in brackets) and sorted by Fold Enrichment (abscissa axis). (C) Comparative analysis of the sets of DEGs using the Venn diagram illustrating the larger increase of upregulated (up) and downregulated (down) DEGs in LPS-treated mutant cells as compared to WT. The number in brackets represents the number of DEGs belonging to the intersection significantly more deregulated (p < 0.05) in the mutant than in the WT genotype (Wald test).\n\nFigure 2: Figure 2. Impact of peroxisomal defect on the expression of cytokine and chemokine encoding genes in WT and mutant (Abcd1−/−Abcd2−/− and Acox1−/−) BV-2 cells. (A) Venn diagrams illustrating the up- and downregulated cytokine and chemokine encoding genes DEGs (Log2FC > 1, AdjP Value < 0.05) in Abcd1−/−Abcd2−/− and Acox1−/− non-stimulated BV-2 cells (DataSet GSE200022). Genes whose expression level was measured at the protein level are boxed. (B) Pie chart displaying the number of these up- or downregulated DEGs after a 24-h LPS treatment (Log2FC > 1, AdjP Value < 0.05) in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells (DataSet GSE237635). (C) Venn diagrams representing the LPS response of these DEGs in each genotype. (D) Heat map representing RNA-Seq gene expression (with Z-scores) of these DEGs at 24 h after LPS stimulation in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells (three independent batches of BV-2 cells for each genotype). (E) Multiplex analysis of the concentration of secreted cytokines and chemokines (CCL2 (MCP-1), CCL3 (MIP-1α), CCL4 (MIP-1β), and TNF). Dot plots histograms present the single values and mean (±SD) of 6–12 measurements in the absence of LPS (empty bars) or after a 24-h treatment with LPS (hatched bars). Statistical differences relative to the untreated genotype are indicated (two-way ANOVA, *p < 0.01, **p < 0.01, ***p < 0.001). Relative fold induction is presented on the right histogram for each cytokine, and statistical differences relative to the fold induction observed in WT cells are indicated (one-way ANOVA, *p < 0.01, **p < 0.01, ***p < 0.001). (F) Representative image of Western blotting analysis (three independent experiments) of the expression levels of Caspase 1 (CASP1 and Pro-CASP1), Interleukin 1β (IL1B and Pro-IL1B), and NLRP3 in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells untreated (–) or treated with LPS for 24 h (+). Expected molecular weights are indicated. Source data are available online for this figure.\n\nFigure 3: Figure 3. Impact of peroxisomal defect on the expression of phagocytosis-related genes in WT and mutant (Abcd1−/−Abcd2−/− and Acox1−/−) BV-2 cells. (A) Schematic representation of the main actors of phagocytosis. (B) Venn diagrams illustrating the up- and downregulated phagocytosis-related DEGs in Abcd1−/−Abcd2−/− and Acox1−/− non-stimulated BV-2 cells (DataSet GSE200022). Genes whose expression level was measured at the protein level are boxed. (C) Pie chart displaying the number of up- or downregulated phagocytosis-related DEGs after a 24-h LPS treatment (Log2FC > 1, AdjP Value < 0.05) in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells (DataSet GSE237635). (D) Venn diagrams representing the LPS response of these DEGs (three independent batches of BV-2 cells for each genotype). (E) Heat map representing RNA-Seq gene expression of these DEGs at 24 h after LPS stimulation in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells. (F) Representative image of Western blotting analysis (three independent experiments) of the expression levels of CD36, FCGR2B, MRC1, TLR2, and TLR4 in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells untreated (–) or treated with LPS for 24 h (+). Expected molecular weights are indicated. Source data are available online for this figure.\n\nFigure 4: Figure 4. Phagocytosis of pHrodo®-Green E.coli BioParticles and pHrodo®-Green–labeled myelin sheath debris by BV-2 WT, Abcd1−/−Abcd2−/−, and Acox1−/− cells. BV-2 cells were incubated with 25 μg/mL pHrodo®Green E.coli BioParticles (A–C) or 10 μg/mL pHrodo®-green–labeled myelin (D–F) in the presence or absence of LPS (LPS 1 μg/mL for 24 h). IncuCyte® was used to monitor the phagocytosis. The time course of pHrodo® signal quantification for 16 h is represented for WT (A, D); Abcd1−/−Abcd2−/− (B, E); and Acox1−/− (C, F) with bioparticles and myelin, respectively. The curves show the mean ± S.E.M. from n = 3 independent experiments for the beads (left) and n = 4 for the myelin (right). Quantification of pHrodo signal over 16 h represented as area under the curve for phagocytosis of beads (G) and myelin (H). The statistical differences were calculated using 2-way ANOVA followed by correction for false discovery rate and represented as “*” to compare the phagocytosis of KO to WT cells and as “#” to compare the LPS-treated KO vs. LPS-treated WT cells (*p < 0.05, ***p < 0.001, ###p < 0.001).\n\nFigure 5: Figure 5. Impact of peroxisomal defect on the expression of genes related to antigen presentation and T lymphocyte co-stimulation in WT and mutant (Abcd1−/−Abcd2−/− and Acox1−/−) BV-2 cells. (A) Venn diagrams illustrating the up- and downregulated DEGs (Log2FC > 1, AdjP Value < 0.05) related to antigen presentation and T lymphocyte co-stimulation in Abcd1−/−Abcd2−/− and Acox1−/− non-stimulated BV-2 cells (DataSet GSE200022). Genes whose expression level was measured at the protein level are boxed. (B) Pie chart displaying the number of these up- or downregulated DEGs after a 24-h LPS treatment (Log2FC > 1, AdjP Value < 0.05) in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells (DataSet GSE237635). (C) Venn diagrams representing the LPS response in each genotype of these DEGs (three independent batches of BV-2 cells for each genotype). (D) Heat map representing RNA-Seq gene expression (with Z-scores) of these DEGs at 24 h after LPS stimulation in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells (three independent batches of BV-2 cells for each genotype). (E) Flow cytometry analysis of the expression level of CD54 (ICAM1), CD80, CD86, and MHC class I protein H2-K1 in WT, Abcd1−/−Abcd2−/−, and Acox1−/− BV-2 cells surface stained with fluorescent-labeled monoclonal antibodies (FITC, Fluorescein isothiocyanate; PE, phycoerythrin; APC, Allophycocyanin). The results are plotted as a distribution histogram of fluorescence intensities (arbitrary units) of populations of living BV-2 cells. Unstained BV-2 cells were shown in gray to evaluate intrinsic autofluorescence, compared to fluorescent antibody-stained cells (WT BV-2 ± LPS in light/dark purple, Abcd1−/−Abcd2−/− ± LPS in light/dark green, and Acox1−/− ± LPS in light/dark orange, respectively). The results are representative of four independent experiments."
      }
    ]
  },
  {
    "id": "PMC10759424_multi",
    "image": [
      "images/PMC10759424-f1.png",
      "images/PMC10759424-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The Role of AMPK Signaling in Ulcerative Colitis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) A brief history of AMPK; (B) The AMPK molecule and its upstream and downstream mechanism.\n\nFigure 2: Figure 2. Possible Biological Mechanisms of AMPK in Ulcerative Colitis."
      }
    ]
  },
  {
    "id": "PMC10774338_multi",
    "image": [
      "images/PMC10774338-f1.png",
      "images/PMC10774338-f2.png",
      "images/PMC10774338-f3.png",
      "images/PMC10774338-f4.png",
      "images/PMC10774338-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Variants in the WDR44 WD40-repeat domain cause a spectrum of ciliopathy by impairing ciliogenesis initiation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Photographs of subjects with WDR44 variants demonstrate common craniofacial features including high frontal hairline, upslanting palpebral fissure, smooth philtrum and thin upper lip vermilion in all patients with the exception of subject III:2 of family 9 harboring the c.2519A > G p.(N840S) who does not display major dysmorphism. Patients harboring the c.2291C > T p.(S764F) (Family 1) and c.1943A > G p.(D648G) (Family 4) variants also show long philtrum and mildly webbed neck. (b, c) Bar graph showing the distribution of the clinical and craniofacial features. Blue: presence of ciliopathy-related features. Gray: absence of ciliopathy-related features. Analysis for 11 patients (c). d Photos of hands showing digital abnormalities including brachydactyly in all showed patients, and camptodactyly of fifth fingers for patient with c.1943A > G p.(D648G) (family 4) and ulnar deviation in the patient harboring the c.2197C > T p.(R733*) variant (family 3). e Kidney ultrasound of patient with c.2291C > T p.(S764F) variant shows parapelvic cysts (red arrows). f Neuroimaging features of the affected subjects with normal control for comparison. Brain MRI with axial T2-weighted images showing mild simplified gyral pattern and faint T2-weighted hyperintensity of the deep fronto-parietal white matter (white empty arrows) in subject III:1 of Family 1 and IV:4 and IV:3 of Family 4. Brain MRI with axial T2 weighted images showing mild enlargement of the subarachnoid spaces (thin arrows) with white matter volume reduction and ventricular enlargement in subjects II:1 of Family 2, III:12 of Family 4, III:2 of Family 8, and III:2 of Family 9. g The schematic represents the WDR44 protein and its domains. The position of variants is indicated in the WDR domain. h Multiple sequence alignment analysis of WDR44 wild-type protein across species. The numbers represent the position of conserved amino acid residues that are altered in the patients. Source data are provided as a Source Data file. DD/ID/LD developmental delay/intellectual disability/learning disability, CSF cerebrospinal fluid.\n\nFigure 2: Figure 2. a Immunoblotting analysis of WDR44 and β-actin in lysates from control (matched and unmatched parents) and WDR44 variant patient fibroblast cells. Proteins band relative intensity is indicated by the graph (above). Statistical comparisions with father 840 or p.D648G are shown. P ≤ 0.0001 (p.D648G, p.S764F), 0.0002 (p.S764F). b WDR44 mRNA relative expression was determined by real-time RT-PCR in control and WDR44 variant patient fibroblasts from 3 independent mRNA isolations. c Immunoblotting analysis of transiently expressed GFP-WDR44 wild-type and variants in 293T cells post 48 h of transfection. Proteins band relative intensity is indicated by the graph (above). Statistical comparisons with wild-type (WT) are shown. P = 0.0108 (L668S), 0.0233 (N840S), 0.0026 (D648G), 0.0027 (D669N), 0.002 (S764F), 0.002 (H839R), 0.0008 (G782C). d Immunoblotting analysis of proteins from the lysates of 24 h vehicle control (-) or 1μM MG132 (+) treated fibroblast cells. p27 is used as a positive marker of proteasome inhibition. Proteins band relative intensity is indicated by the graph (below). Statistical comparisons between DMSO vehicle control and MG132 are shown. P = 0.0365 (p.N840S), 0.0014 (p.D648G), 0.0004 (p.S764F). e Immunoblotting analysis of transiently expressed GFP-WDR44 wild-type or variants in 293T cells treated with vehicle control (Ctrl) or 1μM MG132 (MG) for 16 h or 10μM Chloroquine (CQ) for 24 h. Protein band relative intensity is indicated by the graph (right). Statistical comparisons between Ctrl and MG are shown. P = 0.0355 (D648G), 0.0422 (G782C), 0.029 (N840S), 0.0018 (S764F). f Immunoblotting analysis of COOH-terminal domain of wild-type or variants in 293T cells 48 h after transfection. GFP was used as an internal control of transfection. Schematic above represents the COOH-terminal region of WDR44 used for the analysis. Proteins band relative intensity is indicated by the graph (right). P = 0.0144 (D648G), 0.0105 (D669N), 0.0132 (S764F), 0.0207 (G782C), 0.0230 (H839R). g Predicted structure of the WDR44 WDR domain for residues 480–858 and 887–913 modeled from the AF predicted structure (AF-Q5JSH3). Residues mutated in patients are shown in red. h Structure alignment of WDR44 WDR wild-type (cyan) and patient missense variant (grey). The patient variant structures were built from the structure described in (g) followed by 500 ns MD simulation to assess conformational changes. Patient variants shown to have the largest conformational changes based on RMSD/residue analysis in Fig. S3d. Red arrows show change in position of patient variants from wild-type. Mean ± s.e.m. from three (b–f) or four (a) independent experiments. Unpaired two-tailed t-test; *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001, non-significant (ns). Source data are provided as a Source Data file.\n\nFigure 3: Figure 3. a Quantification of ciliation in control and WDR44 variant (p.D648G, p.S764F, p.N840S) patient fibroblast fed with 10% serum (+serum) or starved (−serum) for 24 h, followed by anti-Arl13b, anti-CEP164, and anti-CP110 antibodies staining. >150 cells were counted from three or more independent experiments. Statistical comparisons with father 648 are shown. +serum: P = 0.012 (p.S764F), 0.0039 (p.D648G), −serum (24 h): P = 0.0001 (p.D648G). b Immunoblotting analysis of GFP or GFP-WDR44 wild-type and β-actin from lysates of patient fibroblasts. Probed for GFP and β-actin antibodies. c Ciliation was quantified in p.D648G and p.S764F patient fibroblast rescued with GFP control or GFP-WDR44 wild-type. >150 cells were counted from three independent experiments. P = 0.0024 (p.S764F). d Quantification of cilia length in fibroblast from p.N840S and controls that were stained as in (a). Statistical comparisons with p.N840S. P = 0.0131 (father 840), <0.0001 (Male-Ctrl, mother 840). (e, f) Hedgehog signaling was analyzed in parental control and patient fibroblasts. GLI1 (e) and PTCH1 (f) transcript fold induction determined by real-time RT-PCR in fibroblast fed with 10% serum (serum+) or starved (serum-) in the presence (SAG+) or absence (SAG-) of SAG for 24 h. Statistical comparisons with father 840 SAG+ are shown. e serum+: P = 0.0001 (p.S764F), <0.0001 (p.D648G), serum-: P = 0.0211 (p.D648G), 0.0375 (p.S764F). f serum+: P = 0.03 (p.D648G), 0.025 (p.S764F). Mean ± s.e.m. from three independent experiments. Unpaired two-tailed t-test; *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001. Source data are provided as a Source Data file.\n\nFigure 4: Figure 4. a Dot blot analysis of WDR44 wild-type and variants expressed in zebrafish morphants (left). Protein loading was demonstrated by Ponceau staining of dot blot (right) probed with WDR44 antibodies. b Bright-field (BF) image analysis of zebrafish embryos injected with wdr44 morpholino and rescued with mRNA of human WDR44 wild-type or variants. Scale bar, 1 mm. (c–h) Quantification of developmental defects: body size, head dysmorphism, microphthalmia, body curvature, heart edema at 3 dpf, and distended pronephric tubules at 6 dpf. Statistical comparison with WT are shown. c P = 0.0229 (R733*), 0.0236 (G782C). d P = 0.0261 (L668S), 0.0062 (D669N), 0.0049 (R733*), 0.0052 (S764F), 0.0079 (G782C), 0.0355 (H839R). e P = 0.0157 (L668S), 0.0404 (D669N), 0.0099 (R733*), 0.0251 (S764F), 0.0046 (G782C), 0.0260 (H839R). f P = 0.0379 (D669N), 0.0032 (R733*), 0.0028 (S764F), 0.0204 (H839R). g 0.0204 (D669N), 0.0080 (R733*), 0.0067 (S764F), 0.0044 (G782C). h P = 0.0003 (D669N), 0.0053 (R733*), 0.0480 (G782C), 0.0331 (H839R), 0.0163 (N840S). i Representative images of 3 dpf Tg(wt1b:EGFP) embryos injected as in (b) showing developing pronephros. Scale bar, 50 μm. Mean ± s.e.m. from three independent experiments imaging >60 embryos (c–h) or >10 embryos (i). Unpaired two-tailed t-test; *P < 0.05, **P < 0.01, ***P < 0.001. Source data are provided as a Source Data file.\n\nFigure 5: Figure 5. Quantification (right) of ciliation in pronephric ducts (a), neuromasts (b), and olfactory placode (c) in zebrafish embryos at 3 dpf. Embryos were injected with wdr44 morpholino with or without mRNA of human WDR44 wild-type and variants, followed by staining with anti-acetylated tubulin antibody and Hoechst. Phalloidin staining was performed in (b, c). Represented immunofluorescence microscopy (IFM) (left) images. Scale bars, 10 μm. Statistical comparison with wdr44MO + WT are shown. a P = 0.0161 (D669N), 0.0002 (R733*), 0.0061 (S764F), 0.0023 (G782C), 0.0328 (H839R). b P = 0.1155 (D648G), 0.0360 (D669N), 0.0064 (R733*), 0.0003 (S764F), 0.0129 (G782C), <0.0001 (H839R). c P = 0.0309 (D669N), <0.0001 (R733*), 0.0003 (S764F), 0.0021 (G782C), P < 0.0001 (H839R). Mean ± s.e.m. from three independent experiments and total number of embryos imaged are indicated on images. Unpaired two-tailed t-test; *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001. Source data are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC10774338_multi_2",
    "image": [
      "images/PMC10774338-f6.png",
      "images/PMC10774338-f7.png",
      "images/PMC10774338-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Variants in the WDR44 WD40-repeat domain cause a spectrum of ciliopathy by impairing ciliogenesis initiation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a Quantification (right) of MC uncapping (denoted as one CP110 centriole on daughter centriole) and capped MC (denoted as two CP110 centriole on both mother and daughter centriole) in the patient and control fibroblast fed with 10% serum (+serum) or starved (−serum) for 24 h. Cells were stained with anti-Arl13b, anti-CEP164, and anti-CP110 antibodies. Nuclei were stained with Hoechst 33342. Represented IFM images (left). Scale bars, 10 μm. >100 cells were counted from three independent experiments. Statistical comparisions with male-Ctrl or p.S764F are shown. +serum: P = 0.0499 (p.S764F), 0.0211 (D648G), −serum (24 h): P = 0.0211 (p.D648G), P = 0.0065 (pD648G). b Percentage of ciliation determined by immunostaining RPE-1 control Cas9 and WDR44 KO clones with anti-Arl13b and anti-CEP164. >150 cells were counted from three independent experiments. Statistical comparisons with Ctrl Cas9 are shown. P = 0.0148 (G2), 0.0081 (E1), 0.0011 (F4). c Quantification of MC uncapping as in (a) in the RPE1 WDR44 KO F4 cells transiently expressing GFP control or GFP-WDR44 wild-type or variants for 48 h. >60 cells with similar GFP expression were counted from three independent experiments. Statistical comparisons with GFP-WDR44 wild-type (WT) are shown. P = 0.0329 (D648G), 0.0178 (S764F), 0.0131 (L668S), 0.01 (G782C), 0.0084 (D669N), 0.0032 (H839R), 0.0039 (N840S). Mean ± s.e.m.. Unpaired two-tailed t-test; *P < 0.05, **P < 0.01, non-significant (ns). Source data are provided as a Source Data file.\n\nFigure 7: Figure 7. a Coimmunoprecipitation analysis of coexpressed GFP-RAB11A and Myc-WDR44 wild-type or variant in 293T for 48 h. Myc-tagged proteins were immunoprecipitated from 293T lysate and probed with GFP, Myc, and GAPDH. The plot (below) shows the relative co-immunoprecipitated levels of GFP-RAB11A bound to Myc-WDR44 wild-type or variants from three independent experiments. Statistical analysis comparing wild-type (WT), R733* and N840S are shown vs WT: P = 0.0269 (L668S), 0.0459 (R733*), 0.0236 (S764F), 0.0226 (G782C), 0.0261 (N840S), 0.0002 (D648G), 0.0009 (D669N), 0.0002 (H839R); vs R733*: P = 0.0459 (WT), 0.0221 (D648G), 0.0448 (S764F); vs N840S: P = 0.0261 (WT), 0.0333 (S764F), 0.0356 (G782C), 0.0018 (D669N), 0.0011 (H839R), 0.0004 (D648G). b Immunoprecipitation analysis of GFP-WDR44 wild-type or variants transiently expressed in RPE1 WDR44 KO F4 cells for 48 h. GFP proteins were immunoprecipitated from lysate and probed with GFP, RAB11, VAPA, and GAPDH antibodies. Blots are represented from three independent experiments. The plots (below) shows the relative co-immunoprecipitated levels of RAB11 and VAPA bound to GFP-WDR44 wild-type or variants. RAB11: P = 0.0183 (G782C), 0.0135 (N840S), 0.0086 (D648G), 0.0022 (L668S), 0.0065 (D669N), 0.0023 (R733*), 0.0005 (S764F), 0.0009 (H839R); VAPA: P = 0.0229 (R733*), P = 0.0087 (D648G). c IFM images of RPE1 WDR44 KO F4 cells transfected with GFP or GFP-WDR44 wild-type or variants. Cells express BFP and are immunostained with RAB11. Plasma membrane and nuclei are indicated by solid and dotted lines, respectively. Representative images from 20–25 cells are shown. White asterisk denotes untransfected cells. Scale bars, 10 μm. Mean ± s.e.m. from three independent experiments. Unpaired two-tailed t-test; *P < 0.05, **P < 0.01, ***P < 0.001. Source data are provided as a Source Data file. WCL whole cell lysate.\n\nFigure 8: Figure 8. a Immunoprecipitation of endogenous WDR44 from controls and p.S764F patient fibroblast in the presence of 10% serum (+serum) or starved (−serum) for 24 h. Immunoblots were probed with WDR44, pAkt-substrate (pAKT WDR44), PanAKT, and β-actin antibodies. Blots are represented from two independent experiments. b Immunoblot analysis of Akt phosphorylation of Myc-WDR44 wild-type or G782C or S764F, and GFP-RAB11 co-immunoprecipitated under ciliating conditions (3 h and 24 h serum starvation) from 293T cells expressing indicated plasmids for 48 h. GAPDH was used to evaluate starting lysate protein levels. Blots are represented from two independent experiments. c The schematic represents (top) WDR44 domains, HA-NH2-terminal domain containing RBD (1-408AA), and GST-COOH-terminal domain containing WDR (477-913 AA). Immunoblotting analysis (bottom left) showing co-immunoprecipitation between HA-NH2-terminal domain and GST-COOH-terminal domain of wild-type or variants from 293T cells expressing indicated plasmids for 48 h. Plot (right) shows the relative co-immunoprecipitated levels of GST-COOH-terminal WDR44 compared to HA-NH2-terminal WDR44 proteins normalized to pre-IP levels of GST-COOH-terminal. P = 0.0224 (N840S), 0.0035 (L668S), 0.0021 (S764F), 0.0031 (G782C), 0.0001 (D648G), 0.0004 (D669N), 0.0008 (H839R). Mean ± s.e.m. from three independent experiments. Unpaired two-tailed t-test; *P < 0.05, **P < 0.01, ***P < 0.001. d Summary of WDR44 variant results. Source data are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC10775765_multi",
    "image": [
      "images/PMC10775765-f1.png",
      "images/PMC10775765-f1-2.png",
      "images/PMC10775765-f2.png",
      "images/PMC10775765-f3.png",
      "images/PMC10775765-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The 2023 Walter B. Cannon Award Lecture: Mechanisms Regulating Vascular Function and Blood Pressure by the PPARγ-RhoBTB1-CUL3 Pathway\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisome proliferator activated receptor γ Final Common Pathway.\n\nFigure 1: Figure 1. Peroxisome proliferator activated receptor γ Hypothesis and Final Common Pathway. The PPARγ hypothesis states that interference with the action of PPARγ (by the DN mutant) in liver, adipose, and skeletal muscle leads to insulin resistance and diabetes, whereas its interference in vascular endothelium and smooth muscle leads to vasomotor dysfunction, arterial stiffness, and hypertension.\n\nFigure 2: Figure 2. Peroxisome proliferator activated receptor γ Final Common Pathway In the endothelium, PPARγ induces transcription of RBP7 and PPARγ/RBP7 together form a transcriptional regulatory hub promoting the expression of antioxidant genes, including adiponectin (AdipoQ), all of which promote an antioxidant environment, NO production, and NO bioavailability to the smooth muscle. In the vascular smooth muscle, endothelium-derived NO activates soluble guanylate cyclase to produce cGMP. To regulate cGMP levels in the cell, PPARγ induces the expression of Rho related BTB domain containing 1 (RhoBTB1), which acts as a substrate recognition protein delivering phosphodiesterase 5 (PDE5) to the Cullin-3 (CUL3) complex for ubiquitination and proteasomal degradation. The ensuing decrease in PDE5 activity promotes cGMP production and NO activity leading to vasodilation. Rho related BTB domain containing 1 also promotes a state of vessel distensibility reducing arterial stiffness. Other PPARγ target genes (RGS5 and TIMP4) control G protein receptor action, control myogenic tone, and reduce remodeling. Peroxisome proliferator activated receptor γ also acts as an antiinflammatory by shuttling p65 from the nucleus repressing expression of inflammatory genes.\n\nFigure 3: Figure 3. Phenotypic Summary of Animal Models A summary of the main animal models discussed in the review is presented. S-CUL3Δ9 represents inducible expression of a dominant mutant of CUL3 that results in exon 9 skipping. S-CUL3Flox represents the inducible smooth muscle knockout of CUL3. S-PPARγP467L also known as S-P467L represents smooth muscle-specific expression of a human mutant in PPARγ (P467L), which causes human hypertension. Although it is discussed early in the review, it is presented directly next to the S-PPARγP467L X S-RhoBTB1, which represents the inducible smooth muscle-specific re-expression of RhoBTB1 in the S-P467L model. S-RhoBTB1 + Ang-II is the inducible smooth muscle-specific expression of RhoBTB1 treated with a slow-pressor dose of Ang-II to induce hypertension and arterial stiffness. The arrows reflect the following comparisons: S-CUL3Δ9 versus control mice; S-CUL3Flox versus control mice; S-PPARγP467L versus control mice; S-PPARγP467L X S-RhoBTB1 versus S-P467L mice; S-RhoBTB1 + Ang-II measures the effect of inducible RhoBTB1 after hypertension is fully established by Ang-II. In the latter, activation of RhoBTB1 did not alter vasodilation, vasoconstriction, or BP in response to Ang-II but relieved arterial stiffness.\n\nFigure 4: Figure 4. Schema for the Identification of PPARγ Target Genes Gene expression profiling was performed comparing the list of genes repressed in the aorta in response to DN PPARγ with the list of genes induced by the PPARγ agonist ROSI. These potential PPARγ target genes were then screened using publicly available ChIP data for the presence of PPARγ binding sites around the gene identified above. Genes that passed all three criteria were considered PPARγ target genes and were separately validated. These include RBP7, RGS5, TIMP4, and RhoBTB1."
      }
    ]
  },
  {
    "id": "PMC10776696_multi",
    "image": [
      "images/PMC10776696-f1.png",
      "images/PMC10776696-f2.png",
      "images/PMC10776696-f3.png",
      "images/PMC10776696-f4.png",
      "images/PMC10776696-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Upregulated pexophagy limits the capacity of selective autophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Schematic of mammalian ubiquitin-dependent pexophagy. b Immunoblot of HeLa cells treated with siRNA and probed for the indicated proteins. c Representative images of HeLa cells treated with the indicated siRNA and immunostained for the peroxisomal marker, PMP70. Scale bar, 25 µm. d Quantification of PMP70 in (c) relative to siCTRL conditions. PMP70 was measured by dividing the number of PMP70 puncta by cell volume (see Methods). e Schematic of aggrephagy assay. HeLa cells were treated with the indicated siRNA prior to aggrephagy induction (see Methods). f Representative images from cells at each stage in the assay: DMEM, 3-h 5 µg mL−1 Puromycin, 3-h 5 µg mL−1 Puromycin followed by 5-h clearance period in DMEM, or 3-h 5 µg mL− Puromycin followed by 5-h clearance period in 2 µM Rapamycin. Cells were immunostained with the ubiquitin antibody FK2; blue=DAPI. Scale bars, 25 µm. g Quantification of aggrephagy assay in (f). Aggregate Volume was calculated by dividing the total volume of FK2 puncta by cell volume. Aggrephagy activity was measured as the % clearance of FK2 aggregates, relative to mock transfected “3 h P + 5 h DMEM” cells. h PEX2 mRNA levels measured by qPCR in cells treated with control non-targeting or PEX2-targeting siRNA, relative to control. i Quantification of PMP70 in HeLa cells treated with the indicated siRNAs. j Aggrephagy activity in HeLa cells treated with the indicated siRNAs, relative to control siRNA-treated condition. Data are displayed as means \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation from n = 4 (d) or n = 3 (g, h, i) independent experiments. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. d, i One-way ANOVA, Tukey’s multiple comparisons test. g, j Two-way ANOVA, Tukey’s multiple comparisons test. h Unpaired t-test, two tailed. Source data and exact P values are provided as a Source Data file.\n\nFigure 2: Figure 2. a HeLa cells transfected with either PMP34-GFP or PMP34-GFP-UBKo 24-h before fixation and immunostaining for PMP70; blue = DAPI. Scale bars, 20 µm. b Quantifications of PMP70 in (a). PMP70 was calculated by dividing the number of PMP70 puncta by cell volume (see Methods). c HeLa cells transfected with either PMP34-GFP or PMP34-GFP-UBKo 24-h before aggrephagy induction. Representative images from cells at each stage in the assay: DMEM, 3-h 5 µg mL−1 Puromycin, 3-h 5 µg mL-1 Puromycin followed by 5-h clearance period in DMEM, or 3-h 5 µg mL-1 Puromycin followed by 5-h clearance period in 2 µM Rapamycin DMEM. Cells were immunostained for FK1; blue=DAPI. Scale bars, 25 µm. d Quantification of Aggregate Volume in (c). Aggregate Volume was calculated by dividing the total volume of FK1 puncta by cell volume. e Quantification of aggrephagy activity in (c), relative to PMP34-GFP. Aggrephagy activity was measured as the % clearance of FK1 aggregates. Data are displayed as means (d, e) or individual cells overlaid with means, where different colors correspond to independent trials (b) \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation from n = 3 (b) or n = 4 (d, e) independent trials. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. b Unpaired t-test, two tailed, performed with means. d, e Two-way ANOVA, Tukey’s multiple comparisons test. Source data and exact P values are provided as a Source Data file.\n\nFigure 3: Figure 3. a Immunoblots of GFP-Parkin HEK293 cells subjected to siRNA knockdown prior to treatment for 8-h with DMSO, 2.5 µM Oligomycin and 250 nM Antimycin A1 (OA), or OA + 250 nM Bafilomycin A1. Immunoblots were probed for outer mitochondrial membrane marker MFN2, inner mitochondrial membrane marker CVα, mitochondrial matrix protein HSP60, and siRNA targets: PEX1, PEX13, PEX14, and ATG12. b–d Percentage loss densitometry quantification of the indicated bands normalized to loading control GAPDH. Bands were quantified using ImageJ software. e Representative confocal fluorescent images of GFP-Parkin HEK293 cells treated as in (a). Cells immunostaining for CVα as indicated; blue= DAPI. Scale bars, 25 µm. f Quantification of CVα after OA treatment in (e) relative to MOCK. CVα was quantified by dividing the total CVα fluorescence intensity by cell volume. g Quantification of CVα after 8-h OA treatment in GFP-Parkin HEK293 cells treated with the indicated siRNA relative to siCTRL conditions (representative images in Fig. S3). h Representative images of GFP-Parkin HEK293 cells treated with the indicated siRNA prior to treatment for 8-h with either OA, or OA + 2 µM Rapamycin. Cells were immunostained for mitochondria marker, CVα; blue=DAPI. Scale bars, 25 µm. i Quantification of CVα in (h). Data are displayed as means from n = 5 (b, c), n = 4 (d, i), n = 3 (f, g) independent experiments \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. b–d Comparison to MOCK, unpaired t-test, two tailed. f One-way ANOVA, Dunnett’s multiple comparisons test. g One-way ANOVA, Tukey’s multiple comparisons test. i Comparison to OA, unpaired t-test, two tailed. Source data and exact P values are provided as a Source Data file.\n\nFigure 4: Figure 4. a Immunoblots of control or ZSD fibroblasts treated for 28-h with either DMSO, 10 µM CCCP or 1 mM DFP and probed for the indicated proteins. b–e Densitometry quantification of the indicated bands from (a) normalized to loading control Vinculin and relative to DMSO conditions. f Densitometry quantification of the indicated bands from (a) in DMSO conditions only, normalized to loading control Vinculin. g Percentage loss of band intensity from DMSO to DFP conditions in (a), (see Methods). h Representative images of control or PEX3-R53Ter ZSD fibroblasts treated for 28-h with either DMSO or 1 mM DFP. Cells were immunostained for HSP60 and LAMP1A; blue=DAPI. Scale bars, 25 µm; zoom scale bars, 5 µm; white boxes, zoomed region. i Manders’ correlation coefficient for HSP60 and LAMP1A from (h). j Quantification of fraction of cells with a mild, moderate, or severe mitophagy phenotype from (h). See Methods and Supplementary Data Fig. 4. Data are displayed as individual cells with means overlaid (i) or fraction of cells (j) from n = 3 independent experiments, or means as indicated from n = 3 (b, c) or n = 4 (d–g) independent experiments \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. b–e Two-way ANOVA, Dunnett’s multiple comparisons test, (f, g) Unpaired t-test, two tailed, i Two-way ANOVA, Tukey’s multiple comparisons test using means. Source data and exact P values are provided as a Source Data file.\n\nFigure 5: Figure 5. a HeLa cells at each stage in the αS assay: untreated (DMEM), 4-h transfection with αS pre-formed fibrils (PFF); 4-h αS PFF followed by an 8-h clearance period in either DMEM or 0.25 mM Leupeptin and 2 µM E-64. Cells were immunostained for αS and LC3. Scale bars, 25 µm. b HeLa cells immunostained for αS and expressing LAMP1a-mCherry at each stage in the assay as in (a), but here with a 15-h clearance period. Scale bars, 25 µm. c Schematic of assay where cells are treated with siRNA before αS PFF transfection. d Representative images from HeLa cells treated with the indicated siRNA and subjected to the αS assay in (c), given an 8-h clearance period in either DMEM or 2 µM Rapamycin. Cells were immunostained for αS and LC3; blue = DAPI. Scale bars, 25 µm; cropped image scale bars, 5 µm; white arrows indicate colocalization of αS and LC3. e Quantification of αS intensity in (d), calculated by dividing the total αS florescence intensity by cell volume. Data are displayed as means \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation from n = 4 independent experiments. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. Two-way ANOVA, Tukey’s multiple comparisons test. Images in (a) and (b) are representative of n = 3 independent experiments. Source data and exact P values are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC10776696_multi_2",
    "image": [
      "images/PMC10776696-f6.png",
      "images/PMC10776696-f7.png",
      "images/PMC10776696-f8.png",
      "images/PMC10776696-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Upregulated pexophagy limits the capacity of selective autophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a Images of control, PEX1-G843D, or PEX3-R53Ter ZSD fibroblasts stained for PMP70; blue = DAPI. Scale bars, 25 µm. b Immunoblot of ZSD fibroblasts probed for PEX1, PMP70, and β-Actin. c Densitometry quantification of PMP70 bands in (b) normalized to β-Actin. d Representative images of ZSD fibroblasts at each stage in the aggrephagy assay. Cells were immunostained with the antibody FK2; blue=DAPI. Scale bars, 25 µm. e Quantification of Aggregate Volume in (a). Aggregate Volume was calculated by dividing the total volume of FK2 puncta by cell volume. f Quantification of aggrephagy activity in (d), relative to control fibroblasts. Aggrephagy activity was measured as the % clearance of FK2 aggregates. Data are displayed as means \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation from n = 5 (c) or n = 3 (e, f) independent experiments. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. c One-way ANOVA, Dunnett’s multiple comparisons test. e, f Two-way ANOVA, Tukey’s multiple comparisons test. Source data and exact P values are provided as a Source Data file.\n\nFigure 7: Figure 7. a Schematic of assay. 20-h after a single siRNA transfection, αS monomers (Mon) or PFF are co-transfected into cells with an mCherry plasmid for 4-h, followed by a 15-h clearance period in DMEM. b Immunoblot of HeLa cells treated with the indicated siRNA for 20-h and probed for PEX13 and β-Actin; representation of n = 3 independent experiments. c Representative images of HeLa cells treated with the indicated siRNA and transfected with either αS Mon or PFF at each stage in the assay, and immunostained for PMP70. Scale bars, 25 µm. d Quantification of αS intensity in (c), calculated by dividing the total αS florescence intensity by cell volume. e Quantification of PMP70 in (c). PMP70 was calculated by dividing the number of PMP70 puncta by cell volume. Data are displayed as means \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation from n = 4 independent experiments. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. Two-way ANOVA, Tukey’s multiple comparisons test. Comparison of siCTRL to siPEX13 (d) and siPEX13 Mon to PFF (e), unpaired t-test, two tailed. Source data and exact P values are provided as a Source Data file.\n\nFigure 8: Figure 8. a Immunofluorescent images of STHdhQ7/7 or STHdhQ111/111 cells stained for peroxisomal marker, PMP70; blue=DAPI. Scale bar, 25 µm. b Quantification of PMP70 in (a). PMP70 was calculated by dividing the number of PMP70 puncta by cell volume. c Immunoblots of STHdhQ7/7 or STHdhQ111/111 cells treated for 24-h with 100 nM Torin1 and probed for mTOR, S6K, p-mTOR, p-S6K, and loading control Vinculin; representative of n = 3 independent experiments. d Representative images of STHdhQ7/7 or STHdhQ111/111 cells expressing either PMP34-GFP or PMP34-GFP-UBKo for 48-h, and immunostained for PMP70; blue = DAPI. Cells were grown in either DMSO or 100 nM Torin1 for the final 24-h. Scale bars, 25 µm. e Quantification of PMP70 in (d), relative to DMSO PMP34-GFP condition for each cell type. f Quantification of PMP34-GFP-UBKo-induced pexophagy in (d). Pexophagy was calculated as the percentage loss of PMP70 from DMSO PMP34-GFP conditions (see Methods). g Immunoblots of STHdhQ7/7 or STHdhQ111/111 cells treated as in (d), probed for HTT, PMP70, and loading control Vinculin. h Densitometry quantifications of PMP70 bands normalized to Vinculin and relative to DMSO PMP34-GFP condition for each cell type. i Quantification of PMP34-GFP-UBKo-induced pexophagy in (g). Data are displayed as means \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation from n = 3 (b), n = 4 (e, f), or n = 5 (h, i) independent experiments. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. b Unpaired t-test, two tailed. e, h Two-way ANOVA, Tukey’s multiple comparisons test. f, i One-way ANOVA, Tukey’s multiple comparisons test. Source data and exact P values are provided as a Source Data file.\n\nFigure 9: Figure 9. a Immunoblot of HeLa cells treated for 5-h with either DMSO or 20 µM LYN-1604 and probed for the indicated proteins. b Densitometry quantifications of ATG13 bands normalized to β-Actin, or the ratio of p-ATG13 band intensity/ATG13 band intensity from (a). c Quantification of aggrephagy activity in cells treated with the indicated siRNA and subjected to the puromycin-aggrephagy assay with a clearance period in either DMEM or LYN-1604 (representative images in Supplementary Data Fig. 8c). Aggrephagy activity was measured as the % clearance of FK1 aggregates, relative to mock transfected “3 h P + 5 h DMEM” cells. d Immunoblot of HeLa cells electroporated with an empty vector control or ULK1-FLAG and probed for the indicated proteins. e Densitometry quantifications of ATG13 bands normalized to β-Actin, or the ratio of p-ATG13 band intensity/ATG13 band intensity from (d). f HeLa cells treated with the indicated siRNA prior to transfection of an empty vector (Supplementary Data Fig. 8f) or ULK1-FLAG and subjection to the puromycin-aggrephagy assay. Representative images of cells at each stage in the assay: DMEM, 3-h 5 µg mL−1 Puromycin, or 3-h 5 µg mL−1 Puromycin followed by 5-h clearance period in DMEM. Cells were immunostained for FK2 and FLAG; blue=DAPI. Scale bars, 25 µm; white boxes, zoomed region. g Quantification of aggrephagy activity of cells in (f Supplementary Data Fig. 8f), relative to empty vector transfected “3 h P + 5 h DMEM” cells. Data are displayed as means from n = 6 (b), n = 3 (c,e), or n = 4 (g) independent trials \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm$$\\end{document}± standard deviation. Statistical significance is denoted as *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001, ns not significant. Unpaired t-test, two tailed. Source data and exact P values are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC10802466_multi",
    "image": [
      "images/PMC10802466-f1.png",
      "images/PMC10802466-f2.png",
      "images/PMC10802466-f3.png",
      "images/PMC10802466-f4.png",
      "images/PMC10802466-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Substrate recognition mechanism of the endoplasmic reticulum-associated ubiquitin ligase Doa10\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a, Schematic diagram of the domain structure of S. cerevisiae Doa10. Helices are represented as cylinders (TMs 1-14 are numbered). Numbers in gray indicate amino acid residue number. b, Cryo-EM density map of Doa10 viewed from the cytosol. Shown is a high-resolution protein density map overlaid with a lowpass-filtered detergent micelle density (gray). The color scheme is the same as in a. c, As in b, but showing a side view along the membrane plane. d, As in c, but overlaid a density map with a lower surface threshold to show RING-CH and L2/3 features. e and f, Atomic model of Doa10 based on the cryo-EM map. Views in e and f are equivalent to b and c, respectively. Parts that are unresolved in cryo-EM were schematized.\n\nFigure 2: Figure 2. a, Lipid molecules entrapped in the interior of the TMD. The orientation of the Doa10 model (viewed from the cytosol) is rotated by ~90° clockwise from Fig. 1b. b, As in a, but a lateral view from the central cavity to the middle domain. c, An AlphaFold2 model of the RING-CH and CTE domains. Shown is a side view, equivalent to view in d and Fig. 1f. d, A result of an MD simulation on WT Doa10 (side view). Positional flexibility of RING-CH is represented with multiple overlaid structures.\n\nFigure 3: Figure 3. a, Amino acid sequence conservation is mapped on the structure of Doa10. TMs 5 to 7 (referred to as the TD domain is indicated by dashed lines. The view (cytosolic view) is equivalent to that of Fig. 2a. b, As in a, but a lateral view from the central cavity to the middle domain. The lateral tunnel is highlighted in yellow. c, A view into the entrance of the lateral tunnel. Shown in a lowpass-filtered cryo-EM map. The boundary of detergent features in the central cavity is indicated by a dotted line.\n\nFigure 4: Figure 4. a, Schematic diagram of Doa10-dependent yeast growth inhibition assay using Deg1-Ura3. b, Structure of TMs 5 to 7 (TD domain). The view is similar to Fig. 3b. Positions of amino acid residues tested for the effects on Deg1-Ura3 degradation are shown with sticks and spheres (magenta: defects observed; cyan/blue: no substantial defects observed; see c and d). c and d, Yeast growth inhibition assay with indicated Doa10 mutants (GFP-tagged Doa10 was expressed at a relatively low level from the DOA10 promoter in a single-copy plasmid). e, As in c and d, but testing different mutants of Doa10 (with an ALFA-tag). Note that a higher expression level of Doa10-ALFA compared to Doa10-GFP (Supplementary Fig. 6a) produces stronger growth inhibition (compare WT and E633V from c). f, Cycloheximide chase experiments on Deg1-Ura3 using indicated Doa10 mutants (‘EV/SV’=E633V/S738V, ‘GS’=Δ710-718::GS, ‘GS+3Val’=Δ710-718::GS+3Val, and ‘EV/DV’=E713V/D714V). Means and s.e.m. are of three independent experiments. g-i, Example snapshots of MD simulations on WT and indicated Doa10 mutants. Blue licorice, L6/7 (positions 710-718); gray spheres, space-filling representation of the wedge-shaped tunnel-lining amino acids from TMs 5 to 7; red and white spheres, water molecules within the lateral tunnel; yellow, mutated valine residues. See Supplementary Fig. 7 for GS and GS+3Val mutants. j-l, The distance distribution was computed between the center of mass of the loop residues (712-715) and the hydrophobic wedge residues (F637, M686, F689, and Y742) for the wild type and mutant systems. The first 150 ns of each trajectory were removed to allow loop relaxation and the 2 replicas were combined. Cyan, residues 710-718; yellow, mutated residues; Gray, van der Waals spheres of wedge-lining residues; red/light gray, water molecules.\n\nFigure 5: Figure 5. a, A schematic diagram of Deg1-Ura and the secondary structure of Deg1 (predicted by AlphaFold2). b, In-vivo photocrosslinking experiment using Bpa-incorporated Deg1-Ura and wild-type Doa10. IP, immunoprecipitation. c, As in b, but Bpa was incorporated into a specific position in Doa10 instead of Deg1. d and e, Structure of the lateral tunnel (d, front view; e, side view) with highlighting the positions tested for crosslinking in panel c. Ribbons in yellow and green are TMs 5–7 and L8/9c, respectively. Residues in magenta crosslink to Deg1-Ura3. f, As in c, but testing the effects of Trx1 fusion on crosslinking with 734Bpa of Doa10. g, As in c, but testing the effects of tunnel mutations on crosslinking with 734Bpa of Doa10."
      }
    ]
  },
  {
    "id": "PMC10802466_multi_2",
    "image": [
      "images/PMC10802466-f6.png",
      "images/PMC10802466-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Substrate recognition mechanism of the endoplasmic reticulum-associated ubiquitin ligase Doa10\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a, AlphaFold2 model of Doa10 in complex with Ubc6 and Ub (a side view along the membrane plane). For Doa10, the RING-CH and N-terminal domains are shown in green, the middle domain in light brown, L8/9b in salmon, and the C-terminal domain in blue. Ubc6 is shown in magenta, and Ub is represented as cyan ribbon and semitransparent gray surface. b, As in a, but showing a model for the Doa10–Cue1–Ubc7–Ub complex. The area outlined with a gray box is shown in panel c. c, A view highlighting the interaction between Cue1 and L8/9b of Doa10 (Doa10 is in a surface representation). d, As in a, but showing the top (cytosolic) view. The area in a gray box is shown in panel f. e, As in b, but showing the top (cytosolic) view. The area in a gray box is shown in panel f. f, A view highlighting the interaction of Cue1 or Ubc6 with L8/9b of Doa10 (composite of the two models shown in d and e). g, Co-immunoprecipitation of Ubc6, Cue1, and Ubc7 with Doa10-GFP and its L8/9b truncation variant (ΔL8/9b). h and i, Bpa was introduced to indicated positions in Doa10, and UV photocrosslink to Ubc6 (panel h) or Cue1 (panel i) was examined by immunoprecipitation and immunoblotting.\n\nFigure 7: Figure 7. a, Schematic diagram of the Deg1-Vma12-Ura3 model substrate. Left, original construct; right, minimal construct. Numbers indicate the amino acid positions. b, Doa10-dependent yeast growth inhibition using various truncation variants of Deg1-Vma12-Ura3. c, As in b, but a Gly/Ser (GS) linker was inserted between the truncated Deg1 (Deg11-35) and Vma12Δ132. Two different GS linkers were tested: ‘10 GS’ = GGS GGS GGS G and ‘20 GS’= GGS GGS GGS GGS GGS GGS GG. d, Degradation of indicated Deg11-35-GS-Vma12Δ132 variants were measured by cycloheximide chase and immunoblotting (also see Supplementary Fig. 9b). Means and s.e.m. of three independent experiments. e, Working model for the substrate-recognition mechanism of Doa10."
      }
    ]
  },
  {
    "id": "PMC10819186_multi",
    "image": [
      "images/PMC10819186-f1.png",
      "images/PMC10819186-f2.png",
      "images/PMC10819186-f3.png",
      "images/PMC10819186-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Inhibition of VHL by VH298 Accelerates Pexophagy by Activation of HIF-1α in HeLa Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. VH298 promotes peroxisome reduction. (A) RPE/mRFP–EGFP–SKL cells were treated with VH298 (50 µM) for 48 h and then imaged under a fluorescence microscope. The percentage of puncta exhibiting EGFP(+)- and mRFP(+)-labeled autophagosomes or EGFP(−)- and mRFP(+)-labeled autolysosomes per cell was determined. The scale bar represents 20 µm (data are presented as mean ± standard error of the mean; n = 100, and *** p < 0.001). (B) HeLa cells stably expressing pmTurquiose2-Peroxi, pmTurquiose2-Mito, pmTurquiose2-ER, or pmTurquiose2-Golgi were imaged via confocal microscopy. The scale bar represents 20 µm. (C) HeLa cells treated with VH298 (50 µM) for 48 h were subjected to Western blotting by using the indicated antibodies against the protein markers of subcellular organelles (ABCD3 for peroxisomes, TOMM20 for mitochondria, P4HB for the ER, and FTCD for the Golgi apparatus).\n\nFigure 2: Figure 2. ATG5 or NBR1 depletion prevents VH298-induced peroxisome loss. (A) Wild-type and ATG5-KO HeLa cells were treated with VH298 (50 µM) for 48 h and then stained with anti-ABCD3 antibody. The number of peroxisomes per cell was estimated by analyzing approximately 100 cells. (B) After treatment with VH298 (50 µM) for 48 h, wild-type and ATG5-KO HeLa cells were subjected to Western blotting by using the indicated antibodies. (C) HeLa cells, which were transiently transfected with scrambled siRNA (Sc), siRNA targeting p62 (sip62), or NBR1 (siNBR1), were treated with or without VH298 (50 µM) for 48 h. Subsequently, cells were stained with anti-ABCD3 antibody, and the number of peroxisomes per cell was counted in approximately 100 cells. The scale bar indicates 20 µm (data are presented as mean ± standard error of the mean; *** p < 0.001, ns: not significant). (D) HeLa cells were treated with VH298 (50 µM) in the presence or absence of validated siRNA against NBR1 (siNBR1) and then harvested for analysis by Western blotting with the indicated antibodies.\n\nFigure 3: Figure 3. VH298 promotes ABCD3 ubiquitination-mediated pexophagy. (A) HeLa cells overexpressing HA and HA-UB were treated with VH298 (50 µM) for 48 h. Following treatment, the cells were harvested and subjected to immunoprecipitation by using anti-ABCD3 antibodies conjugated to agarose beads. The samples were analyzed via Western blotting by using the indicated antibodies. (B) HeLa cells were treated with VH298 (50 µM) for 48 h and subsequently stained with anti-ABCD3 (green) and anti-UB (red) antibodies. Pearson’s correlation coefficient was calculated to analyze the colocalization between ABCD3 and UB. The bars in the graph represent the results of colocalization analysis by using the Coloc 2 plugin in Fiji, utilizing Pearson’s correlation coefficient. The mean Pearson’s correlation coefficient values for the level of colocalization between ABCD3 and UB are indicated in the graph. The scale bar indicates 20 µm (data are presented as mean ± standard error of the mean; n = 100 and *** p < 0.001).\n\nFigure 4: Figure 4. VH298 induces pexophagy via HIF-1α activation. (A) RPE/mRFP–EGFP–SKL cells pretreated with VH298 (50 µM) for 42 h were further incubated with or without cycloheximide (10 µg/mL) for 6 h. The cells were then imaged by using a fluorescence microscope. The percentage of puncta exhibiting EGFP(+)- and mRFP(+)-labeled autophagosomes or EGFP(−)- and mRFP(+)-labeled autolysosomes per cell was determined. The scale bar indicates 20 µm (data are presented as mean ± standard error of the mean; n = 100 and *** p < 0.001). (B) RPE/mRFP–EGFP–SKL cells were treated with VH298 (50 µM), VL285 (50 µM), and roxadustat (50 µM) for 48 h and then imaged by using a fluorescence microscope. Subsequently, the fluorescence intensities of EGFP and mRFP were captured and quantified. The scale bar indicates 20 µm (data are presented as mean ± standard error of the mean; n = 100 and *** p < 0.001). (C) RPE cells were treated with VH298 (50 µM) and roxadustat (50 µM) for 48 h, after which they were analyzed via Western blotting by using the indicated antibodies. (D) RPE/mRFP-EGFP-SKL cells were transiently transfected with scrambled siRNA (Sc), siRNA targeting HIF-1α for 48 h, and then treated with or without VH298 (50 µM) for 48 h. The cells were then imaged by using a fluorescence microscope. The percentage of puncta exhibiting EGFP(+)- and mRFP(+)-labeled autophagosomes or EGFP(−)- and mRFP(+)-labeled autolysosomes per cell was determined. The scale bar indicates 20 µm (data are presented as mean ± standard error of the mean; n = 100 and *** p < 0.001)."
      }
    ]
  },
  {
    "id": "PMC10837142_multi",
    "image": [
      "images/PMC10837142-f1.png",
      "images/PMC10837142-f2.png",
      "images/PMC10837142-f3.png",
      "images/PMC10837142-f4.png",
      "images/PMC10837142-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Genome sequencing and functional analysis of a multipurpose medicinal herb Tinospora cordifolia (Giloy)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Summary of T. cordifolia genome assembly and genes. (a) Summary of generated data and genome assembly (b) Statistical summary of mapped genes of T. cordifolia.\n\nFigure 2: Figure 2. Phylogenetic tree showing the position of T. cordifolia with other species. The phylogenetic tree includes 26 core eudicot species, two basal eudicot species (T. cordifolia and Papaver somniferum) and a monocot species.\n\nFigure 3: Figure 3. Comparative analysis of T. cordifolia genome. (a) Phylogeny of six Ranunculales species including T. cordifolia (b) Venn diagram of ortholog gene clustering of six species (c) Biological processes of T. cordifolia specific genes (d) Cellular component of T. cordifolia specific genes (e) Molecular functions of T. cordifolia specific genes Figs. 3a and 3b are obtained from Orthovenn3138.\n\nFigure 4: Figure 4. Benzyl iso-quinoline alkaloid biosynthesis pathway in T. cordifolia. This pathway indicates the genes involved in biosynthesis of alkaloids like berberine, magnoflorine, palmatine, and tembetarine. It includes tyrosine aminotransferase (TAT), Hydroxyphenylpyruvate decarboxylase, Tyrosine decarboxylase (TYDC), Tyrosinase/Phenolase (TYR/3OHase), (S)-Norcoclaurine synthase (NCS), Norcoclaurine 6-O-methyltransferase (NoMT), (S)-Coclaurine N-methyltransferase (CNMT), N-Methylcoclaurine 3'-hydroxylase (NMCH), 3'-Hydroxy-N-methylcoclaurine 4' -O-methyltransferase (4OMT), Corytuberine synthase (CTS), (S)-Corytuberine-N-methyltransferase (SCNMT/RNMT), Berberine bridge enzyme (BBE), S)-Scoulerine 9-O-methyltransferase (SOMT/SMT), (S)-Tetrahydroprotoberberine oxidase (STOX), Columbamine O-methyltransferase (CoOMT), and (S)-Canadine synthase (CAS).\n\nFigure 5: Figure 5. Terpenoid biosynthesis pathway in T. cordifolia. This pathway indicates the genes involved in biosynthesis of terpenoids in T. cordifolia. It includes 1-deoxy-D-xylulose-5-phosphate synthase (DXS), 1-deoxy-D-xylulose-5-phosphate reductoisomerase (DXR), 2-C-methyl-D-erythritol 4-phosphate cytidylyltransferase (ispD), 4-diphosphocytidyl-2-C-methyl-D-erythritol kinase (ispE), 2-C-methyl-D-erythritol 2,4-cyclodiphosphate synthase (ispF), (E)-4-hydroxy-3-methylbut-2-enyl-diphosphate synthase (ispG), 4-hydroxy 3-methylbut-2-en-1-yl diphosphate reductase (ispH), Acetoacetyl-CoA thiolase (AACT), HMG-CoA synthase (HMGS), HMG-CoA reductase (HMGR), Mevalonate kinase (MK), Phosphomevalonate kinase (PMK), Mevalonate-5-diphosphate decarboxylase (MDD), Isopentenyl diphosphate isomerase (IDI), Geranyl diphosphate synthase (GPPS), Farnesyl diphosphate synthase (FPPS), Geranylgeranyl diphosphate synthase (GGPS), Farnesol kinase (FOLK), Farnesyl-diphosphate farnesyltransferase 1 (FDFT1), and Squalene monooxygenase (SQLE). Genes in red, blue, pink and green represents genes showing high nucleotide divergence, unique amino acid substitutions, positive selection, and multiple signatures of adaptive evolution, respectively."
      }
    ]
  },
  {
    "id": "PMC10837142_multi_2",
    "image": [
      "images/PMC10837142-f6.png",
      "images/PMC10837142-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Genome sequencing and functional analysis of a multipurpose medicinal herb Tinospora cordifolia (Giloy)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Common symbiosis signalling pathway in T. cordifolia. The figure (Created with BioRender.com) indicates the key genes of common symbiosis signalling pathway and the fill name of genes is provided in the Supplementary Table S16. Genes in pink indicates genes only with positive selection, yellow indicates genes showing only amino acid substitutions, blue indicates genes with two signatures, and green indicates genes with all three signatures of adaptive evolution.\n\nFigure 7: Figure 7. Peroxisome biogenesis pathway in T. cordifolia. The figure of peroxisome biogenesis is generated from KEGG database137. It includes genes PEX1, PEX2, PEX3, PEX5, PEX6, PEX7, PEX10, PEX11, PEX12, PEX13, PEX14, PEX16, PEX19, PEX26, PXMP2, MPV17, PXMP4, and PMP34. Genes in pink, yellow and green colour indicate genes showing one, two and all three signatures of adaptive evolution, respectively."
      }
    ]
  },
  {
    "id": "PMC10844355_multi",
    "image": [
      "images/PMC10844355-f1.png",
      "images/PMC10844355-f2.png",
      "images/PMC10844355-f3.png",
      "images/PMC10844355-f4.png",
      "images/PMC10844355-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Arabidopsis retromer subunit AtVPS29 is involved in SLY1-mediated gibberellin signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. AtVPS29 positively regulates SLY1 level but negatively regulates its expression. Total proteins were extracted from leaves of 15-day-old wild-type (WT) and vps29-3 mutants. After performing 11% SDS-PAGE, the levels of AtVPS29 and SLY1 were examined using western blotting with anti-AtVPS29 (a) or anti-SLY1 (b) antibodies. Numbers under the lanes indicate relative intensities. Tubulin was used as a loading control. c Total RNA was isolated from 15-day-old WT and vps29-3 mutant plants. Transcript levels were assessed using real-time qRT-PCR with SLY1-specific primers. Results are presented as means ± S.D. (n = 3). Asterisks indicate statistically significant differences in transcript levels (*p < 0.05; Student’s t test) between WT and vps29-3 mutants. SLY1, SLEEPY1\n\nFigure 2: Figure 2. Transcript levels of GA receptor genes in vps29-3 mutants. Total RNA was isolated from 15-day-old WT and vps29-3 mutants. Transcript levels were analyzed using real-time qRT-PCR with gene-specific primers. Results are presented as means ± S.D. (n = 3). Asterisks indicate statistically significant differences in transcript levels (*p < 0.05; ***p < 0.001; Student’s t test) between WT and vps29-3 mutants. Abbreviations: GID1a, GA-INSENSITIVE DWARF 1a; GID1b, GA-INSENSITIVE DWARF 1b; GID1c, GA-INSENSITIVE DWARF 1c\n\nFigure 3: Figure 3. Transcript levels of GA-synthetic genes in vps29-3 mutants. Total RNA was isolated from 15-day-old WT and vps29-3 mutants. Transcript levels were analyzed using real-time qRT-PCR with gene-specific primers. Results are presented as means ± S.D. (n = 3). Asterisks indicate statistically significant differences in transcript levels (**p < 0.01; ***p < 0.001; Student’s t test) between WT and vps29-3 mutants. Abbreviations: GA20ox2, GIBBERELLIN 20-OXIDASE 2; GA3ox1, GIBBERELLIN 3-OXIDASE 1; GA3ox2, GIBBERELLIN 3-OXIDASE 2\n\nFigure 4: Figure 4. AtVPS29 negatively regulates RGA level but positively regulates its expression. a Total proteins were extracted from leaves of 15-day-old WT and vps29-3 mutants. After subjecting them to 11% SDS-PAGE, the levels of RGA were analyzed by western blotting using anti-RGA antibody. Numbers under the lanes indicate relative intensities. Tubulin was used as a loading control. b Total RNA was isolated from 15-day-old WT and vps29-3 mutants. Transcript levels were determined using real-time qRT-PCR with RGA-specific primers. Results are expressed as means ± S.D. (n = 3). Asterisks indicate statistically significant differences in transcript levels (***p < 0.001; Student’s t test) between WT and vps29-3 mutants. RGA, REPRESSOR OF ga1-3\n\nFigure 5: Figure 5. vps29-3 mutants are less sensitive to exogenous GA. a Comparison of leaf size and root length between WT and vps29-3 mutants after 8 days of growth on 1/2 MS medium (mock) and 1/2 MS medium supplemented with 10 and 20 µM GA3, respectively. Scale bar 1 cm. b, c Statistical analysis of the differences in leaf size (b) and root length (c) between the genotypes shown in (a). Data are presented as means ± S.D (n > 10). Black and white circles indicate WT and vps29-3 mutants, respectively"
      }
    ]
  },
  {
    "id": "PMC10844355_multi_2",
    "image": [
      "images/PMC10844355-f6.png",
      "images/PMC10844355-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Arabidopsis retromer subunit AtVPS29 is involved in SLY1-mediated gibberellin signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. vps29-3 mutants show reduced root meristem size. a Confocal images of root tips of WT and vps29-3 mutants. Roots from seedlings 7 days after germination were used for imaging. White arrowheads indicate the boundary between the meristematic and elongation zones of the root. Scale bars correspond to 25 μm. b Root meristem cell number in the roots of 7-day-old WT and vps29-3 mutants. Asterisks indicate statistically significant differences in transcript levels (***p < 0.001; Student’s t test) between WT and vps29-3 mutants. Values represent the mean of 15 measurements ± SD. c Average cortex cell sizes in the roots of 6-day-old WT and vps29-3 mutants. Each value represents measurements from at least 15 seedlings. The median, minimum, and maximum values are shown. NS, not significant\n\nFigure 7: Figure 7. Schematic representation of the possible mechanism of activation of GA signaling by AtVPS29. a In wild-type plants, SLY1 undergoes sumoylation via AtSIZ1 activity, which converts it into its active form. Sumoylated SLY1 forms the SCFSLY1−SUMO complex, which targets DELLA proteins, including RGA, for ubiquitination. Polyubiquitinated DELLA proteins are subsequently degraded by the 26S proteasome complex. This process promotes cell division and expansion, leading to growth and development. b Due to potentially reduced AtSIZ1 activity in vps29-3 mutants, SLY1 might not undergo sumoylation, leading to its inactivation and consequent accumulation of RGA. As a result, cell division and expansion are inhibited, leading to dwarfism"
      }
    ]
  },
  {
    "id": "PMC10847333_multi",
    "image": [
      "images/PMC10847333-f1.png",
      "images/PMC10847333-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Advancements and future prospects of adeno-associated virus-mediated gene therapy for sensorineural hearing loss\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Overview of inner ear delivery routes, structure of the organ of corti, and causal genes associated with hearing loss in preclinical studies. (A) The four local delivery routes to the inner ear include (1) RWM injection, (2) RWM injection combined with CF, (3) cochleostomy, (4) utricle injection, and (5) canalostomy. (B) Structure organ of corti. ASCC, anterior semicircular canal; PSCC, posterior semicircular canal; LSCC, lateral semicircular canal; RWM, round window membrane; CF, semicircular canal fenestration.\n\nFigure 2: Figure 2. Overview of dual-AAV system restoring the expression of the large therapeutic proteins. The CDS of a gene is bifurcated into two sections (5’ and 3’), each of which is encapsulated into two AAVs. When co-transduced into the same cell, various methods are be used to reestablish the expression of large therapeutic proteins. This restoration process involves the recombination of the two segments at multiple stages: the DNA level (A), the pre-mRNA level (B), or directly at the protein level (C). (A) Reconstitution full-length CDS: the trans-splicing method involves the reconstitution of the full-length CDS through the process of concatemerization of the two vectors mediated by ITRs, followed by the splicing signals which eliminate the ITR structure. In the overlapping method, both vectors contain an overlap region, which functions as a homologous sequence, enabling the two gene segments to recombine effectively. The hybrid method design of the two vectors imitates that of the trans-splicing method, but with an added HR positioned downstream of the SD in the 5’-vector and upstream of the SA in the 3’-vector. The full gene can be reassembled either through ITR-mediated concatemerization or homologous recombination, followed by splicing to remove the intermediate sequence. (B) Reconstitution of full-length mRNA: in this approach, the two mRNA pair up via their complementary HDs, followed by splicing which results in the elimination intermediate sequence. (C) Reconstitution of full-length protein: the self-recognition and self-excision of inteins facilitate pairing the two half polypeptides to form the full-length protein. 5’CDS, 5’ portion of the coding sequence; 3’CDS; 3’ portion of the coding sequence; AAV, adeno-associated virus; ITR, inverted terminal repeat; HR, highly recombinogenic exogenous sequence; SD, splicing donor; SA, splicing acceptor; HD, hybridization domain; prom, promoter; polyA, polyadenylation (figure modified from Tornabene and Trapani, 2020)."
      }
    ]
  },
  {
    "id": "PMC10864527_multi",
    "image": [
      "images/PMC10864527-f1.png",
      "images/PMC10864527-f2.png",
      "images/PMC10864527-f3.png",
      "images/PMC10864527-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Generation and characterization of a zebrafish gain-of-function ACOX1 Mitchell disease model\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Brain and spinal cord imaging. At initial presentation: (A) MRI cervical spine sagittal T2-weighted image with hyperintense signal involving the central gray matter, dorsal and lateral tracts of the cervical and thoracic spinal cord (yellow arrow). (B) MRI thoracic spine axial T2-weighted image with hyperintense signal involving primarily gray matter (yellow arrow). (C) MRI cervical spine axial post-gadolinium T1-weighted image with contrast enhancement of the dorsal white matter tracts (yellow arrow). Follow-up at 6 months: (D) MRI cervical spine sagittal T2-weighted image with re-demonstration of central gray matter hyperintensity of the cervical and thoracic spinal cord with associated volume loss (white arrow). (E) MRI cervical spine axial T2-weighted image with increased hyperintense signal involving primarily gray matter and volume loss within the gray matter tracts (white arrow). (F) MRI brain axial T2-weighted FLAIR image with diffuse parenchymal volume loss and nearly symmetric bilateral periventricular and deep white matter signal abnormality in the frontal, parietal, and occipital lobes (white arrows). Obtained 2 weeks before death: (G) MRI cervical spine sagittal T2-weighted image with recurrent non-enhancing hyperintense signal involving primarily the dorsal central aspect of the spinal (red arrow). (H) MRI brain axial T1-weighted imaging post-gadolinium with contrast enhancement involving the optic chiasm, prechiasmatic optic nerves, and bilateral optic tracts within the suprasellar region (red arrows). (I) MRI brain axial T2-weighted FLAIR image with progressive bilateral periventricular white matter signal abnormality with central areas of white matter necrosis (red arrows).\n\nFigure 2: Figure 2. (A) Zebrafish Acox1 protein is highly conserved compared to human ACOX1. The degree of amino acid similarity is indicated by color, with red being identical and blue being non-conserved, as visualized using PRALINE. (B) Schematic diagram of expression constructs used in zebrafish experiments. (C) Confocal z-stack images of the expression of the construct in live zebrafish larvae; immunohistochemistry for anti-GFP, and anti-RFP in the Tg(olig2:dsRed) line. Dorsal to top, rostral to the right; age 3 dpf. Note: the black line in the middle of the figure indicates where the image was stitched together. (D) Confocal z-stack images, spinal cord, rostral to the right, dorsal to the top. Expression of N237S is indicated by tagged GFP, and mature oligodendrocytes are labeled by olig2:dsRed. (E) Quantification shows no effect on oligodendrocyte numbers.\n\nFigure 3: Figure 3. Characterization of zebrafish mutant experiments by overexpression of human ACOX1 N237S. (A) Schematic diagram of experiments. (B) Zebrafish show abnormal motor (swimming) behavior, which is rescued by D-NAC. ***p < 0.001. (C) qRT-PCR characterization of transcripts. Expression of mutant form does not impact myelin transcripts or general inflammatory markers but does activate the ISR (atf4).\n\nFigure 4: Figure 4. Zebrafish peroxisomal reporter construct and characterization of effects on peroxisomes. (A) Schematic of the mCherry-SKL construct and transient expression in zebrafish. Confocal z-stack, lateral view of the trunk, live 3 dpf larva, green channel, DCFH-DA (dacetyldichlorofluorescein). (B) Live confocal images and paired IMARIS (3D reconstruction) image (below), of mCherry-SKL (red) containing peroxisomes in the hair cells (blue) of larval zebrafish neuromast at 6 dpf in zebrafish overexpressing WT or N237S ACOX1. (C) Size and distance to nearest neighbors in zebrafish overexpressing WT or N237S ACOX1, showing a decreased density of peroxisomes in these cells. (D) qRT-PCR for expression of genes that affect the abundance of peroxisome: pparab, pex11a, pex11b, pex11g, and nrb1b."
      }
    ]
  },
  {
    "id": "PMC10873952_multi",
    "image": [
      "images/PMC10873952-f1.png",
      "images/PMC10873952-f2.png",
      "images/PMC10873952-f3.png",
      "images/PMC10873952-f4.png",
      "images/PMC10873952-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Tissue-specific roles of peroxisomes revealed by expression meta-analysis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pathway-related genes in peroxisomes and mitochondria. For simplicity, only human gene symbols are shown within the figure. a Mammalian peroxisome biogenesis factors include matrix protein receptors PEX5 and PEX7, membrane biogenesis factors PEX3, PEX16, and PEX19; docking and import complex components PEX13 and PEX14; E3 ubiquitin ligase complex PEX2, PEX10, and PEX12; the AAA complex PEX1 and PEX6 with tail-anchored PEX26. TYSND1 and LONP2 process imported matrix proteins. The PEX11 family is involved in the elongation of peroxisomes; the fission of peroxisomes and mitochondria requires FIS1, MFF, DNM1L, and GDAP1. E3 ubiquitin ligase TRIM37 and autophagy receptors NBR1 and SQSTM1 mediate pexophagy. b Metabolite flux in peroxisomes relies on pore formation by PXMP2, PXMP4, and SLC25A17. ABCD1, ABCD2, and ABCD3 import FAs with different substrate selectivity. c CAT, EPHX2, and GSTK1 facilitate ROS metabolism, and D-AAs are oxidized by DAO and DDO. d BCFAs are metabolized by PHYH, HACL1, and ALDH3A2. SLC27A2 activates and transports BCFAs. AMACR converts the (2R)-enantiomer. e Mitochondrial β-oxidation requires FA import by the carnitine shuttle CPT1A, CPT1B, CPT1C, CPT2, and SLC25A20 (red), see b for peroxisomal import factors. Mitochondrial import is followed by dehydrogenation (blue) by ACADS, ACADSB, ACADM, ACADL, ACADVL, ACAD9, or ACAD10; the peroxisomal analogs are ACOX1, ACOX2, and ACOX3. Mitochondrial ECI1 and DECR1 break down unsaturated FAs by isomerization and oxidation of double bonds. Hydration, oxidation, and thiolytic cleavage are carried out by multifunctional or individual enzymes (green): HADHA, HADHB, ECHS1, HADH, ACAA2 in mitochondria, and EHHADH, HSDB174, ACAA1 in peroxisomes. ACOT4 and ACOT8 catalyze the hydrolysis of acyl-CoAs into free FAs and CoA. CROT catalyzes the export of peroxisomal FAs. ACBD4 and ACBD5 tether peroxisomes to the ER. f Plasmalogen synthesis involves FAR1- or FAR2-mediated reduction of acyl-CoAs to primary fatty alcohols and synthesis of an ether-linked intermediate by GNPAT and AGPS. The peroxisomal enzymes, BAAT and ECI2 are essential for BA and PUFA synthesis, respectively\n\nFigure 2: Figure 2. Peroxisome biogenesis, fission, and pexophagy factors are uniformly expressed across different tissues. a, b Heatmaps showing transcriptome (green) and proteome data (blue) of a) humans and b mice for indicated genes and proteins. Gray indicates missing values. c Calculated ratios for PEX7/PEX5 and PTS2/PTS1-cargos of human and murine transcriptome data with indicated significant differences relative to cardiac tissue. Error bars represent SEM. ns, not significant; *p < 0.05; **p < 0.01; ***p < 0.001; ****p < 0.0001. d Distributions of human and murine transcriptome data for all peroxins. e Human and murine transcriptome (green) and proteome (blue) data, and f summarized distributions of human and murine transcriptome data for pexophagy, the mitochondrial, and peroxisomal fission complex\n\nFigure 3: Figure 3. Factors for peroxisomal metabolite flux, ROS, and D-AA metabolism are equally distributed except for low cerebral ROS factors and higher expression in the liver and murine kidney. a–d Transcriptome (green) and proteome (blue) data in a humans and b mice together with respective summarized distributions in c humans and d mice for peroxisomal metabolite flux. e–h Heatmaps visualizing transcriptome (green) and proteome (blue) in e humans and f mice with summarized distributions of transcriptome data in g humans and h mice of peroxisomal factors involved in ROS and D-AA metabolism\n\nFigure 4: Figure 4. Expression of mitochondrial and peroxisomal β-oxidation factors. Mitochondrial β-oxidation factors are high in the liver and heart, whereas their peroxisomal counterparts are high in hepatic and renal tissue. a–d Transcriptome (green) and proteome (blue) data in a humans and c mice next to summarized distributions of transcriptome data in b human and d mice of factors involved in mitochondrial β-oxidation. e–h Heatmaps of the transcriptome (green) and proteome data (blue) in e humans and g mice with summarized distributions of transcriptome data in f human and h mice of peroxisomal β-oxidation factors\n\nFigure 5: Figure 5. Expression profiles of α-oxidation and biosyntheses of plasmalogens, PUFAs, and BAs. α-Oxidation, BA, and PUFA biosynthesis factors are most abundant in the liver and least abundant in the brain, while factors for plasmalogen synthesis are highly expressed in cardiac tissue. a–d Transcriptome (green) and proteome data (blue) in a humans and c mice with summarized distributions of transcriptome data in b human and d mice of factors involved in peroxisomal α-oxidation. e, g Heatmaps showing transcriptomics (red) and proteomics (blue) in e humans and g mice of peroxisomal factors involved in plasmalogen, PUFA, and BA biosynthesis. f, h Aggregated distributions of transcriptome data in f human and h mice of peroxisomal factors involved in plasmalogen biosynthesis"
      }
    ]
  },
  {
    "id": "PMC10910329_multi",
    "image": [
      "images/PMC10910329-f1.png",
      "images/PMC10910329-f2.png",
      "images/PMC10910329-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Plasma C24:0- and C26:0-lysophosphatidylcholines are reliable biomarkers for the diagnosis of peroxisomal β-oxidation disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Plasma C24:0- and C26:0-LPC showed excellent diagnostic accuracy for peroxisomal β-oxidation deficiencies. Plasma concentrations of very long-chain LPCs were analyzed in 340 patients and 407 control individuals. Each graph corresponds to one analyte (C26:0-, C24:0-, and C22:0-LPC). Patients are presented both as a collective group and divided by disease category. Plasma LPCs concentrations are plotted in box-and-whisker format, with dotted lines indicating the cutoff values (C26:0-LPC ≤ 0.17 μmol/L, C24:0-LPC ≤ 0.27 μmol/L, and C22:0-LPC ≤ 0.19 μmol/L). Abbreviations are as follows, with the number of patients in each group shown in brackets: CTRL = controls (n = 407), ALL PT = total patients (n = 340), ♂ ALD = male adrenoleukodystrophy patients (n = 155), ♀ALD = female adrenoleukodystrophy patients (n = 77), ZSD = Zellweger spectrum disorder patients (n = 61), UnPD = Patients with a deficient peroxisomal β-oxidation by VLCFA analysis lacking a differential diagnosis (n = 47). Significantly higher concentrations of all three very long-chain LPCs were observed in all disease groups when compared with control individuals (P < 0.0001). The highest C24:0- and C26:0-LPC concentrations were observed in ZSD patients (ranging from 0.28 to 2.17 μmol/L and 0.16–3.68 μmol/L, respectively), whereas ALD males presented the highest C22:0-LPC values (ranging from 0.08 to 1.23 μmol/L). ALD males also exhibited significantly higher concentrations of C22:0-LPC (P < 0.0001), C24:0-LPC (P < 0.0001), and C26:0-LPC (P ≤ 0.001) than ALD females. Plasma C26:0-LPC concentrations were significantly higher in ZSD patients compared with ALD males (P < 0.0001), while an inverse relation was observed for plasma C22:0-LPC (P < 0.0001). No differences were observed for plasma C24:0-LPC between these two groups.\n\nFigure 2: Figure 2. C24:0- and C26:0-LPC showed higher specificity than VLCFA in plasma samples with elevated triglyceride concentrations. Plasma very long-chain LPCs and VLCFA were analyzed in samples collected from individuals with hypertriglyceridemia. Each data point on the scatter plot represents a plasma sample obtained from a single individual (n = 20; median triglyceride concentration = 12.08 mmol/L; range = 5.65–29.62 mmol/L; cutoff < 1.69 mmol/L). Dotted lines indicate the cutoff values for each parameter. Among these individuals, 14 out 20 (70.0%) presented an abnormal VLCFA profile. This included eight individuals with an increase in C26:0, one with an elevated C26:0/C22:0 ratio and five individuals with elevations in both C26:0 and C26:0/C22:0. In contrast, only one patient (H1) exhibited a slight increase in C24:0- and C26:0-LPC (0.30 and 0.23 μmol/L, respectively), and this patient also showed increases in C26:0 and the C26:0/C22:0 ratio.\n\nFigure 3: Figure 3. The C26:0-LPC/C22:0-LPC ratio is a valuable parameter to biochemically differentiate ZSD from ALD patients. A: The C26:0-LPC/C22:0-LPC ratios obtained for the different patient groups are shown. Abbreviations are as follows, with the number of patients in each group indicated in brackets: ZSD = Zellweger spectrum disorder patients (n = 61), ALD = total adrenoleukodystrophy patients including males and females (n = 232), ♂ ALD = male adrenoleukodystrophy patients (n = 155), ♀ ALD = female adrenoleukodystrophy patients (n = 77), ns = not statistically significant. Since differences in the C26:0-LPC/C22:0-LPC ratio between ALD males and ALD females were not statistically significant, all ALD individuals were considered as a single group for this analysis. B: ROC curve analysis demonstrated superior performance for the C26:0-LPC/C22:0-LPC ratio (red curve) to differentiate ZSD and ALD patients compared with individual plasma C26:0-LPC (blue curve) or C22:0-LPC (green curve) concentrations. The results of the ROC curve analyses are as follows (CI = confidence interval; AUC = area under the curve): C26:0-LPC/C22:0-LPC ratio: AUC = 0.91 (95% CI 0.86–0.96); C26:0-LPC: AUC = 0.83 (95% CI 0.76–0.90); C22:0-LPC: AUC = 0.72 (95% CI 0.64–0.80). ROC, receiver operating characteristic."
      }
    ]
  },
  {
    "id": "PMC10928120_multi",
    "image": [
      "images/PMC10928120-f1.png",
      "images/PMC10928120-f2.png",
      "images/PMC10928120-f3.png",
      "images/PMC10928120-f4.png",
      "images/PMC10928120-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Substrate recognition mechanism of the endoplasmic reticulum-associated ubiquitin ligase Doa10\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Schematic diagram of the domain structure of S. cerevisiae Doa10. Helices are represented as cylinders (TMs 1-14 are numbered). Numbers in gray indicate amino acid residue number. b Cryo-EM density map of Doa10 viewed from the cytosol. Shown is a high-resolution protein density map overlaid with a lowpass-filtered detergent micelle density (gray). The color scheme is the same as in (a). c As in (b), but showing a side view along the membrane plane. d As in (c), but overlaid a density map with a lower surface threshold to show RING-CH and L2/3 features. e, f Atomic model of Doa10 based on the cryo-EM map. Views in (e) and (f) are equivalent to (b) and (c), respectively. Parts that are unresolved in cryo-EM were schematized.\n\nFigure 2: Figure 2. a Lipid molecules entrapped in the interior of the TMD. The orientation of the Doa10 model (viewed from the cytosol) is rotated by ~90° clockwise from Fig. 1b. b As in (a), but a lateral view from the central cavity to the middle domain. c An AlphaFold2 model of the RING-CH and CTE domains. Shown is a side view, equivalent to view in (d) and Fig. 1f. d Result of an MD simulation on WT Doa10 (side view). Positional flexibility of RING-CH is represented with multiple overlaid structures.\n\nFigure 3: Figure 3. a Amino acid sequence conservation is mapped on the structure of Doa10. TMs 5 to 7 (referred to as the TD domain is indicated by dashed lines. The view (cytosolic view) is equivalent to that of Fig. 2a. b As in (a), but a lateral view from the central cavity to the middle domain. The lateral tunnel is highlighted in yellow. c A view into the entrance of the lateral tunnel. Shown in a lowpass-filtered cryo-EM map. The boundary of detergent features in the central cavity is indicated by a dotted line.\n\nFigure 4: Figure 4. a Schematic diagram of Doa10-dependent yeast growth inhibition assay using Deg1-Ura3. b Structure of TMs 5 to 7 (TD domain). The view is similar to Fig. 3b. Positions of amino acid residues tested for the effects on Deg1-Ura3 degradation are shown with sticks and spheres (magenta: defects observed; cyan/blue: no substantial defects observed; see c and d). c, d Yeast growth inhibition assay with indicated Doa10 mutants (GFP-tagged Doa10 was expressed at a relatively low level from the DOA10 promoter in a single-copy plasmid). e As in (c) and (d), but testing different mutants of Doa10 (ALFA-tagged). Note that a higher expression level of Doa10-ALFA compared to Doa10-GFP produces stronger growth inhibition. f Cycloheximide chase experiments on Deg1-Ura3 using indicated Doa10 mutants (‘EV/SV’ = E633V/S738V, ‘GS’ = Δ710-718::GS, ‘GS+3Val’=Δ710-718::GS+3Val, and ‘EV/DV’ = E713V/D714V). Mean ± s.e.m. of three independent experiments. g–i Example snapshots of MD simulations for WT and indicated Doa10 mutants illustrating the collapse of the L6/7 loop. L6/7 are rendered in blue licorice, along with the sidechains for positions 710–718. The residues forming the hydrophobic wedge of the tunnel (F637, M686, F689, and Y742) are rendered in both gray semitransparent surface and licorice, with the center of mass (COM) of the loop residues 712–715 and the COM of the wedge residues rendered as orange spheres. Their separation is indicated with a black line. In these snapshots, the separation distances are 15.9 Å, 11.4 Å, and 14.0 Å for WT, E633V/S738V, and E713V/D714V, respectively. The mutated valine residues are rendered in yellow. See Supplementary Fig. 8 for GS and GS+3Val mutants. j–l The distance distribution was computed between the center of mass of the loop residues (712–715) and the hydrophobic wedge residues (F637, M686, F689, and Y742) for the wild type and mutant systems. The first 150 ns of each trajectory were removed to allow loop relaxation and the 2 replicas were combined. Data in (c–e) are representative of three independent experiments. Data in (f) are mean ± s.e.m. from three independent experiments. Source data are provided as a Source Data file.\n\nFigure 5: Figure 5. a Schematic diagram of Deg1-Ura and the predicted secondary structure of Deg1 using AlphaFold2. b In-vivo photocrosslinking experiment using Bpa-incorporated Deg1-Ura and wild-type Doa10. IP, immunoprecipitation. c As in (b), but with Bpa incorporated into a specific position in Doa10 instead of Deg1. d, e Structure of the lateral tunnel (d, front view; e, side view), highlighting positions tested for crosslinking in panel (c). Ribbons in yellow and green represent TMs 5–7 and L8/9c, respectively. Residues in magenta crosslink to Deg1-Ura3. f As in (c), but testing the effects of Trx1 fusion on crosslinking with 734Bpa of Doa10. g As in (c), but testing the effects of tunnel mutations on crosslinking with 734Bpa of Doa10. Data in (b, c, f, g) are representative of two independent experiments. Source data are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC10928120_multi_2",
    "image": [
      "images/PMC10928120-f6.png",
      "images/PMC10928120-f7.png",
      "images/PMC10928120-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Substrate recognition mechanism of the endoplasmic reticulum-associated ubiquitin ligase Doa10\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a In-vivo UV photocrosslinking experiment testing a direct interaction between the CL1 degron and lateral tunnel of Doa10. p-Benzoyl-L-phenylalanine (Bpa) was incorporated into either amino acid position 734 (tunnel interior) or 926 (cytosolic surface) of Doa10. Deg1-Ura3-2xStrep was used as a positive control. IP, immunoprecipitation. b As in (a), but testing mScarlet-Sbh2 and mScarlet-Pex15Δ30 as substrates. Note that these substrates also contain 2xStrep-tag immediately after mScarlet for immunodetection. c mScarlet fluorescence intensity measurements on yeast cells expressing mScarlet-Sbh2 (under the TEF1 promoter) and Doa10 variants (under the RET2 promoter). Where indicated, the substrate or Doa10 or both were omitted in constructing strains. Intensities were normalized with respect to the WT Doa10-expressing strain. Mean ± s.e.m. of 6 independent experiments. d As in (c), but testing mScarlet-Pex15Δ30 as a substrate. Mean ± s.e.m. of 7 independent experiments. e, f Cycloheximide chase experiments using mScarlet-Sbh2 (e) or mScarlet-Pex15Δ30 (f) and indicated Doa10 variants (strains identical to those in c and d). Pgk1 was used as a loading control. Data in (a, b, e, f) are representative of three independent experiments. Statistical significance was accessed by unpaired t-test (two-tailed). *p = 0.0091; ***p < 0.0001. Source data are provided as a Source Data file.\n\nFigure 7: Figure 7. a AlphaFold2 model of Doa10 in complex with Ubc6 and Ub (a side view along the membrane plane). For Doa10, the RING-CH and N-terminal domains are shown in green, the middle domain in light brown, L8/9b in salmon, and the C-terminal domain in blue. Ubc6 is shown in magenta, and Ub is represented as cyan ribbon and semitransparent gray surface. Low-confidence (pLDDT <50) regions were now shown. We generated a total of five models, and all models were highly similar to one another with Cα RMSD ranging from 0.9 to 1.5 Å. b As in (a), but showing a model for the Doa10–Cue1–Ubc7–Ub complex. The area outlined with a gray box is shown in panel (c). We generated a total of five models, and all models were highly similar to one another with Cα RMSD ranging from 1.5 to 2.2 Å. c A view highlighting the interaction between Cue1 and L8/9b of Doa10 (Doa10 is in a surface representation). d As in (a), but showing the top (cytosolic) view. The area in a gray box is shown in panel (f). e As in (b), but showing the top (cytosolic) view. The area in a gray box is shown in panel (f). f A view highlighting the interaction of Cue1 or Ubc6 with L8/9b of Doa10 (composite of the two models shown in d and e). g Co-immunoprecipitation of Ubc6, Cue1, and Ubc7 with Doa10-GFP and its L8/9b truncation variant (ΔL8/9b). Doa10, Ubc6, Cue1, and Ubc7 were overexpressed from CEN/ARS plasmids using a GAL1 promoter. h, i Bpa was introduced to indicated positions in Doa10, and UV photocrosslink to Ubc6 (panel h) or Cue1 (panel i) was examined by immunoprecipitation and immunoblotting. Ubc6, Cue1, and Ubc7 were overexpressed from CEN/ARS plasmids using a GAL1 promoter while Doa10 was expressed from CEN/ARS plasmids using a TDH3 promoter. Data in (g, h, i) are representative of two independent experiments. Source data are provided as a Source Data file.\n\nFigure 8: Figure 8. a Schematic diagram of the Deg1-Vma12-Ura3 model substrate. Left, original construct; right, minimal construct. Numbers indicate the amino acid positions. b Doa10-dependent yeast growth inhibition using various truncation variants of Deg1-Vma12-Ura3. c As in (b), but a Gly/Ser (GS) linker was inserted between the truncated Deg1 (Deg11–35) and Vma12Δ132. Two different GS linkers were tested: ‘10 GS’ = GGS GGS GGS G and ‘20 GS’ = GGS GGS GGS GGS GGS GGS GG. d Degradation of indicated Deg11–35-GS-Vma12Δ132 variants were measured by cycloheximide chase and immunoblotting (also see Supplementary Fig. 12b). Means and s.e.m. of three independent experiments. e Working model for the substrate-recognition mechanism of Doa10. Cytosolic substrates could be either soluble proteins with an N- or C- terminal degron (e.g., Deg1 and CL1) or TA membrane proteins that are extracted by the Msp1 and Spf1 ATPases (e.g., Pex15Δ30). Transmembrane substrates could be membrane proteins with a degron (either intrinsic or generated by damage or unfolding) in their cytosolic domains (e.g., Deg1-Vma12). Data in (b, c) are representative of two independent experiments. Data in (d) are mean ± s.e.m. from three independent experiments."
      }
    ]
  },
  {
    "id": "PMC10946116_multi",
    "image": [
      "images/PMC10946116-f1.png",
      "images/PMC10946116-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The natural history and burden of illness of metachromatic leukodystrophy: a systematic literature review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PRISMA diagram. aThe reference lists from these publications were cross-checked against lists of included references to ensure that all relevant data were identified. Data from SLRs/meta-analyses were not extracted. bFour references were data-extracted, but data were either not reported separately for patients with MLD, or no relevant data were reported in the publication. cOf the 120 publications from which data were extracted, 108 related to the natural history and burden of illness of MLD (i.e., non-treatment related). MLD: metachromatic leukodystrophy; PRISMA: Preferred Reporting Items for Systematic review and Meta-Analysis; SLR: systematic literature review\n\nFigure 2: Figure 2. MLD comorbidities and complications reported in three or more studies. Comorbidities and complications related to MLD were reported in 35 studies. MLD: metachromatic leukodystrophy"
      }
    ]
  },
  {
    "id": "PMC10950804_multi",
    "image": [
      "images/PMC10950804-f1.png",
      "images/PMC10950804-f2.png",
      "images/PMC10950804-f3.png",
      "images/PMC10950804-f4.png",
      "images/PMC10950804-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Adipose tissue peroxisomal lipid synthesis orchestrates obesity and insulin resistance through LXR-dependent lipogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PexRAP-AKO mice have increased diet induced obesity.A) Diagram of the peroxisomal pathway involved in ether lipid synthesis. The initial steps of ether lipid synthesis occur in peroxisomes, generating 1-O-alkyl glycerol-3-phosphate (AGP), a precursor of ether lipids, such as plasmalogens. The subsequent steps take place in the endoplasmic reticulum (ER). Peroxisomes can also generate lysophosphatidic acid (LPA), a precursor of conventional diacyl phospholipids. Structures of a diacyl phospholipid and a plasmalogen are shown, where X is usually a choline or an ethanolamine. Abbreviations: ACSL, acyl-CoA synthetase; AGPS, alkylglycerone phosphate synthase; DHAP, dihydroxyacetone phosphate; FAR1, fatty acyl-CoA reductase; GNAPT, glyceronephosphate O-acyltransferase; PexRAP, Peroxisomal Reductase activating PPARγ. B) qPCR analysis of PexRAP and FASN gene expression in wild-type C57BL/6J mice fed a chow or high-fat diet (60% kcal fat) for 22 weeks (n = 11–13 for iWAT and gWAT, 5–7 for BAT). C) Western blot analysis of iWAT tissue from control or PexRAP-AKO mice. D) Body weight of male control and PexRAP-AKO mice fed a high fat diet (HFD, 60% kcal fat) beginning at 8 weeks of age (n = 8–9). E) Body composition results from EchoMRI analysis of male control and PexRAP-AKO mice fed a HFD for 16 weeks (n = 7–9). F) Mass of tissues from male control and PexRAP-AKO mice fed a HFD for 16 weeks (n = 6–8). G) Hematoxylin and eosin (H&E) staining of formalin-fixed paraffin embedded (FFPE) tissues from male control and PexRAP-AKO mice fed a HFD for 19 weeks from which H) iWAT and I) gWAT cell area were quantified (n = 3 mice/group) using AdipoSoft/ImageJ [60]. Data are shown as mean ± SEM. Comparisons between groups were made with a two-tailed unpaired Student's t-test (B,D,E,F,H,I).\n\nFigure 2: Figure 2. PexRAP-AKO mice fed a high fat diet (60% kcal fat) have impaired glucose homeostasis, decreased insulin signaling, hyperlipidemia, and increased immune cell infiltration of adipose tissue.A) Glucose tolerance test and B) area of the curve measurements of male control and PexRAP-AKO mice fed a HFD for 12 weeks (n = 17–18). C) Glucose-stimulated insulin secretion of male control and PexRAP-AKO mice fed a HFD (n = 7–9). D) Insulin tolerance test and E) area of the curve measurements of male control and PexRAP-AKO mice fed a HFD for 12 weeks (n = 7–9). F–H) Western blot analysis in iWAT (F), gWAT (G), and liver (H) of male HFD-fed control or PexRAP-AKO mice injected intraperitoneally with vehicle or insulin. Tissues were harvested 10 min after insulin injection. AKT phosphorylation was analyzed at Thr308 and Ser473. I) Serum triglyceride and J) cholesterol levels of ad-libitum fed male control or PexRAP-AKO mice following 12 weeks of HFD feeding (n = 4). K) Media glycerol levels (normalized to tissue weight) of fresh iWAT explants from HFD-fed control or PexRAP-AKO mice incubated in media containing vehicle or isoproterenol for 2 h (n = 4). L) F4/80 staining and quantification in gWAT tissue from male control and PexRAP-AKO mice fed a HFD for 16 weeks. M) qPCR analysis of gene expression of gWAT tissue from male control and PexRAP-AKO mice fed a HFD for 16 weeks. Data are shown as mean ± SEM. Comparisons between groups were made with a two-tailed unpaired Student's t-test (A,B,C,D,E,I,J,L,M) or two-way ANOVA with Bonferroni's multiple comparison test (K).\n\nFigure 3: Figure 3. PexRAP-AKO increases transcription of genes involved in de novo lipogenesis and cholesterol synthesis in iWAT.A) Volcano plot of differentially expressed genes from bulk RNA-sequencing analysis of iWAT from PexRAP and control mice. Several genes that were very significantly increased are highlighted. B) Heatmap of logCPM value-derived Z-scores. C) Gene ontology (GO) pathway enrichment analysis of genes differentially expressed (FDR ≤ 0.05) in PexRAP-AKO mice. D) Heatmap of all genes in the cholesterol biosynthetic process GO term (GO:0006695). E) Enrichment plot of GO:0008610 (lipid biosynthetic process), a top result of an unbiased GSEA analysis. F) MA plot (logFC vs. logCPM) of results of differential expression analysis of RNA-seq data from control and PexRAP-AKO mice (n = 5/group for all). G) Heatmap of key lipid synthetic genes.\n\nFigure 4: Figure 4. PexRAP inactivation induces lipogenesis through activation of LXR.A) qPCR analysis of lipogenic genes in iWAT from male control or PexRAP-AKO mice fed a HFD (60% kcal fat) for 14 weeks (n = 3–4). B) Counts per minute results of 14C-Malonyl CoA de-novo lipogenesis assay performed on iWAT from male control or PexRAP-AKO mice fed a HFD for 14 weeks (n = 3–4). C) Top results from hypergeometric motif enrichment analysis (HOMER) of genes differentially expressed (FDR ≤ 0.05) in PexRAP-AKO mice according to RNA-seq analysis (n = 5). D) Schematic of LXR reporter construct. E) Normalized luminescence and F) green fluorescence microscopy from 3T3-L1 cells stably transfected with a plasmid expressing GFP and firefly luciferase under control of a LXR response element (LXRE), differentiated to white adipocytes, and then treated with scrambled (SC) or PexRAP shRNA and GW3965 or vehicle (DMSO) (n = 6). G) qPCR analysis of lipogenic genes in 3T3-L1 cells differentiated to white adipocytes and then treated with scrambled (SC) or SREBP1 shRNA followed by SC or PexRAP shRNA (n = 5–6). H) qPCR analysis and I) Western blot analysis of 3T3-L1 cells differentiated to white adipocytes and then treated with scrambled (SC) or LXRαβ shRNA followed by SC or PexRAP shRNA (n = 4). J) Western blot analysis of 3T3-L1 cells differentiated to white adipocytes and then treated with scrambled (SC) or PexRAP shRNA. K) Western blot analysis of iWAT from male control or PexRAP-AKO mice fed a HFD for 14 weeks. L) CHOP mRNA expression in iWAT of PexRAP-AKO (N = 4) and control (N = 3) mice fed a HFD for 19 weeks. Data are shown as mean ± SEM. Comparisons between groups were made with a two-tailed unpaired Student's t-test (A,B,E, L) or two-way ANOVA with Tukey's multiple comparisons test (G,H).\n\nFigure 5: Figure 5. PexRAP deletion is associated with decreased synthesis of PE plasmalogens and increased PC/PE ratio. Targeted ESI-MS analysis of PC and PE species from the nuclear fraction of iWAT from HFD fed male control and PexRAP-AKO mice, expressed as A) logFC values (PexRAP-AKO versus Control) and B) absolute concentrations. C) Shotgun ESI-MS analysis of PC and PE species from the nuclear fraction and D) post-nuclear membrane fraction of 3T3-L1 cells differentiated to white adipocytes and then treated with scrambled (SC) or PexRAP shRNA (species with adjusted p-value less than or equal to 0.01 are shown). E) PC/PE ratios based on lipid changes in C and D (n = 4). F) Schematic showing ways in which 13Carbon may be incorporated to phospholipids from glucose. G) Volcano plot of isotope incorporation in control cells versus PexRAP-KD cells from an ESI-MS-based 13Carbon-flux analysis of 3T3-L1 cells differentiated to white adipocytes, treated with scrambled (SC) or PexRAP shRNA, and then maintained in [U13C6]-glucose containing media for 5 days (n = 4, species with adjusted p-value less than or equal to 0.05 are shown). Data are shown as mean ± SEM (B, E). Comparisons between groups were made with a two-tailed unpaired Student's t-test adjusted for multiple comparisons using the Benjamini–Hochberg method (A,C,D,G) or a two-tailed unpaired Student's t-test (B, E)."
      }
    ]
  },
  {
    "id": "PMC10950804_multi_2",
    "image": [
      "images/PMC10950804-f6.png",
      "images/PMC10950804-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Adipose tissue peroxisomal lipid synthesis orchestrates obesity and insulin resistance through LXR-dependent lipogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. PexRAP depletion is associated with cholesterol mislocalization to the nucleus and LXR activation in an alkyl glycerol-dependent manner.A) Schematic depicting timeline of alkyl glycerol (AG) rescue in PexRAP-KD or control 3T3-L1 adipocytes. B) Fluorescence microscopy of cholesterol (Filipin III, blue) and nuclei (Nuclear-ID, red) in differentiated 3T3-L1 adipocytes. Nuclear localization of cholesterol is indicated by white arrows. Quantification of mean fluorescence of nuclear Filipin III staining is shown on the right (n = 4). C) GC–MS quantification of total cholesterol in nuclear and postnuclear membrane fractions of iWAT tissue from HFD-fed control or PexRAP-AKO mice (n = 4–5). D) Normalized luminescence of 3T3-L1 cells stably transfected with a plasmid expressing GFP and firefly luciferase under control of a LXR response element (LXRE), differentiated to white adipocytes, treated with scrambled (SC) or PexRAP shRNA and finally treated with AG (n = 24). Data are shown as mean ± SEM. Comparisons between groups were made with a two-tailed unpaired Student's t-test (B,C,D).\n\nFigure 7: Figure 7. Proposed mechanism by which adipose-specific PexRAP deletion increases diet-induced obesity and insulin resistance. Loss of PexRAP decreases the amount of phosphatidylethanolamine (PE) plasmalogens present in cellular membranes. The absence of these key membrane lipids leads to release of membrane cholesterol, which is sensed by the sterol-regulated transcription factor Liver X receptor (LXR). LXR dimerizes with RXR to drive a transcriptional program characterized by increased expression of lysophosphatidylcholine acyltransferase 3 (Lpcat3), which remodels the PE-plasmalogen deficient membranes, and de novo lipogenesis genes. Aberrant activation of lipogenic genes in adipose tissue drives diet-induced obesity, hyperlipidemia and insulin resistance. Created with BioRender."
      }
    ]
  },
  {
    "id": "PMC10994533_multi",
    "image": [
      "images/PMC10994533-f1.png",
      "images/PMC10994533-f2.png",
      "images/PMC10994533-f3.png",
      "images/PMC10994533-f4.png",
      "images/PMC10994533-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Bi-allelic ACBD6 variants lead to a neurodevelopmental syndrome with progressive and complex movement disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Family pedigrees, schematic variants’ representation, conserved regions of substitution variants in ACBD6, and splicing effects. (A) Pedigrees and segregation results for the 28 unrelated families. Double lines between individuals represent consanguinity. The 45 affected individuals recruited for the study are shaded and indicated with their respective subject (S) number (S1, S2 or S3). The segregation data for all individuals tested via Sanger sequencing are shown with the presence of the ACBD6 variant (red) and/or the reference allele (black), two red/black texts indicate a homozygous state and one red + one black text indicates a heterozygous state. The genotyping is based on the coding DNA sequence. DEL = deletion; DUP = duplication; WT = wild-type. (B) Top: Schematic representation of the gene and protein positions of detected variants in ACBD6. ACBD6 is located on chromosome 1 at cytogenetic position q25.2q25.3. Middle: The genetic variants mapped to the NM_032360.4 transcript of ACBD6. Bottom: ACBD6 variants mapped on the protein level. Three variants, including p.(Gly22fs), p.(Leu121ThrfsTer27) and a 30 kb deletion in the C-terminus, have been reported previously.6,7,10 Recurrent variants are labelled with family codes. (C) Splicing schematic for the c.574-2A>G (top) variant in ACBD6 showing cryptic acceptor splice site activation in exon 6. The c.664-2A>G (middle) and c.694+1G>A (bottom) variants affect splicing of exon 7 both show exon skipping. Additionally, the c.694+1G>A variant activates a cryptic donor splice site. (D) Interspecies alignment performed with Clustal Omega showing the complete conservation down to invertebrates of the amino acid residues affected by a missense variant leading to an amino acid substitution p.(Asp201Gly) and an in-frame duplication p.(Asn219dup).\n\nFigure 2: Figure 2. Clinical features of the affected individuals with bi-allelic ACBD6 variants. [A(i–xiii)] Representative photographs demonstrating facial features of the affected individuals in adulthood: F1:S1 (i); F1:S2 (ii); F1:S3 (iii); F3:S2 (iv); F3:S1 (v); F6:S1 (vi); F7:S2 (vii); F7:S1 (viii); F11:S1 (ix); F17:S1 (x); F17:S2 (xi); F20:S1 (xii); and F16:S1 (xiii). [A(xiv–xxxi)] Representative photographs demonstrating facial features of the affected individuals in childhood: F3:S2 (xiv) at 5 years old; F3:S1 (xv) at 12 years old; F6:S2 (xvi); F8:S1 (xvii); F8:S2 (xviii); F10:S1 (xix); F10:S2 (xx); and F11:S1 (xxi) at younger age; F13:S1 (xxii); F14:S1 (xxiii); F15:S1 (xxiv); F16:S1 (xxv) at 2 years old; F16:S1(xxvi) at 4 years old; F19:S1 (xxvii); F19:S2 (xxviii); F20:S2 (xxix); F12:S1 (xxx); and F12:S2 (xxxi). The most frequently seen facial dysmorphologies in adults are high nasal ridge, full nasal tip, small mouth, thin upper lip and broad chin. The most frequently seen facial dysmorphologies in children are bifrontal/bitemporal narrowing, arched eyebrows, hypertelorism, up-slanting palpebral fissures, depressed nasal bridge, full nasal tip, thin upper lip, full lower lip and broad chin. [B(i–ix)] Representative photographs demonstrating postural abnormalities seen in the affected individuals. A stooped body posture and lateral flexion of the trunk can be seen in the individuals F1:S1 (i), F1:S2 (ii), F1:S3 (iii), F3:S1 (iv), F3:S2 (v), F6:S1 (vi), F6:S2 (vii), F8:S2 (viii) and F13:S1 (ix). (C) Bar graph summarizing proportions of various clinical findings in the ACBD6 cohort. Blue = affected; orange = unaffected; grey = not ascertained/not applicable. GDD = global developmental delay; ID = intellectual disability. [D(i–xii)] Representative neuroimaging features of the affected individuals. Brain MRI, midline sagittal images of the affected individuals F1:S1 (i), F1:S2 (ii), F5:S1(iii), F56:S2 (iv), F7:S1 (v), F7:S2 (vi), F10:S1 (vii), F10:S2 (viii), F11:S1 (ix), F13:S1 (x), F14:S1 (xi) and F19:S1 (xii). Most of the affected individuals have corpus callosum agenesis or hypoplasia with prevalent involvement of the posterior sections (empty arrows), variably associated with short midbrain (thin arrows) and small inferior cerebellar vermis (arrowheads). In addition, mild hypertrophy of the clava was noted in some subjects (dotted arrows). Note that the anterior commissure was markedly hypoplastic or absent in all affected individuals.\n\nFigure 3: Figure 3. CRISPR/Cas9 mutation of zebrafish acbd6 causes smaller eyes, impaired vision, abnormal locomotion, developmental delay and increased mortality. (A) Whole-mount in situ hybridization for detecting acbd6 mRNA expression pattern in zebrafish embryo at 24 hours post-fertilization (hpf). fb = forebrain; mb = midbrain; MHB = midbrain and hindbrain boundary; hb = hindbrain; ov = otic vesicle. Dorsal view to the top, anterior to the left. (B) Representative images of wild-type (acbd6+/+), heterozygous (acbd6+/−) and homozygous (acbd6−/−) mutant larva at 6 days post-fertilization (dpf). Head size and eye size are indicated by blue and red lines, respectively. Anterior to the left and dorsal to the top. Scale bar = 200 μm. (C and D) Quantification of eye and head size as indicated in B. +/+ (n = 26 larvae), +/− (n = 114 larvae) and −/− (n = 47 larvae). Each symbol represents one larva. Values are calculated as a percentage of the mean value of +/+ larvae. Error bars = mean ± standard deviation (SD). (E) The result of visual startle response analysis performed on +/+ (n = 43 larvae), +/− (n = 99 larvae) and −/− (n = 48 larvae) zebrafish larvae at 6 dpf. Each symbol represents one larva. The number of responses for five stimuli of each larva is calculated as a percentage of responses. Error bars = mean ± standard error of the mean (SEM). (F) Locomotor activities of zebrafish larvae in light and dark periods at 6 dpf. +/+ (n = 42 larvae), +/− (n = 99 larvae) and −/− (n = 48 larvae) zebrafish larvae were habituated in the dark for 30 min, followed by three cycles of 10-min time bins of light and dark periods. Black arrows indicate the increased movement of homozygous mutants at the first minute in the dark. Error bars = mean ± SEM. D = dark period; L = light period. (G) Average cumulative distance travelled by each larva from three cycles of either light or dark periods in F. Error bars = mean ± SD. (H) Average cumulative distance travelled by each larva during the first minute of the dark period across three cycles as indicated by black arrows in F. Error bars = mean ± SD. (I) Locomotor activities of zebrafish larvae in light and dark conditions at 12 dpf. +/+ (n = 39 larvae), +/− (n = 71 larvae) and −/− (n = 29 larvae). Error bars = mean ± SEM. Red arrow indicates increased movement of homozygous mutants at the first minute after light on. Red arrowhead indicates increased movement of homozygous mutants at the second minute after light on. (J) Average cumulative distance travelled by each larva during three cycles of either light or dark periods in I. Error bars = mean ± SD. (K) Average cumulative distance travelled by each larva during the first cycle of the first minute of the light period as indicated by red arrow in I. Error bars = mean ± SD. (L) Genotyping results of zebrafish at 6 dpf (n = 191 larvae), 12 dpf (n = 196 larvae) and 30 dpf (n = 118 juveniles) stages from acbd6+/− intercross. (M) Representative images of morphological phenotype from acbd6+/+, acbd6+/− and acbd6−/− at 30 dpf. Anterior to the left and dorsal to the top. (N) Sagittal section of acbd6+/+ brain at 30 dpf. Anterior to the left and dorsal to the top. MO = medulla oblongata; Ob = olfactory bulb; PGZ = periventricular grey zone of optic tectum. (O–W) Representative images of transverse sections of telencephalon (O–Q), optic tectum (R–T) and cerebellum (U–W) from acbd6+/+, acbd6+/− and acbd6−/− juvenile as indicated in N. In C and D, one-way ANOVA with Tukey’s multiple comparisons test; in E, G, H, J and K, one-way ANOVA with Dunnett’s T3 multiple comparisons test; ns, not significant; *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001.\n\nFigure 4: Figure 4. Zebrafish acbd6 F0 knockouts exhibit increased susceptibility to chemical-induced seizures, excessive motor neuron branching and skeletal muscle degeneration. (A) Representative images of uninjected control and acbd6 F0 larvae at 6 days post-fertilization (dpf). Left: Ventral view, anterior to the left. Right: Dorsal view, anterior to the left. Blue line indicates head size; magenta line indicates eye size; and cyan line indicates eye distance. Scale bar = 0.2 mm. (B and C) Quantification of the head and eye size (n = 30 larvae for each group) of uninjected control (uninj.), acbd6 F0 knockout (F0), F0 + zebrafish wild-type acbd6 mRNA (+acbd6) and F0 + human wild-type ACBD6 mRNA (+ACBD6) as indicated in B. (D) The visual startle response (VSR) analysis after mRNA rescue at 6 dpf. n = 36 larvae for each group. Each symbol represents one larva. The number of responses to five stimuli of each larva was calculated as a percentage of responses. Error bars = mean ± standard error of the mean (SEM). (E) Quantification of the eyes distance (n = 20 larvae for each group) as indicated in B. (F) Quantification of the eye size of F0 knockout rescued with mRNA of human p.Glu63Ter (+E63*) or p.Asp201Gly (+D201G) variant. n = 25 larvae for each group. (G) Locomotor activities of zebrafish larvae in light and dark conditions at 6 dpf. n = 64 larvae for each group. The larvae were habituated in the dark for 30 min, followed by three cycles of 10-min periods of light and dark. Error bars represent the mean ± SEM. D = dark period; L = light period. Red arrows indicate increased movement of F0 1 min after light on, and black arrows indicate increased movement 1 min after light off. (H) Average cumulative distance travelled by each larva during three cycles of either light or dark periods in G. Error bars = mean ± standard deviation (SD). (I) The average cumulative distance traveled by each larva during the first minute of the dark period was measured over three cycles, as shown by the black arrow in G. Error bars represent the mean ± SD. (J) The average cumulative distance traveled by the larvae was measured for each group after being treated with different doses of pentylenetetrazole (PTZ) at 5 dpf. n = 16 larvae for each group. (K–N) Confocal images of Tg(mnx1:GFP; olig2:DsRed) larva at 12 dpf are shown, with transgenic larvae injected with slc45a2 sgRNA used as a control and those injected with acbd6 + slc45a2 sgRNAs shown as acbd6 F0. (L' and N') Enlarged images from white boxes are shown in L' and N', with red asterisks indicating autofluorescence from remaining pigment cells. GFP and DsRed are displayed in cyan and magenta, respectively, with magenta arrowheads indicating excess axonal arborizations. The images are presented in a lateral view, with anterior to the left and dorsal to the top. Additional motor neuron phenotypes at 6 and 12 dpf can be found in Supplementary Fig. 13. (O–T) Confocal images of stained skeletal muscle fibers with phalloidin are presented, including images from slc45a2 sgRNA-injected control (O–Q) and acbd6 + slc45a2 sgRNA-injected (R and S) larvae at 12 dpf. Orthogonal views generated from P and S using the Orthogonal views tool in ImageJ are also displayed. #Degenerated muscles. White arrowheads and a white arrow indicate Z-discs and the thickness of the myotube, respectively. Supplementary Fig. 14 provides additional muscle phenotypes at 6 and 12 dpf. In B–D and F, one-way ANOVA with Tukey’s multiple comparisons test; E and H–J, one-way ANOVA with Dunnett’s T3 multiple comparisons test; ns, not significant; *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001.\n\nFigure 5: Figure 5. Xenopus tropicalis (acbd6) crispants have gastrulation, movement, craniofacial, brain and eye defects together with microcephaly. (A) The gene structure of human (ACBD6) and X. tropicalis (acbd6) reveals eight exons. (B) Gastrulation defects, including failure of blastopore closure and anterior posterior defects, were observed in F0X. tropicalis embryos injected with two different CRISPR/Cas9 constructs (sgRNA-68 and sgRNA-71) disrupting exon 1 of acbd6. (C) Those animals surviving to free-feeding stages presented with microcephaly, craniofacial dysmorphism and eye abnormalities. (D) The differences in head size between the uninjected control (2.07 ± 0.36 mm) and acbd6 crispant tadpoles (1.52 ± 0.27 mm, sgRNA-68) were found to be significant, t(34) = 5.183, P < 0.001. (E and F) Alcian blue staining marking the cartilaginous structures in the head and neck show equivalent structures between control (E) and acbd6 crispant tadpoles (F), revealing no gross morphological abnormalities. (G) Detailed structural analysis in higher resolution microCT imaging (1% phosphotungstic acid contrast stain) revealed significant structural abnormalities in the facial musculature (red arrows; G), abnormalities of the eye (microphthalmia, anophthalmia; yellow arrows, G) and structural abnormalities in the brain most pronounced in the midbrain regions (blue arrow, G). (H) Locomotion analysis at NF44/45 revealed that crispants moved significantly less than control tadpoles. (I) The Kaplan–Meier survival analysis of 65 control and crispant tadpoles shows two periods of crispant-specific decline, the first at gastrula stages (Day 0–1) and the second with post-feeding [Day 8, Nieuwkoop and Faber (NF) stage 47]."
      }
    ]
  },
  {
    "id": "PMC10994533_multi_2",
    "image": [
      "images/PMC10994533-f6.png",
      "images/PMC10994533-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Bi-allelic ACBD6 variants lead to a neurodevelopmental syndrome with progressive and complex movement disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Morphological characteristics of peroxisomes in ACBD6-deficient patient cells are not altered and chemical proteomic profiling of N-myristoylation in human fibroblasts. (A) Patient fibroblasts and controls were processed for immunofluorescence microscopy using antibodies against the peroxisomal membrane marker PEX14, the matrix marker catalase or mitochondrial ATP synthetase B (ATPB). Peroxisomal localization of PEX14 and catalase indicate that peroxisomal membrane and PTS1-dependent matrix import are normal. Note that the morphology of mitochondria, which are elongated in fibroblasts, was also not altered when compared to controls. (B) Quantification of peroxisome number based on immunofluorescence images (see A for representative images) (n = 29–36 cells). Data are from three independent experiments. ns, not significant; Kruskal–Wallis ANOVA test with Dunn’s multiple comparisons. (C) COS-7 cells were transfected with plasmids encoding Myc-ACBD5 or Myc-ACBD6 and processed for immunofluorescence microscopy using antibodies against Myc and PEX14. Note that Myc-ACBD5 localizes to peroxisomes, whereas Myc-ACBD6 localizes to the nucleus and the cytoplasm in COS-7 cells. Scale bars = 10 µm. (D) Ranked plot of myristic acid alkyne (YnMyr)-labelled, known co- and post-translationally N-myristoylated proteins, as identified in Supplementary Fig. 18E. Position on the left equals lower abundance in ACBD6 deficient fibroblasts, position on the right equals higher abundance in ACBD6 deficient fibroblasts.\n\nFigure 7: Figure 7. Chemical and whole proteome analysis of acbd6 wild-type and crispant zebrafish and Xenopus tropicalis model systems. (A) Volcano plot comparing myristic acid alkyne (YnMyr) labelling of proteins in wild-type and acbd6 crispant zebrafish at 72 h post-fertilization (hpf). (B) Comparing YnMyr labelling of proteins in wild-type and acbd6 crispant zebrafish at 120 hpf. Further description as in A. (C) Top 20 biological processes most significantly enriched in proteins downregulated in acbd6 crispant zebrafish at 72 hpf. (D) Volcano plot comparing YnMyr labelling of proteins in wild-type and acbd6 crispant 68 X. tropicalis. (E) Comparing YnMyr labelling of proteins in wild-type and acbd6 crispant 71 X. tropicalis. Further description as in D. (F) Top 20 biological processes most significantly enriched in proteins upregulated in acbd6 crispant 68 X. tropicalis. Most significantly enriched processes are at the top. In A and D, position on the left equals reduced in crispant; position on the right equals increased in crispant. Horizontal dotted line indicates significance threshold (P = 0.05). FC = fold-change. In C and F, the most significantly enriched process is at the top. Colour indicates Q-value as secondary significance indicator. Size of circle indicates a number of proteins enriched in the depicted process. Dr = Danio rerio; Hs = Homo sapiens; Xt = X. tropicalis."
      }
    ]
  },
  {
    "id": "PMC11024634_multi",
    "image": [
      "images/PMC11024634-f1.png",
      "images/PMC11024634-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Malformations of cortical development: Fetal imaging and genetics\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Study profile: +, pathogenic finding, −, normal result; N, number; TOP, termination of pregnancy.\n\nFigure 2: Figure 2. Case no. 3: Hemimegalencephaly (HME). (A) MRI image of the brain, the arrow indicates the HME‐affected hemisphere. (B) Ultrasound image of the fetal head, the arrow indicates the hyperplasia cavum septum pellucidum. (C) Brain autopsy: gross morphology of the brain. (D) Histological examination: (a) HME‐affected hemisphere; (b) non‐HME‐affected hemisphere (Hematoxylin and eosin staining). (E) Whole‐exome sequencing results: mTOR p.Ser2215Phe. (a) father; (b) mother; (c) HME‐affected brain tissue; (d) non‐HME‐affected brain tissue."
      }
    ]
  },
  {
    "id": "PMC11045382_multi",
    "image": [
      "images/PMC11045382-f1.png",
      "images/PMC11045382-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Adrenomyeloneuropathy with Later Development of Cerebral Form Caused by a Hemizygous Splice-site Variant in ABCD1\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A: Family tree of the patient. Open symbols indicate unaffected individuals, whereas the filled symbol with an arrow indicates the proband. The circle with a dot indicates an obligate carrier. III-5 was the proband, and III-2 was also genetically tested and found to be a carrier. B: Magnetic resonance imaging showed fluid attenuated inversion recovery (FLAIR) high-intensity areas in the posterior part of the corpus callosum (yellow arrowhead), left-dominant corticospinal tracts (yellow arrows), and from the bilateral superior cerebellar peduncles (green arrowheads) and right middle cerebellar peduncle to the right cerebellar white matter (green arrow). C: A direct nucleotide sequence analysis revealed the hemizygous variant c.1489-1G>A (NM_000033.4) in the ABCD1 gene. The base shown in red is the variant in this patient.\n\nFigure 2: Figure 2. A: Schematic description of aberrant splicing in this patient. The upper part shows the normal splicing of controls. The lower part shows the mechanism of aberrant splicing in this patient. The variant of this patient (c.1489-1G>A) triggered the activation of the cryptic acceptor site in exon 6 (31st base from the start of exon 6). A direct nucleotide sequence analysis of the RT-PCR products of ABCD1 cDNA showed a deletion of the first 31 bp of exon 6, leading to the alteration of the coding sequence of ABCD1 and resulting in a premature stop codon in the middle of exon 7 (p.Val497Alafs*51). B: The results of a quantitative analysis using lymphoblastoid cell lines by droplet digital PCR using TATA binding protein (TBP) mRNA as a reference. Those results show a lower ABCD1/TBP mRNA expression ratio in the patient than in controls (n=3). This bar graph shows the expression ratio of ABCD1/TBP of the patient and the average expression±standard deviation (SD) of controls. The expression ratio of each subject is the average of two wells. C: The results of agarose gel electrophoresis of the RT-PCR amplification products of the region spanning from the exon 1/2 boundary to the exon 9/10 boundary of ABCD1. A single band is observed for the X-ALD patient (lane 2) as well as for the controls (lanes 3-5). The intensity of the band of the patient is substantially weaker than that of the controls. The bottom illustration shows the normal splicing of the control."
      }
    ]
  },
  {
    "id": "PMC11084724_multi",
    "image": [
      "images/PMC11084724-f1.png",
      "images/PMC11084724-f2.png",
      "images/PMC11084724-f3.png",
      "images/PMC11084724-f4.png",
      "images/PMC11084724-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"D-Bifunctional Protein Deficiency Diagnosis—A Challenge in Low Resource Settings: Case Report and Review of the Literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Magnetic resonance imaging: 1. enlarged ventricles; 2. bilateral temporal subarachnoid cyst, mega cisterna magna; 3. delayed partial myelination of the posterior limb of the internal capsule; 4. bilateral perisylvian polymicrogyria; 5. cerebellar atrophy (central lobule, culmen), dysgenesis of the corpus callosum.\n\nFigure 2: Figure 2. Clinical course, investigations, and follow-up of the proband. Legend: m—months; d.—days; R—outpatient re-evaluation; DOL—day of life; HUS—head ultrasonography; US—ultrasonography; MLPA—multiplex ligation-dependent probe amplification; SMA—spinal muscular atrophy; MRI—magnetic resonance imaging; WES—whole exome sequencing; CT—computer tomography.\n\nFigure 3: Figure 3. D-bifunctional protein peroxisomal enzymatic activity. Very-long-chain fatty acids (VLCFAs), pristanic acid (PRIS), dihydroxycholestanoic acid (DHCA), and trihydroxycholestanoic (THCA) are activated by free unesterified coenzyme A (CoA); acyl-CoA oxidase 1 (palmitoyl-CoA-oxidase) (ACOX1), and acyl-CoA oxidase 2 (branched-chain acyl-CoA oxidase) (ACOX2) are involved in the first step of peroxisomal β-oxidation, while D-bifunctional protein (D-BP) is involved in the next two steps—hydratation and dehydrogenation; straight-chain 3 oxoacyl-CoA thiolase (Th1) and sterol carrier protein-2/3-oxoacylCoA thiolase (sterol carrier protein X) (Th2) are involved in thiolysis [36,37].\n\nFigure 4: Figure 4. D-bifunctional protein domains, HSD17B4 gene schematic structure, and classification of D-BP deficiency; red—location of the described patient defect. Legend: SCP-2 like—steroid carrier protein-2 like.\n\nFigure 5: Figure 5. Diagnostic approach pathways in D-bifunctional protein deficit (D-BPD) during neonatal period. Legend: 1—hypotonia is present at birth in 98% of cases; 2—seizures occur at birth in 93% of cases and are refractory to anticonvulsants; 3—suggestive facial dysmorphism includes high forehead, hypertelorism, epicanthus, upslanted palpebral fissure, long philtrum, depressed nasal bridge, high arched palate, large fontanelle, retrognatism, macrocephaly, and low-set ears (most aspects are similar to Zellweger syndrome); 4—in severe forms of D-BPD, infants do not acquire any developmental skills; in mild forms, with some residual protein activity, infants may reach very early developmental milestones but gradual developmental regression is noted within a few months, and hyperreflexia and hypertonia develop with D-BPD progression; 5—routine biochemical tests, blood gases analysis, neonatal imaging (X-rays, ultrasound brain, heart, and abdomen), amplitude and conventional integrate electroencephalography, auditory and visual tests, DNA analysis that may exclude perinatal hypoxic–ischemic encephalopathy, neonatal sepsis and meningitis, chronic infections (TORCH syndrome), congenital brain abnormalities, and congenital neurological or muscular diseases; 6—D-BPD cases were reported in association with abnormal prenatal development (fetal ascites, polyhydramnios), other metabolic or homeostasis abnormalities (such as increased transaminases), digestive tract abnormalities (bile duct proliferation, cholestasis, hepatomegaly, hepatic steatosis, feeding difficulties), endocrine problems (primary adrenal insufficiency), renal cysts, splenomegaly, ocular abnormalities (nistagmus, strabismus, visual loss), osseous and muscular abnormalities (frontal bossing, dolichocephaly, clubfoot, hammertoe, split hand, clacific stippling, delayed skeletal maturation, osteopenia, decrease muscle mass), hearing impairments, central nervous system abnormalities (cerebral dysmyelination or hypoplasia, gliosis, cortical dysplasia, cerebellar atrophy, callosal hypoplasia or atrophy, ventriculomegaly), and failure to thrive; 7—consanguineous parents or siblings with neurodevelopmental delay (alive or dead) are suggestive of rare hereditary conditions; *—biochemical markers may be normal during neonatal period; 8—VLCFA—very-long-chain fatty acid levels are increased; 9—phytanic acid and pristanic acid (the final product of phytanic acid α-oxidation) are increased secondary to impaired peroxisomal β-oxidation due to D-BPD; 10—dihydroxycholestanoic acid (DHCA); 11—trihydroxycholestanoic acid (THCA); DHCA and THCA plasmatic levels are increased due to D-BPD; 12—normal plasmalogen levels in red blood cells excludes generalized peroxisomal disorders; 13—genetic testing may help exclude epileptic syndromes with neonatal/infantile onset; 14—cultures’ skin fibroblasts help in diagnosis in infants with normal biochemical markers during neonatal period and differential diagnosis from Zellweger syndrome, and allow for quantification of the enzyme activity, which is of further help in predicting D-BPD course; 15—magnetic resonance imaging may show congenital brain defects (see above; Legend 6), abnormal/delayed myelination, white substance demyelination, neuronal migration disorders, focal heterotopia, and germinolytic cysts; MRI may show normal aspects during the neonatal period, followed, in time, by a suggestive model of cerebral and cerebellar leukoencephalopathy; 16—WES—whole-exome sequencing; 17—WGS—whole-genome sequencing; 18—HSD17B4 gene—17β-hydroxystroid dehydrogenase type 4 sequencing identifies the defect and its location and helps in predicting the patient’s outcome [2,3,4,5,6,7,8,9,10,12,15,16,18,19,20,28,34]."
      }
    ]
  },
  {
    "id": "PMC11109271_multi",
    "image": [
      "images/PMC11109271-f1.png",
      "images/PMC11109271-f2.png",
      "images/PMC11109271-f3.png",
      "images/PMC11109271-f4.png",
      "images/PMC11109271-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Fluorescent fatty acid conjugates for live cell imaging of peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Confocal microscopy of live HEK293T cells stained with BODIPY-C12 (1 μg/ml, cyan) and BODIPY (1 μg/ml, magenta) for 10 min. Nuclei were stained with Hoechst (10 μg/ml). A representative intensity profile is shown, Pearson Correlation Coefficient (PCC) = 0.12, scale bars − 5 and 1 μm. LD – lipid droplet, FI – fluorescence intensity. b Confocal microscopy of live HEK293T cells expressing GFP-SKL(magenta), stained with BODIPY-C12 (1 μg/ml, cyan) for 10 min. Nuclei were stained with Hoechst (10 μg/ml). A representative intensity profile is shown, PCC = 0.86, scale bars − 10 and 1 μm. c Confocal microscopy of live CRISPR/Cas9 PEX19 KO and WT HEK293T cells during BODIPY-C12 (1 μg/ml) staining, scale bar − 5 μm. Nuclei were stained with Hoechst (10 μg/ml). Western blot shows PEX19 levels in WT and PEX19 KO cells. d Confocal microscopy of fixed CRISPR/Cas9 PEX19 KO and WT HEK293T cells stained with PMP70 antibody, scale bar − 5 μm. Nuclei were stained with Hoechst (10 μg/ml).\n\nFigure 2: Figure 2. a Confocal microscopy of live WT and PEX19 KO HEK293T cells stained with PeroxiSPY650 (1 μM), PeroxiSPY555 (1 μM), BODIPY-C12 (1 μg/ml), or BODIPY-FL-C12 (green) (1 μg/ml) for 10 min. Nuclei were stained with Hoechst (10 μg/ml), scale bar − 5μm. Probe structures are shown. b–e Confocal microscopy of live WT and PEX19 KO HEK293T cells stained with (b) PeroxiSPY650 (1 μM, cyan) and Nile Red(magenta), (c) PeroxiSPY555 (1 μM, cyan) and BODIPY(magenta), (d) BODIPY-C12 (cyan) and BODIPY (magenta) (e) BODIPY-FL-C12 (cyan) and Nile Red(magenta) (1 μg/ml) for 10 min. Nuclei were stained with Hoechst (10 μg/ml), scale bars – 1 and 5 μm. Representative fluorescence intensity profiles are shown. f, g Confocal microscopy of live WT HEK293T cells stained simultaneously with PeroxiSPY650(cyan) and BODIPY-C12(magenta) of indicated concentrations (μM) for 10 min. scale bar − 5 μm. Quantification shows the peroxisome fluorescence intensity of each dye, mean ± SEM, N = 3 replicas of an average peroxisome fluorescence intensity pooled from > 300 peroxisomes per replica.\n\nFigure 3: Figure 3. a Confocal microscopy of live WT and PEX5 KO HEK293T cells expressing GFP-SKL (magenta) and stained with BODIPY-C12 (1 μg/ml, cyan) for 10 min. Nuclei were stained with Hoechst (10 μg/ml). Representative intensity profiles are shown, PCC (WT) = 0.77, PCC (PEX5 KO) = 0.15, scale bar − 5 μm. Western blot shows PEX5 levels in WT and PEX5 KO cells. b, c Confocal microscopy of fixed WT, PEX5 KO, and complemented PEX5 KO PEX5L HEK293T cells expressing GFP-SKL, stained with PMP70 and PEX5 antibodies. Nuclei were stained with Hoechst (10 μg/ml), scale bar − 5 μm. c Quantification shows the ratio of peroxisome to cytoplasm fluorescence intensity of GFP-SKL marker, mean ± SEM, **** - p < 0.0001, N = 300 cells, Kruskal-Wallis test. d, e Confocal microscopy of live WT, PEX5 KO, and complemented PEX5 KO PEX5L HEK293T cells, stained with BODIPY-C12 (1 μM) for the indicated amounts of time, scale bar − 10 μm. Graphs show the ratio of cells with identifiable peroxisomes, mean ± SEM, N = 3 pooled from 300 cells for each time point. f–h Confocal microscopy of live WT, PEX5 KO, and complemented PEX5 KO PEX5L HEK293T cells, stained with PeroxiSPY (1 μM) for the indicated amounts of time, scale bar − 10 μm. Graphs show the ratio of cells with identifiable peroxisomes, mean ± SEM, N = 3 pooled from 300 cells for each time point.\n\nFigure 4: Figure 4. a, b Confocal microscopy of live WT and PMP70 KO HEK293T cells stained with BODIPY-C12 (0.1 μg/ml) for 10 min. Nuclei were stained with Hoechst (10 μg/ml). Representative overlayed intensity profiles for different cell lines are shown (PMP70 KO(magenta), WT (cyan), PEX19 KO (black)), scale bar – 10 and 5 μm. Western blot shows PMP70 levels in WT and PMP70 KO cells. c–e Confocal microscopy of live WT and PMP70 KO HEK293T cells stained with PeroxiSPY650 and PeroxiSPY555 (1 μM) for 10 min. Nuclei were stained with Hoechst (10 μg/ml). Representative overlayed intensity profiles for different cell lines are shown (PMP70 KO(magenta), WT (cyan), PEX19 KO (black)), scale bar – 10 μm. f, g Confocal microscopy of live WT and VAPA/VAPB KO HeLa cells stained with BODIPY-C12 (0.1 μg/ml) for 15 min, scale bar − 10 μm. Nuclei were stained with Hoechst (10 μg/ml). f Western blot shows VAPB and VAPA levels in WT and KO cells. Representative overlayed intensity profiles for different cell lines are shown (VAPA/B KO (magenta) and WT (cyan)). h Confocal microscopy of fixed WT and VAPA/VAPB KO HeLa cells stained with PMP70 antibody, scale bar − 10 μm. Nuclei were stained with Hoechst (10 μg/ml). i, j Confocal microscopy of live WT and VAPA/VAPB KO HeLa cells stained with PeroxiSPY555 and PeroxiSPY650 (1 μM) for 15 min, scale bar − 10μm. Nuclei were stained with Hoechst (10 μg/ml). Representative intensity profile from separate representative cytoplasmic regions in WT and VAPA/B KO is shown ((VAPA/B KO (magenta) and WT (cyan)). (k) Confocal microscopy of live and fixed WT HEK293T cells stained with BODIPY-C12 (1 μg/ml) for 10 min. Nuclei were stained with Hoechst (10 μg/ml), scale bar – 1 and 5 μm. Representative overlayed intensity profiles for different conditions are shown (live cells (cyan) and fixed cells (magenta)).\n\nFigure 5: Figure 5. a Western blot of PEX10 in control and proband patient-derived iPSCs. Quantification shows the ratio of PEX10 to GAPDH in control (magenta) and Proband (cyan), mean ± SEM, *** - p < 0.001, N = 3 biological repeats, two-tailed unpaired T test. b Confocal microscopy of fixed control and proband patient-derived iPSCs expressing GFP-SKL. Nuclei were stained with Hoechst (10 μg/ml), scale bar – 5μm. Quantification shows the ratio of peroxisome to the cytoplasm fluorescence intensity of GFP-SKL marker in control (cyan) and Proband (magenta), mean ± SEM, **** - p < 0.0001, N = 120 cells, two-tailed Mann-Whitney. c Confocal microscopy of live control and proband patient-derived iPSCs stained with BODIPY-C12 (0.1 μg/ml) for indicated amounts of time. Nuclei were stained with Hoechst (10 μg/ml), scale bar – 5 μm. Quantification shows the ratio of peroxisome to cytoplasm fluorescence intensity of BODIPY-C12 in control (cyan) and Proband (magenta), mean ± SEM, * - p = 0.0267, N = 3 replicas of a ratio of peroxisome to cytoplasm fluorescence intensity pooled from > 300 peroxisomes per replica, two-tailed unpaired T test. d, e Confocal microscopy of live control and proband patient-derived iPSCs expressing GFP-SKL and stained with PeroxiSPY650 (1 μM), scale bar – 1 and 10 μm. Quantification shows the ratio of peroxisome to cytoplasm fluorescence intensity of PeroxisPY650 in control (cyan) and Proband (magenta), mean ± SEM, *** - p < 0.001, N = 9 replicas pooled from 300 peroxisomes per sample per repeat. e Quantification shows the number of peroxisomes per square micron, mean ± SEM, **** - p < 0.0001, N = 100 cells, two-tailed unpaired T test. f Radioactive 3H-C22 fatty acid oxidation in control and Proband iPSCs. Quantification shows counts per minute (cpm) after 24 h of oxidation in control (cyan) and Proband (magenta), mean ± SEM, N = 6 replicas, two-tailed unpaired T test. g Confocal microscopy of fixed control, PEX3 null patient-derived fibroblasts, and patient fibroblasts complemented with PEX3-GFP. Peroxisomes were stained with PMP70 antibody, nuclei were stained with Hoechst (10 μg/ml), scale bar – 10 μm. h Confocal microscopy of live control, PEX3 null patient-derived fibroblasts, and patient fibroblasts complemented with PEX3-GFP, stained with PeroxiSPY650 (1 μM) for 15 min. Representative cumulative intensity profiles are shown. i Schematic of BODIPY-C12 (B-C12) staining of peroxisomes in WT, VAP KO, PMP70 KO, PEX5 KO, and PEX19 KO cells."
      }
    ]
  },
  {
    "id": "PMC11117611_multi",
    "image": [
      "images/PMC11117611-f1.png",
      "images/PMC11117611-f2.png",
      "images/PMC11117611-f3.png",
      "images/PMC11117611-f4.png",
      "images/PMC11117611-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"NEDD4 and NEDD4L: Ubiquitin Ligases Closely Related to Digestive Diseases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Ubiquitination process: First, E1 activates ubiquitin by attaching to the Cys residue in the tail of the ubiquitin molecule in the ATP energy supply. Then, E1 transfers the activated ubiquitin molecule to E2, which subsequently recognizes the target protein and modifies it through ubiquitination, along with a number of special E3 enzymes.\n\nFigure 2: Figure 2. The NEDD4 family has three functional structural domain parts: the N-terminal C2 structural domain for lipid membrane binding (green), the central 2-4 WW structural domains involved in interactions with substrates (blue), and the C-terminal HECT catalytic structural domain associated with E3 ubiquitin ligase activity (orange).\n\nFigure 3: Figure 3. NDDD4/NDDD4L signaling pathway in esophageal and gastric cancer.\n\nFigure 4: Figure 4. NDDD4/NDDD4L signaling pathway in colorectal cancer.\n\nFigure 5: Figure 5. NDDD4/NDDD4L signaling pathway in hepatocellular carcinoma."
      }
    ]
  },
  {
    "id": "PMC11126700_multi",
    "image": [
      "images/PMC11126700-f1.png",
      "images/PMC11126700-f2.png",
      "images/PMC11126700-f3.png",
      "images/PMC11126700-f4.png",
      "images/PMC11126700-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin-protein ligase UHRF1 promotes adipogenesis and limits fibrosis by suppressing GPNMB-mediated TGF-β signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. UHRF1 is required for 3T3-L1 adipogenesis. (A) Western blot analysis of UHRF1 protein expression in NT, UHRF1 knockout G1 (UHRF1 KO G1), UHRF1 knockout G2 (UHRF1 KO G2), shScramble, shUHRF1 C1 and shUHRF1 C2 3T3-L1 cells, with Actin as the loading control. (B, C) Graph representing the growth curve of NT, UHRF1 KO G1, UHRF1 KO G2, shScramble, shUHRF1 C1, and shUHRF1 C2 preadipocytes at different time points. (D, E) Cell count of NT, UHRF1 KO G1, UHRF1 KO G2, shScramble, shUHRF1 C1, and shUHRF1 C2 cells during adipogenic differentiation. (F) Oil Red O staining of adipocytes at day 10 post-differentiation in NT, UHRF1 KO G1, UHRF1 KO G2, shScramble, shUHRF1 C1, and shUHRF1 C2 cells visualized by light microscopy at ×20 magnification (scale bar, 200 μm). The percentage of adipocytes in each group is indicated in the image. Data are mean ± SEM of 3 independent experiments. Statistical analyses were performed using ordinary one-way ANOVA, *P < 0.05.\n\nFigure 2: Figure 2. Transcriptomics analysis of UHRF1 KO G1 (pre)adipocytes reveals DEGs and significantly altered pathways, including inhibition of adipocyte differentiation. (A) Schematic representation of transcriptomics analysis of whole RNA extracted from the following samples: UHRF1 KO G1 versus NT at preadipocyte stage (day 0) and UHRF1 KO versus NT at adipocyte stage (day 10) of 3T3-L1 cells. (B) The number of statistically significant DEGs in both datasets at the indicated cut-off P-value < 0.05 and FDR < 0.05. Upregulated and downregulated genes are highlighted in red and green, respectively. (C–H) Expression log ratio of top upregulated genes in both data sets of UHRF1 KO cells and its qPCR validation. (I, J) IPA prediction of the top 20 affected canonical pathways in both datasets, and those highlighted in red and green are the percentage of upregulated and downregulated genes in each pathway, respectively. (K) Summary graph of adipocyte dataset that shows the interaction network between the most significant predicted pathways and molecules. The orange line indicates activated entities with a positive z-score, and the blue line indicates inhibited entities with a negative z-score, respectively, and estimated edges are shown as dotted lines. Data are mean ± SEM of 3 independent experiments. Statistical analyses were performed using ordinary one-way ANOVA, *P < 0.05.\n\nFigure 3: Figure 3. Adipogenic differentiation is suppressed in UHRF1-depleted cells. (A) Western blot analysis of UHRF1 and adipocyte markers C/EBP-β, PPAR-γ, and C/EBP-α in NT and UHRF1 KO G1 at different time points during adipogenic differentiation. (B–E) Western blot quantification of UHRF1, C/EBP-β, PPAR-γ, and C/EBP-α in NT and Uhrf1 KO G1 in which relative protein level was normalized to the loading control, Actin, using ImageJ software. (F–J) Western blot analysis of UHRF1 and adipogenic markers C/EBP-β, PPAR-γ, and C/EBP-α and its quantification graph in shScramble and shUHRF1 C2 during adipogenic differentiation. Data are mean ± SEM of 3 independent experiments. Statistical analyses were performed using ordinary one-way ANOVA, *P < 0.05.\n\nFigure 4: Figure 4. GPNMB is induced and secreted in UHRF1-lacking 3T3-L1 preadipocytes. (A) Venn diagram showing 846 common upregulated genes between preadipocyte and adipocyte data sets. (B) The Expression log ratio of GPNMB in both datasets. (C, D) Relative mRNA expression of GPNMB in NT, UHRF1 KO G1, shScramble, and shUHRF1 C2 at different time-points during adipocyte differentiation by qPCR. (E, F) GPNMB protein levels in NT, UHRF1 KO G1, shScramble, and shUHRF1 C2 by Western blot analysis with Actin as the loading control. (G, H) ImageJ software-based Quantitation of GPNMB protein in Western blot results by normalizing to Actin. Fold change values were calculated relative to the D0 control. (I) Immunostaining of GPNMB in NT, UHRF1 KO G1 preadipocytes where nuclei are stained in blue (DAPI), GPNMB stained in green (FITC). Images were taken at 63 × magnification. (J) Quantification of GPNMB fluorescence intensity in NT and UHRF1 KO G1 preadipocytes immunostaining by ImageJ software. (K) ELISA detected the secreted level of GPNMB in the conditioned media of NT and UHRF1 KO G1 preadipocytes. (L, M) Western blot analysis of GPNMB and its quantification graph in the conditioned media of NT and UHRF1 KO G1 preadipocytes. Data are mean ± SEM of 3 independent experiments. Statistical analyses were performed using ordinary one-way ANOVA, *P < 0.05.\n\nFigure 5: Figure 5. TGF-β and its targets are induced in UHRF1 KO cells during differentiation. (A) Upstream regulators of common upregulated genes predicted by IPA analysis. Upregulated targets are represented in red color, and downregulated targets are shown in green color. (B) Upregulated TGF-β targets predicted in adipocyte dataset. (C, D) Western blot analysis showing TGF-β induction in NT and UHRF1 KO G1 during differentiation and its quantification graph. (E–P) qPCR analysis of MMP3, MMP13, COL1A1, COL6A3, MCP1, Fibronectin, and MITF in NT, UHRF1 KO G1 and shUHRF1 C2 cells during differentiation. Data are mean ± SEM of 3 independent experiments. Statistical analyses were performed using ordinary one-way ANOVA, *P < 0.05."
      }
    ]
  },
  {
    "id": "PMC11126700_multi_2",
    "image": [
      "images/PMC11126700-f6.png",
      "images/PMC11126700-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin-protein ligase UHRF1 promotes adipogenesis and limits fibrosis by suppressing GPNMB-mediated TGF-β signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Recombinant GPNMB induces TGF-β and suppresses adipogenesis in 3T3-L1 cells. (A–C) Western blot analysis of secreted TGF-β and MMP13 in conditioned media collected from NT, UHRF1 KO G1, GPNMB-treated NT, and GPNMB-treated UHRF1 KO G1 cells and its quantification data. (D) Oil Red O images of control and recombinant GPNMB (100 ng/ml) treated 3T3-L1 cells on day 8 post-induced 3T3-L1 cells (scale bar, 200 μm). (E, F) Western blot analysis showing induction of TGF-β in recombinant GPNMB-treated 3T3-L1 during adipocyte differentiation and its quantification graph. (G) Expression log ratio of TGF-β targets in adipocyte data set. (H) Western blot analysis of adipogenic markers such as PPAR-γ, C/EBP-α, and Adiponectin in control and GPNMB-treated 3T3-L1 cells. (I) Western blot quantification graph of PPAR-γ, C/EBP-α, and Adiponectin in control and GPNMB-treated 3T3-L1 cells. Data are mean ± SEM of 3 independent experiments. Statistical analyses were performed using ordinary one-way ANOVA, *P < 0.05.\n\nFigure 7: Figure 7. Overexpression of UHRF1 reverses the phenotype observed in UHRF1-depleted cells. (A) Representative fluorescence and brightfield microscopy images of lentivirus-mediated expression of GFP control or UHRF1-GFP in HEK293T cells (Scale bar, 100 μm). GFP-positive cells in the total cell population are shown in the merged image. (B) Representative confocal microscopy images of GFP control and UHRF1-GFP in HEK293T cells. Nuclei were stained with Hoechst (blue). Scale bar, 50 μm. (C–H) Representative western blot data and quantification of changes in the expression levels of UHRF1-GFP, TGF-β, GPNMB, MMP3 and MMP13 levels in UHRF1-GFP HEK293T cells versus GFP control. Target protein levels were normalized to Actin using ImageJ software. (I) Fluorescence and brightfield microscopy images of lentivirus-mediated expression of GFP control and UHRF1-GFP in SW872 cells (Scale bar, 100 μm). GFP-positive cells in the total cell population are shown in the merged image. (J) Representative confocal microscopy images of GFP control and UHRF1-GFP in SW872 cells. Nuclei were stained with Hoechst (blue). Scale bar, 50 μm. (K–N) Representative western blot data and quantification of changes in the expression levels of UHRF1-GFP, PPAR-γ and TGF-β in UHRF1-GFP SW872 cells versus GFP control. Target protein levels were normalized to Actin using ImageJ software. (O, P) Oil Red O staining images of oleic acid (50 µM)-induced differentiation of SW872 cells overexpressing GFP control or UHRF1-GFP on day 4 post-differentiation. Scale bar 100 μm. (P) Bar graph showing the total number of lipid droplets present in the entire 40 × field Oil Red O images of GFP control and UHRF1-GFP. Data are mean ± SEM of 3 independent experiments. Statistical analyses were performed using ordinary one-way ANOVA, *P < 0.05."
      }
    ]
  },
  {
    "id": "PMC11180138_multi",
    "image": [
      "images/PMC11180138-f1.png",
      "images/PMC11180138-f2.png",
      "images/PMC11180138-f3.png",
      "images/PMC11180138-f4.png",
      "images/PMC11180138-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"EHHADH deficiency regulates pexophagy and accelerates tubulointerstitial injury in diabetic kidney disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A Association of tubular mRNA expression of EHHADH with eGFR determined by Spearman’s R test. B Association of tubular mRNA expression of EHHADH with eGFR slope determined by Spearman’s R test. C Association of tubular mRNA expression of EHHADH with 24 h proteinuria determined by Spearman’s R test. D Immunofluorescence staining of EHHADH (red) and α-SMA (green) in human kidney samples from healthy controls and patients with DN. E Association of EHHADH with α-SMA determined by Spearman’s R test.\n\nFigure 2: Figure 2. A Weight of WT, Ehhadh KO (KO), diabetic WT (WT-STZ) and diabetic Ehhadh KO (KO-STZ) mice. B Blood glucose levels of WT, KO, WT-STZ and KO-STZ mice. C Urine albumin-to-creatinine ratio (uACR) in WT, KO, WT-STZ, and KO-STZ mice. D Urine KIM1-to-creatinine ratio in WT, KO, WT-STZ, and KO-STZ mice. E Morphological examinations of kidney histology by periodic acid-Schiff (PAS) and Sirius red staining. F Quantification of tubular injury scoring in control and diabetic mice. G Representative images of IF staining of α-SMA, Collagen I and F4/80 in kidneys from control and diabetic mice. H–J Quantification of the positive areas of α-SMA, Collagen I and F4/80 in kidneys from control and diabetic mice. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, #p < 0.05, ##p < 0.01.\n\nFigure 3: Figure 3. A NRK-52E cells were transfected with scramble siRNA (siNC) or Ehhadh-targeting siRNA (siEhhadh#1 and siEhhadh#2), and the cells were harvested and analyzed by Western blotting with the indicated antibodies after 48 h of transfection. B–D Quantification of the relative protein expression levels of EHHADH, PMP70, and PEX14. E Immunofluorescence staining of PMP70 and PEX14 in NRK-52E cells transfected with siNC or siEhhadh. F Quantification of PMP70-positive peroxisomes numbers per cell. G Quantification of PEX14-positive peroxisomes per cell. H Representative images of IF staining of EHHADH, PMP70, and PEX14 in kidneys from control and diabetic mice. I–K Quantification of the relative fluorescence intensity. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001.\n\nFigure 4: Figure 4. A NRK-52E cells were transfected with siNC or siEhhadh. The cells were treated with 3-MA (5 mM) for 6 h and then harvested at 48 h after transfection and analyzed by Western blotting with the indicated antibodies. B–D Quantification of the relative protein expression levels of PMP70 and PEX14 and the LC3B II/I ratio. E NRK-52E cells were transfected with siNC or siEhhadh. Prior to 48 h, the cells were treated with BafA1 (500 nM) for 6 h and then harvested and analyzed by Western blotting with the indicated antibodies. F–H Quantification of the relative protein expression levels of PMP70 and PEX14 and the LC3B II/I ratio. I Immunofluorescence staining of PMP70 in NRK-52E cells transfected with siNC or siEhhadh for 48 h and treated with or without 3-MA or BafA1. J Quantification of PMP70-positive peroxisome numbers per cell. K Immunoblotting analysis of kidney protein expression levels in mice treated with or without 3-MA or BafA1. L, M Quantification of the relative protein expression levels of PMP70 and PEX14. N Representative IF staining images of PEX14 and LAMP2, PMP70 and LC3B in the renal tubules of WT or KO mice treated with or without 3-MA or BafA1. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001.\n\nFigure 5: Figure 5. A NRK-52E cells were transfected with siNC or siEhhadh. After 24 h, the cells were treated with NAC (1 mM) for 24 h and then incubated with DCFH-DA. B Quantification of the relative fluorescence intensity. C NRK-52E cells were transfected with siNC or siEhhadh. After 24 h, the cells were treated with NAC (1 mM) for 24 h and then harvested and analyzed by Western blotting with the indicated antibodies. D–F Quantification of the relative protein expression levels of PMP70 and PEX14 and the LC3B II/I ratio. G Immunofluorescence staining of PMP70 and PEX14 in NRK-52E cells transfected with siNC or siEhhadh for 48 h and treated with or without NAC. H Quantification of PMP70-positive peroxisomes per cell. I Quantification of PEX14-positive peroxisomes per cell. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001 ."
      }
    ]
  },
  {
    "id": "PMC11184980_multi",
    "image": [
      "images/PMC11184980-f1.png",
      "images/PMC11184980-f2.png",
      "images/PMC11184980-f3.png",
      "images/PMC11184980-f4.png",
      "images/PMC11184980-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogen oxidation induces the generation of excited molecules and electrophilic lipid species\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Scheme depicting the oxidation of phosphatidylethanolamine plasmalogen (pPE) vinyl ether bond by singlet oxygen. pPE (p18:0/18:1) undergoes reaction with O2 (1Δg), resulting in the formation of dioxetane and hydroperoxyacetal intermediates. A) Thermal decomposition of 1,2-dioxetane generates carbonyl compounds, including one in a triplet excited state (*). These high-energy excited triplet carbonyls can transfer energy to molecular oxygen, leading to the production of O2 (1Δg). Subsequent C–C bond rupture yields a formyl PE and a fatty aldehyde. B) Decomposition of hydroperoxyacetal results in the formation of peroxyl radicals, either through H atom transfer or metal catalysis. These peroxyl radicals then react, producing O2 (1Δg), diacyl PE, LPE, and an alpha–beta unsaturated fatty aldehyde.\n\nFigure 2: Figure 2. Characterization of plasmalogen photooxidation products by LC–HRMS analysis. A) Total ion chromatograms of pPE (p18:0/18:1) photooxidized with MB for 0, 10, 20, and 30 min. B) MS1 mass spectra of pPE oxidation products detected at 4.3, 9.6, and 10.3 min. MS2 mass spectra of pPE (p18:0/18:1) (C), pPE(p18:0-OOH:18:1) (D), PE (formyl/18:1) (E), and LPE(18:1) (F). G) Reaction scheme illustrating the reduction of pPE (p18:0-OOH/18:1) with TPP, resulting in the formation of a hemiacetal. This hemiacetal undergoes cleavage, yielding a fatty aldehyde, Ald (18:1Δ2), and LPE (18:1). H) Relative concentrations of plasmalogen-oxidized products before and after TPP addition. Reaction conditions: 1 mM of pPE (p18:0/18:1) was photooxidized in the presence of 50 μM of MB at −40°C under the following conditions: (−MB) without methylene blue; (+MB) with methylene blue; and (+MB + TPP) with MB and with TPP. Data are shown as area ratio ± SEM.\n\nFigure 3: Figure 3. Determination of the relative ratio between dioxetane and hydroperoxyacetal pathways. A) Reaction scheme illustrating the oxidation of plasmalogen vinyl ether bond by O2 (1Δg). Top—the [2 + 2] cycloaddition mechanism leads to the formation of dioxetane, which undergoes subsequent cleavage to produce PE (formyl/18:1) and Ald (17:0). Bottom—The ene reaction generates hydroperoxyacetal, which is then reduced to produce LPE (18:1) and Ald (18:1Δ2). B) Quantification of PE (formyl/18:1) and pPE (p18:0-OOH/18:1). C) Quantification of fatty aldehydes, Ald (17:0) and Ald (18:1Δ2), after 30 min of irradiation. Reaction conditions were the same as in Figure 2. Data are shown as area ratio ± SEM.\n\nFigure 4: Figure 4. Characterization of long-chain fatty aldehydes by mass spectrometry. A) Scheme illustrating fatty aldehyde (Ald) derivatization with the CHH probe. MS/MS spectra of the Ald-CHH adducts detected for: Ald (17:0) commercial standard (B), Ald (17:0) generated from pPE (p18:0/18:1) photooxidation (C), and Ald (18:1 Δ2) generated from pPE (p18:0-OOH/18:1) reduction with TPP (D). E) Scheme depicting alpha–beta unsaturated fatty aldehyde derivatization with CSH and CHH probes. MS/MS spectra of the Ald–CSH–CHH adduct detected for: Ald (16:1 Δ2) commercial standard (F) and Ald (18:1 Δ2) generated from pPE (p18:0-OOH/18:1) reduction with TPP (G).\n\nFigure 5: Figure 5. Generation of excited triplet carbonyls and singlet molecular oxygen from plasmalogen dioxetane intermediate. A) Scheme illustrating the formation of dioxetane through the reaction of O2 (1Δg) with the vinyl ether bond. Dioxetane thermolysis yields carbonyl species, one of them in the excited state. These excited triplet carbonyls can emit light in the visible region or transfer energy to molecular oxygen, resulting in the generation of O2 (1Δg). Excited singlet molecular oxygen production was confirmed by light emission in the NIR region (1,270 nm) and chemical trapping of O2 (1Δg) with DPA. B) Visible-light emission resulting from dioxetane thermolysis. C) Enhancement of triplet carbonyl light emission using 10 mM of DBA. D) NIR light emission at 1,270 nm. E) Chemical trapping of O2 (1Δg) by DPA and analysis of DPAO2 by HPLC (UV 210 nm). Light emission and chemical trapping experiments were performed using 1 mM of pPE (p18:0/18:1) or PE (18:1/18:1) solutions that were photooxidized with MB at −40°C for 30 min."
      }
    ]
  },
  {
    "id": "PMC11184980_multi_2",
    "image": [
      "images/PMC11184980-f6.png",
      "images/PMC11184980-f7.png",
      "images/PMC11184980-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogen oxidation induces the generation of excited molecules and electrophilic lipid species\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Plasmalogen hydroperoxyacetal reacts with metal ions, producing alpha–beta unsaturated fatty aldehydes and LPE. A and B) Scheme depicting the reaction products for pPE hydroperoxyacetal and PE hydroperoxides. C and D) Quantification of phospholipid oxidation products by LC–HRMS. Reaction conditions: 1 mM of plasmalogen solution photooxidized with MB at −40°C for 30 min was mixed with 50 μM of CeIV or FeII in CHCl3/methanol/water (90:9:1 v/v/v) for 1 h.\n\nFigure 7: Figure 7. Characterization of alpha–beta unsaturated carbonyl group in PE (18:1Δ2/18:1). A) Extracted ion chromatogram of m/z 742.539 in photooxidized pPE (p18:0/18:1) treated with CeIV (peak at 9.8 min) and the commercial PE(18:1/18:1) standard (peak at 10.1 min). B) MS/MS spectrum of PE (18:1Δ2/18:1)-CSH adduct.\n\nFigure 8: Figure 8. Singlet molecular oxygen generation from plasmalogen hydroperoxyacetal reaction with CeIV. A) Light emission signal at 1,270 nm obtained for the reaction of 5 μM of pPE (p18:0-OOH/18:1). B) Comparison with the reaction using LAOOH. C) NIR light emission spectrum obtained in the reaction of 100 μM of pPE (p18:0-OOH/18:1) with 75 μM of CeIV. D) NIR light emission spectrum obtained during the thermolysis of 1 mM of DMNO2."
      }
    ]
  },
  {
    "id": "PMC11192191_multi",
    "image": [
      "images/PMC11192191-f1.png",
      "images/PMC11192191-f2.png",
      "images/PMC11192191-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Childhood Cerebral Adrenoleukodystrophy: Case Report and Literature Review Advocating for Newborn Screening\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MRI (Plain) of the Brain. (A–C) are T1-weighted; (D–F) are T2-weighted; (G–I) are FLAIR-weighted. (A–C) show hypointense regions and (D–I) show hyperintense regions in the periventricular white matter with multiple cystic spaces. The splenium of corpus callosum is also involved. Blue arrows mark the abnormal regions.\n\nFigure 2: Figure 2. MRI (Plain) of the Brain. (A–C) are FLAIR-weighted, T2-weighted, and T1-weighted MRI respectively. (A and B) show hyperintensity in the bilateral dentate nucleus, whereas (C) shows hypointensity in the bilateral dentate nucleus (marked by white arrows).\n\nFigure 3: Figure 3. Postcontrast study with gadolinium-enhanced MRI of the brain; (A–C) show mild focal linear enhancement on both sides with greater enhancement on the right side (marked by white arrows)."
      }
    ]
  },
  {
    "id": "PMC11218195_multi",
    "image": [
      "images/PMC11218195-f1.png",
      "images/PMC11218195-f2.png",
      "images/PMC11218195-f3.png",
      "images/PMC11218195-f4.png",
      "images/PMC11218195-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Clinical exome analysis and targeted gene repair of the c.1354dupT variant in iPSC lines from patients with PROM1-related retinopathies exhibiting diverse phenotypes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generation of patient-derived iPSC from IRD1 patient. At D0, dermal biopsy is cut into small pieces, seeded in 100-mm culture dishes, and maintained with IMDM medium. At D14, outgrowth of fibroblast is noticeable from biopsy pieces. At D28, passage 2 patient-derived fibroblast are reprogrammed using the episomal vectors through electroporation. At D38, three days after electroporation, IMDM medium is changed to mTSR-E7 medium. At D56, three weeks after electroporation, iPSC colonies have emerged between fibroblasts. iPSC colonies are picked up manually and seeded in new culture dishes using the mTeSR plus medium. At D70, passage 2 iPSC colonies displaying compact colonies with distinct borders, well-defined edges, and large nuclei. Days after electroporation*\n\nFigure 2: Figure 2. Design of a gene editing strategy for repairing the c.1354dupT (p.Tyr452 Leufs*13) mutation in the exon 13 of the PROM1 gene. A In silico representation of the target sequence in a WT case. The amino acid affected by target mutation “Tyrosine” is highlighted in a green circle B In silico representation of a patient affect by the c.1354dupT (p.Tyr452 Leufs*13). The mutation is indicated by a black arrow and represented by a lowercase “t”. The Leucine generated due the mutation’s frameshift is highlighted in a red circle, and the consequent stop codon is indicated by a black arrow. The localization of the four designed gRNAs (40RE, 47RE, 66FW and 77FW) are framed in orange C In silico representation of the target sequence in a genetically repaired case. Blue arrows indicate silent mutations that introduce a restriction site for the Ssp1 and destroy the Protospacer Adjacent Motif (PAM) sequence to prevent the edited allele from being targeted again by the gRNA. The amino acid affected by target mutation “Tyrosine” is highlighted in a green circle. The WT reading frame is recovered\n\nFigure 3: Figure 3. Phenotypic Variability of the c.1354dupT (p.Tr452 Leufs*13) Mutation in the PROM1 Gene in Three Target Patients. A Patient IRD1 is a 47-year-old female displaying a CORD phenotype. Retinography reveals pigment in bone spicules, papillary pallor, macular atrophy, and vascular attenuation. Fundus Autofluorescence (FAF) displays patchy/mottled hypoautofluorescent patterns. Optical Coherence Tomotraphy (OCT) presents panretinal outer retinal layers (ORL) disruption with foveal involvement. B Patient IRD2 is a 54-year-old female exhibiting an RP phenotype. Retinography with bone spicules pigmentation, papillary pallor, macular atrophy, and vascular attenuation. FAF showing patchy/mottled hypoautofluorescent patterns. OCT reveals panretinal ORL disruption including the fovea. C Patient IRD3, a 20-year-old male, exhibits an STGD4 phenotype. Retinography displays Bull’s eye Maculopathy. FAF shows a hypoautofluorescent ring around the fovea. OCT exhibits ORL disruption of the previously described ring with preserved fovea, mainly affecting the RPE line but with photoreceptors still present in the macular area. D The pedigree analysis reveals an autosomal recessive (AR) inheritance pattern for all three target patients. IRD1’s paternal grandfather and two paternal great-uncles are affected; additionally, a cousin of his father received an RP diagnosis. That family resides in a small village in Cantabria and exhibits relatively high consanguinity. IRD2 has two affected male brothers and a non-affected son (her husband has congenital achromatopsia, highlighted in pink). IRD3 has no reported family history of ocular disease but few members present Charcot-Marie-Tooth (CMT) disease, highlighted in pink. The parents of IRD2 are second cousins, indicating consanguinity; IRD3’s father has CMT disease due to a duplication of the PMP22 gene mutation in homozygosis, and IRD3 was heterozygous for this mutation as well, albeit asymptomatic\n\nFigure 4: Figure 4. Characterization of the generated patient-derived iPSC lines. Alkaline phosphatase (AP) reactivity analysis. A Positive AP test results for all generated iPSC lines: [CORD]-FiPSC1-Ep5F-2, [RP]-FiPSC1-Ep5F-10, [STGD4]-FiPSC1-Ep5F-8. 50 µm scale. B Pluripotency analysis. Immunoreactivity of [RP]-FiPSC1-Ep5F-10 for pluripotency markers OCT4, SSEA3, SOX2, SSEA4, TRA1-60, NANOG, and TRA-1–81. 25 µm scale. C Molecular analysis of all generated iPSC lines. Relative mRNA expression of endogenous reprogramming factors (SOX2, OCT3/4, KLF4, LMYC, LIN28) apparently higher in the patient’s iPSC lines in comparison to unstransfected fibroblast. Above, the number of copies of the EBNA1 gene evidently lower in the generated iPSC lines than in 72 h post-transfection fibroblast, electroporated in the same reprogramming conditions. D Analysis of the functional pluripotency of embryoid bodies (EB) derived from [RP]-FiPSC1-Ep5F-10. Immunoreactivity to ectoderm (β-III Tubulin), mesoderm (α-SMA) and endoderm (α-1 Fetoprotein) markers, along with phase contrast micrography of EB. 50 µm and 200 µm scale. E Identity analysis of the generated patient-derived iPSC lines. Correspondence between the patient’s fibroblast lines: [RP]-hFb, [STGD4]-hFb, [CRD]-hFb, and their respective patient-derived iPSC line for the Short Tandem Repetition (STR) loci: CSF1PO, D13S317, D16S539, D21S11, D5S818, D7S820, TH01, TPOX y vWA, and Amelogenin. F Cytogenetic integrity of the generated iPSC lines. G-banded metaphase analysis of the patient-derived iPSC lines\n\nFigure 5: Figure 5. gRNA selection and detection of gene-edited iPSC clones (A) Comparison of gene editing efficiency among different gRNAs (40RE, 47RE, 66FW, 77FW). Ssp1 digestion of PCR products obtained from gDNA of U2OS cells edited with each gRNA and its respective repair oligonucleotide. Untransfected U2OS cells served wild type (WT) control (B) Screening test for detection of genetically repaired clones. A comparison of conventional PCR products using the ALELO40RE primer between untransfected U2OS cells (WT) and U2OS cells transfected with gRNA 40RE and the corresponding repair oligonucleotide 40RE (40RE)"
      }
    ]
  },
  {
    "id": "PMC11225845_multi",
    "image": [
      "images/PMC11225845-f1.png",
      "images/PMC11225845-f2.png",
      "images/PMC11225845-f3.png",
      "images/PMC11225845-f4.png",
      "images/PMC11225845-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The presence of plasmenyl ether lipids in Capsaspora owczarzaki suggests a premetazoan origin of plasmalogen biosynthesis in animals\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Fatty acid profile of Capsaspora owczarzaki cells along its life cycle. (A) Relative percentages of each fatty acid, as methyl ester derivatives (FAME), fatty aldehyde (17:0 Ald) and its dimethyl acetal (17:0 DMA), obtained after acid transmethylation. (B) Total C20-PUFA and (C) aldehydes (17:0 Ald plus 17:0 DMA) in each stage. Green, orange and red bars: filopodial, aggregative and cystic stages, respectively. i17:0 and n17:0 indicate iso and normal heptadecanoic acid FAME. Data are expressed as mean ± SD (n = 3). *p < 0.05, **p < 0.005, ***p < 0.0005, ns: not significant (one-way ANOVA with Tukey post hoc test). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)\n\nFigure 2: Figure 2. (A) Partial gas chromatogram obtained after acid or basic transmethylation of filopodiated cells lipid extracts. (B) Mass spectra of 17:0 Ald and 17:0 DMA, detected only under acid transmethylation.\n\nFigure 3: Figure 3. Aerobic pathway for de novo plasmenyl ethanolamine biosynthesis. The IUBMB code number of each enzyme is shown. The protein code of the human enzymes (third column) and the Capsaspora owczarzaki code for the corresponding orthologs (fourth column) are also indicated. FAR: fatty acyl-CoA reductase; GNPAT: glycerone phosphate acyltransferase; AGPS: alkyl-glycerone phosphate synthase; DHRS7B: acyl/alkyl-glycerone phosphate reductase; EPT1: ethanolaminephosphotransferase; CEPT1: choline/ethanolaminephosphotransferase. a: enzymes not conclusively assigned.\n\nFigure 4: Figure 4. Phylogenetic analysis of PEDS1. Arrow indicates the proposed acquisition event of PEDS1 in Filozoa. Maximum likelihood phylogenetic reconstruction was performed with amino acid sequences from: A. castellanii (XP_004357191), A. tenebrosa (XP_031565811), A. queenslandica (XP_019858443), A. ceylanicum (EYC45081), A. carolinensis (XP_008108340), A. avenae (KAH7728392), B. taurus (NP_001093785), B. glabrata (XP_013082447), B. aeneus (CAH0557382), C. elegans (NP_493036), C. owczarzaki (XP_004348333), C. assimilis (CAH1130273), C. moneduloises (XP_031982549), D. rerio (XP_005159144), D. pulex (XP_046441868), D. rotundus (XP_024415067), D. purpureum (XP_003283098), D. santomea (XP_039483291), E. electricus (XP_026885415), F. rusticolus (XP_037259213), H. placei (VDO38720), H. sapiens (NP_954580), J. jaculus (XP_004663924), L. canadensis (XP_030165270), L. enrietii (KAG5480133), L. seymouri (KPI89550), M. mulatta (NP_001180988), M. javanica (XP_017507389), M. undulates (XP_033923137), M. scopiformis (XP_018071845), M. musculus (NP_663513), M. xanthus (WP_140865935), N. fowleri (XP_044565043), N. gruberi (XP_002676085), O. degus (XP_004636098), O. sinensis (XP_029652872), O. faveolated (XP_020624199.1), O. keta (CDQ82662), P. dominula (XP_015180136), P. chileana (Pchi_g12073), P. vietnamica (Pvie_g9176), P. violaceum (KAF2069211), R. temporaria (XP_040187100.1), S. formosus (XP_018582118), S. habroptila (XP_030358758), T. gelada (XP_025254407), Thozetella sp. (KAH8900397), T. semiorbis (KAH0527355), T. adhaerens (XP_002112059), T. lacteum (KYQ89613), T. brucei (XP_822479), T. cruzi (PWU95043), V. komodoensis (XP_044296322), V. pensylvanica (XP_043667822), X. laevis (AAI29523). Numbers represent bootstrap values. The bar represents the percentage of substitutions.\n\nFigure 5: Figure 5. Alignment of filozoan PEDS1. In red, the essential histidines of the active site. In green, the two-aminoacids insertion of filasterean organisms. Amino acid sequences were aligned using the MAFFT algorithm and visualized by Jalview. (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)"
      }
    ]
  },
  {
    "id": "PMC11226853_multi",
    "image": [
      "images/PMC11226853-f1.png",
      "images/PMC11226853-f2.png",
      "images/PMC11226853-f3.png",
      "images/PMC11226853-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Interaction between RNF4 and SART3 is associated with the risk of schizophrenia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PPC value and the mRNA levels of RNF4 and SART3. A. Comparison of PCC value of gene pairs correlated with SCZ. The plot showed highly co-expressed gene pairs in the brain (PCC≥0.8 based on the brain expressions from GTEx). B. The mRNA level of RNF4 and SART3 in first-episode SCZ cases vs age- and sex-matched controls. n = 30 per group. C. The mRNA level of RNF4 and SART3 in chronic SCZ cases vs. age- and sex-matched controls. n = 30 per group. ****P < 0.0001. STAR3: Squamous cell carcinoma antigen recognized by T cells 3. RNF4: Ring finger protein 4. LIN7A: Lin-7 Homolog A. GAS5: Growth arrest-specific 5. RPL32: Ribosomal protein L32. SCZ: Schizophrenia. PCC: Pearson correlation coefficient. GTEx: Genotype-Tissue Expression.\n\nFigure 2: Figure 2. Genetic association between RNF4 and SART3 SNPs A. Locations of SNPs in RNF4 and SART3 genes. B. Pairwise linkage disequilibrium results among SNPs in RNF4 and SART3. C. The distribution of high-risk, low-risk genotype combinations and hierarchical interaction graphs as well as interaction dendrogram in the best three locus model of RNF4(rs1203860, rs2282765) and SART3(rs2287550), OR = 1.94[1.08–3.49]. STAR3: Squamous cell carcinoma antigen recognized by T cells 3. RNF4: Ring finger protein 4. OR: odds ratio.\n\nFigure 3: Figure 3. SART3 negatively regulates RNF4 by ubiquitination A. Co-localization of SART3 and RNF4. 293T cells were transfected with mCherry-SART3 and eGFP-RNF4. Images were taken with a confocal microscope (Olympus) (scale bar:10 μm). B. The left side of the panel shows the IB analysis of lysate and IPs derived from 293T cells transfected with the GFP or GFP-RNF4 constructs. The right side of panel B shows the IB analysis of lysate and IPs derived from 293T cells transfected with GFP-RNF4 constructs. IgG was used as a negative control. C. IB analysis of lysate derived from 293T cells transfected siRNA against SART3. D. IB analysis of lysate derived from 293T cells transfected with the indicated constructs E.V. or mCherry-SART3. Where indicated, MG132 (20 μM) was treated for 8h. E. IB analysis of RNF4 ubiquitin and lysate derived from 293T cells transfected with the indicated constructs. *P < 0.05 shows an increase versus vehicle or control; #P < 0.05 shows a reduction versus vehicle or control; n.s. means no significance. STAR3: Squamous cell carcinoma antigen recognized by T cells 3. RNF4: Ring finger protein 4. DAPI: 4′,6-Diamidino-2′-phenylindole. IP: Immunoprecipitation. IB: Immunoblotting. IgG: Immunoglobulin G. GFP: Green fluorescent protein. NC: Negative control. Si-SART3: The small interference RNA targeting SART3. E.V.: Empty vector. mCherry-SART3: mCherry and SART3 expression plasmid. AU: Area units. Anti-Ub: Anti-Ubiquitin antibody.\n\nFigure 4: Figure 4. SART3 regulates the expression of NRF2 (A) IB analysis of lysate and IPs derived from 293T cells. IgG was used as a negative control. (B) IB analysis of lysate derived from 293T cells with transfected the indicated constructs. E.V. or mCherry-SART3. (C) IB analysis of lysate derived from 293T cells with transfected siRNA against SART3. (D) The mRNA expression level of NRF2 in first-episode SCZ cases vs age- and sex-matched controls (n = 30). *P < 0.05 shows an increase versus vehicle or control; #P < 0.05 shows a reduction versus vehicle or control; ****P < 0.0001. STAR3: Squamous cell carcinoma antigen recognized by T cells 3. Nrf2: Nuclear factor E2-related factor 2. IP: Immunoprecipitation. IB: Immunoblotting. IgG: Immunoglobulin G. Si-NC: The small interference RNA negative control. Si-SART3: The small interference RNA targeting SART3. mCherry-SART3: mCherry and SART3 expression plasmid. AU: Area units. SCZ: Schizophrenia."
      }
    ]
  },
  {
    "id": "PMC11230659_multi",
    "image": [
      "images/PMC11230659-f1.png",
      "images/PMC11230659-f2.png",
      "images/PMC11230659-f3.png",
      "images/PMC11230659-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Experiences of patients with metachromatic leukodystrophy, adrenoleukodystrophy, or Krabbe disease and the experiences of their family members: a qualitative systematic review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Search results and study selection and inclusion process.25\n\nFigure 2: Figure 2. Synthesized finding 1: Providing care by family members and health care providers as physical symptoms progress\n\nFigure 3: Figure 3. Synthesized finding 2: Building medical teamwork to provide appropriate support services\n\nFigure 4: Figure 4. Synthesized finding 3: Coordinating family functions to accept and cope with the disease"
      }
    ]
  },
  {
    "id": "PMC11246155_multi",
    "image": [
      "images/PMC11246155-f1.png",
      "images/PMC11246155-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Exploiting fly models to investigate rare human neurological disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Localization of the proteins that are associated with rare neurologic disorders in the cell (schematic drawing). Adapted from “Structural Overview of an Animal Cell,” by BioRender.com (2024). Retrieved from https://app.biorender.com/biorender-templates. ACOX1: Acyl-CoA oxidase 1; CDK19: cyclin-dependent kinase 19; DNMBP: dynamin binding protein; EMC1: ER membrane protein complex subunit 1; INTS11: integrator complex subunit 11; IQSEC1: IQ motif and Sec7 domain ArfGEF 1; IRF2BPL: interferon regulatory factor 2 binding protein like; SUPT16H: SPT16 homolog, facilitates chromatin remodeling subunit; TIAM1: TIAM Rac1-associated GEF 1; TNPO2: transportin 2.\n\nFigure 2: Figure 2. Pathogenicity of variants in neurons and glia. Each gene is expressed in different tissues and cells, and variants can be pathogenic in neurons or in glia. Created with BioRender.com. ACOX1: Acyl-CoA oxidase 1; CDK19: cyclin-dependent kinase 19; DD: Developmental delay; GoF: gain of function; ID: intellectual disability; IRF2BPL: interferon regulatory factor 2 binding protein like; LoF: loss of function; ROS: reactive oxygen species; TIAM1: TIAM Rac1-associated GEF 1; TNPO2: transportin 2; VLCFA: very-long-chain fatty acid."
      }
    ]
  },
  {
    "id": "PMC11251054_multi",
    "image": [
      "images/PMC11251054-f1.png",
      "images/PMC11251054-f2.png",
      "images/PMC11251054-f3.png",
      "images/PMC11251054-f4.png",
      "images/PMC11251054-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Prenatal genetic diagnosis of fetuses with dextrocardia using whole exome sequencing in a tertiary center\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The flow chart of analysis in our cohort.\n\nFigure 2: Figure 2. Trio whole-exome sequencing results for case 1. The left panel showing the DNAH11: c.10036C > T (p.Arg3346*) variant which the region indicated by the red arrow. The right panel showing the DNAH11: c.5822G > C (p.Trp1941Ser) variant which the region indicated by the red arrow. (A) Sanger sequencing analysis of the fetus. (B) Sanger sequencing analysis of the mother. (C) Sanger sequencing analysis of the father.\n\nFigure 3: Figure 3. Trio whole-exome sequencing results for case 2. The left panel showing the LRRC56: c.1053dupC (p.Glu352Argfs*21) variant which the region indicated by the red arrow. The right panel showing the LRRC56: c.760G > T (p.Glu254*) variant which the region indicated by the red arrow. (A) Sanger sequencing analysis of the fetus. (B) Sanger sequencing analysis of the mother. (C) Sanger sequencing analysis of the father.\n\nFigure 4: Figure 4. Trio whole-exome sequencing results for case 3. The left panel showing the DNAH5: c.6304C > T (p.Arg2102Cys) variant which the region indicated by the red arrow. The right panel showing the DNAH5: c.4355 + 5G > A variant which the region indicated by the red arrow. (A) Sanger sequencing analysis of the fetus. (B) Sanger sequencing analysis of the mother. (C) Sanger sequencing analysis of the father.\n\nFigure 5: Figure 5. Trio whole-exome sequencing results for case 4. (A) The left panel showing the DNAH11: c.11352C > A (p.Phe3784Leu) variant which the region indicated by the red arrow. The right panel showing the DNAH11: c.1778G > A (p.Ser593Asn) variant which the region indicated by the red arrow. (a) Sanger sequencing analysis of the fetus. (b) Sanger sequencing analysis of the mother. (c) Sanger sequencing analysis of the father. (B) The left panel showing the PEX10: c.928 T > C (p.Cys310Arg) variant which the region indicated by the red arrow. The right panel showing the PEX10: c.814_815del (p.Leu272Valfs*66) variant which the region indicated by the red arrow. (a) Sanger sequencing analysis of the fetus. (b) Sanger sequencing analysis of the mother. (c) Sanger sequencing analysis of the father."
      }
    ]
  },
  {
    "id": "PMC11255849_multi",
    "image": [
      "images/PMC11255849-f1.png",
      "images/PMC11255849-f2.png",
      "images/PMC11255849-f3.png",
      "images/PMC11255849-f4.png",
      "images/PMC11255849-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Circulating biomarkers of kidney angiomyolipoma and cysts in tuberous sclerosis complex patients\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Strategy for metabolomics studies to find plasma chemical features associated with kidney AML/cyst in TSC patients (A) Overall schematic to find plasma chemical features associated with kidney AML/cyst. (B) Volcano plot showing 40 chemical features (red dots) applying selection criteria, a |log2(fold change)|>1 and an adjusted p value<0.05 by Student’s t test followed by FDR correction. N = 232 and 51 for AML/cyst-positive and -negative TSC patients.\n\nFigure 2: Figure 2. Correlation analysis between the identified chemical features (A) Correlation between MW 144.11485 (octanoic acid) and MW 142.09936 (putative 2-octenoic acid). (B) Correlation between MW 144.11485 (octanoic acid) and MW 160.10987 (putative hydroxy-octanoic acid). P values by Pearson’s chi-squared test. N = 232 AML/cyst-positive TSC patients.\n\nFigure 3: Figure 3. Comparison of abundance of the 7 selected chemical features between plasma samples from non-TSC, AML/cyst-negative TSC, and AML/cyst-positive TSC patients (A–G) Y axis indicates ion counts. Note that the abundance of these chemical features is significantly higher in the AML/cyst-positive TSC patients than the other groups, with octanoic acid in (A) showing the greatest differences. Numbers indicate p values by Student’s t test. N = 51, 51, and 232 patients for each group.\n\nFigure 4: Figure 4. Clinical performance of blood test combining 7 chemical features in detecting AML/cyst (A) Relative frequency of AML/cyst-negative vs. -positive patients that are either positive or negative on the test. Positive means one of the 7 chemical features is elevated above the cut-off. (B) Receiver operating characteristic (ROC) curve of the blood test. (C) Distribution of the number of positive markers in AML/cyst-negative vs. -positive patients. Note that no AML/cyst-negative patients showed >3 positive markers. In contrast, the majority of AML/cyst-positive patients showed at least 2 markers positive.\n\nFigure 5: Figure 5. Blood octanoic acid increase is linked to peroxisome activity (A) Ion counts of plasma VLCFAs in AML/cyst-positive patients with normal vs. increased octanoic acid. Numbers indicate p values by Student’s t test. (B) A significant negative correlation between the abundance of octanoic acid and that of very long-chain fatty acid (VLCFA) C26:3 in AML/cyst-positive patients. P value by Pearson’s chi-squared test. (C) Gene expression of peroxisome proliferator-activated receptors gamma (PPAR-gamma) in normal kidney (N = 3) vs. TSC-AML kidney (N = 11). Numbers indicate p values by Student’s t test."
      }
    ]
  },
  {
    "id": "PMC11297951_multi",
    "image": [
      "images/PMC11297951-f1.png",
      "images/PMC11297951-f2.png",
      "images/PMC11297951-f3.png",
      "images/PMC11297951-f4.png",
      "images/PMC11297951-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Enzalutamide inhibits PEX10 function and sensitizes prostate cancer cells to ROS activators\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A, B Prostate cancer cell lines (22Rv1, DU145, PC-3, C4-2, and LNCaP) treated with vehicle or ML210 (2 μM) (A) or RSL3 (1 μM) (B) and evaluation of the cell count and cell ROS level according to manufacturer’s instructions. C H2O2 level of prostate cancer cells (C4-2 and LNCaP) after treatment with ML210 (2 μM) or enzalutamide (5 μM) or combination. Unpaired t-test. (P < 0.0001 as “****”). D, E The CCK-8 OD value of two cell lines (C4-2-R and C4-2-N) after treating with ML210 (2 μM) and with or without enzalutamide (5 μM) combination. ANOVA. (P < 0.01 as “**”; P < 0.001 as “***”; P < 0.0001 as “****”). F, G Colony formation assay were performed on two cell lines (C4-2-R and C4-2-N) after treated with ML210 (2 μM) alone or in combination with enzalutamide (5 μM). Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”; P < 0.001 as “***”). H The IC50 of ML210 in prostate cell lines (C4-2) with or without enzalutamide (5 μM) treatment. I–K The images represented the results of C4-2 sequencing processed by ML210 (2 μM) or vehicle. Three independent samples were taken from each group and treated with ML210 (2 μM) or vehicle for 48 h before sampling. The volcano showed up- and down-regulated genes after ML210 treatment (I). The result of PPI showed that the peroxisome-related genes had changed significantly (J). Peroxisome pathway was the most significantly changed pathway after ML210 treatment in GSEA analysis (K). L The expression of Peroxisome-related genes and other key genes (KLK3) in prostate cancer cells (C4-2) after treatment with enzalutamide (5 μM). Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”; n.s. means nonspecific).\n\nFigure 2: Figure 2. A Expression of PEX10 in prostate cancer and normal tissues from the TCGA database. Unpaired t-test. (P < 0.05 as “*”). B The image showed the IHC staining score of PEX10 based on Gleason Score. One-way ANOVA. IHC staining score = ∑ (pi×i) = (percentage of weak intensity area ×1) + (percentage of moderate intensity area ×2) + (percentage of strong intensity area ×3), pi represents the percentage of the area of positive signal pixels; i represents the positive grade. C, D H2O2 level in prostate cancer cells (C4-2 and LNCaP) after overexpression of PEX10. Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”). E, F PMP70 expression level in prostate cancer cells (C4-2 and LNCaP) after overexpression of PEX10. Unpaired t-test. (P < 0.001 as “***”). G, H ROS level in prostate cancer cells (C4-2 and LNCaP) after overexpression of PEX10. Unpaired t-test. (P < 0.001 as “***”). I, J SA-β-GAL level in prostate cancer cells (C4-2 and LNCaP) after overexpression of PEX10. Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”). K, L The percentage of mitochondria with atrophy and increased membrane density and its statistic in C4-2 cells after PEX10 ectopic expression. Unpaired t-test. (P < 0.05 as “*”). M–O The immunofluorescence staining of JC-1 and statistic in prostate cancer cells (C4-2 and LNCaP) after overexpression of PEX10. Unpaired t-test. (P < 0.01 as “**”, P < 0.001 as “***”). P, Q Colony numbers and statistic in prostate cancer cells (C4-2 and LNCaP) after overexpression of PEX10. Unpaired t-test. (P < 0.01 as “**”; P < 0.001 as “***”). R, S CCK8 OD value and statistic in prostate cancer cells (C4-2 and LNCaP) after overexpression of PEX10. ANOVA. (P < 0.05 as “*”; P < 0.01 as “**”).\n\nFigure 3: Figure 3. A The expression of PEX10 after knockdown of PEX10. B–D PMP70 expression level in prostate cancer cells (C4-2 and LNCaP) after PEX10 knockdown. Unpaired t-test. (P < 0.001 as “***”). E, F H2O2 level in prostate cancer cells (C4-2 and LNCaP) after PEX10 knockdown. Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”). G–I ROS level in prostate cancer cells (C4-2 and LNCaP) after treating with ML210 (2 μM) and (or) PEX10 knockdown. Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”, P < 0.001 as “***”). J, K CCK8 OD value and statistic in prostate cancer cells (C4-2 and LNCaP) after treating with ML210 (2 μM) and (or) PEX10 knockdown. ANOVA. (P < 0.01 as “**”; P < 0.001 as “***” ; P < 0.0001 as “****”). L–N Colony numbers and statistic in prostate cancer cells (C4-2 and LNCaP) after treating with ML210 (2 μM) and (or) PEX10 knockdown. Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”; P < 0.001 as “***”). O Specific mechanistic diagram of the ML210/PEX10/ROS axis. Created with BioRender.com (www.biorender.com).\n\nFigure 4: Figure 4. A The expression of Peroxisome-related genes and other key genes (KLK3, AGPS and FAR1) in prostate cancer cells (C4-2) after AR knockdown. Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”; P < 0.001 as “***”; P < 0.0001 as “****”). B The protein level of PEX10 in AR-positive prostate cancer cells (C4-2 and LNCaP) and AR-negative prostate cancer cells (PC-3 and DU145). C, D AR and PEX10 expression at mRNA level in prostate cancer cells (C4-2 and LNCaP) after AR knockdown, Unpaired t-test. (P < 0.01 as “**”; P < 0.001 as “***”). E AR, PEX5, AGPS and PEX10 expression at the protein level (C4-2 and LNCaP) after AR knockdown. F, G H2O2 level in prostate cancer cells (C4-2 and LNCaP) after AR knockdown. Unpaired t-test. (P < 0.01 as “**”). H–J PMP70 expression level in prostate cancer cells (C4-2 and LNCaP) after AR knockdown. Unpaired t-test. (P < 0.01 as “**”, P < 0.001 as “***”). K–M The correlation of AR and PEX10 expression from the TCGA cohort (K). IHC shows the correlation of AR and PEX10 expression in prostate cancer patient tissues (n = 70, r = 0.6289, R2 = 0.3955, P < 0.0001) (L, M). N The expression of PEX10 and AR protein after AR knockdown or combined with ectopic expression of PEX10 in prostate cancer cells (C4-2 and LNCaP). O The expression of PMP70 protein after AR knockdown or combined with ectopic expression of PEX10 in prostate cancer cells (C4-2 and LNCaP).\n\nFigure 5: Figure 5. A ChIP-seq binding peak of H3K27ac, AR, and FOXA1 on PEX10 gene of prostate cancer cell lines (DU145, PC-3, VCaP, and LNCaP). B Lists of potential binding sequences of AR and FOXA1 in PEX10 2411280-2410760 region. C PEX10 expression at protein level in AR-positive prostate cancer cells (C4-2 and LNCaP) after treatment with DHT (100 nM) or enzalutamide (5 μM). D, E KLK3 and PEX10 expression at mRNA level in AR-positive prostate cancer cells (C4-2 and LNCaP) after treatment with DHT (100 nM) or enzalutamide (5 μM). Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”; P < 0.001 as “***”). F, G ChIP-qPCR showed the AR or FOXA1 binding change after AR or FOXA1 was ectopically expressed in C4-2 cells. H ChIP-qPCR showed the AR binding change after treatment with DHT (100 nM) or enzalutamide (5 μM). I The expression of PEX10 at the mRNA level after AR or FOXA1 knockdown alone or in combination. J The expression of PEX10 at the protein level after AR or FOXA1 knockdown alone or in combination. K The expression of PEX10 with the supplementation and a different dose of FOXA1. L The diagram shows the construction of the wild type or mutant PEX10 enhancer plasmid. M The luciferase level after transfection with wild-type or mutant PEX10 enhancer plasmid and treated with DHT (100 nM) or enzalutamide (5 μM). Unpaired t-test. (n.s. no specific; P < 0.01 as “**”; P < 0.001 as “***”, P < 0.0001 as “****”). N The luciferase level after transfection with wild-type or mutant PEX10 enhancer plasmid after ectopic expression of AR. Unpaired t-test. (n.s. no specific, P < 0.05 as “*”; P < 0.01 as “**”, P < 0.0001 as “****”)."
      }
    ]
  },
  {
    "id": "PMC11297951_multi_2",
    "image": [
      "images/PMC11297951-f6.png",
      "images/PMC11297951-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Enzalutamide inhibits PEX10 function and sensitizes prostate cancer cells to ROS activators\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A, B H2O2 level after treatment with vehicle, DHT (100 nM) or enzalutamide (5 μM) in prostate cancer cell lines (C4-2 and LNCaP). Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”). C, D H2O2 level after treatment with DHT and then knocked down PEX10 in prostate cancer cell lines (C4-2 and LNCaP). Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”). E, F The CCK-8 OD value of two PEX10 overexpression or overexpression control prostate cancer cell lines (C4-2 and LNCaP) after treatment with ML210 (2 μM) and combination with or without enzalutamide (5 μM). ANOVA. (P < 0.01 as “**”; P < 0.001 as “***”). G The growth state of patient prostate cancer tissue original organoid after treatment with ML210 (2 μM) or enzalutamide (5 μM) combination from days 1 to 9. Expression (H) and statistic (I) of AR, CK5/6, Ki67 and PEX10 in organoids of different groups by IHC method. Unpaired t-test. (n.s. no specific; P < 0.01 as “**”). J–L The image representative of in vivo tumor xenograft model (C4-2-R) (J) performed on SCID mice (n = 5) and the volume (L) and weight (K) statistic of the tumor with the constant treatment of ML210 (5 mg/kg) and/or enzalutamide (10 mg/kg), ANOVA. (P < 0.0001 as “****”). Unpaired t-test. (P < 0.05 as “*”; P < 0.01 as “**”).\n\nFigure 7: Figure 7. AR and FOXA1 bind the PEX10 enhancer and promote PEX10 promoter function. PEX10 participates in peroxisome formation and ROS process and finally inhibits the ROS. Enzalutamide could inhibit AR function and finally promote ROS. Enzalutamide could activate the ROS in prostate cancer cells and sensitize cells to ML210. Created with BioRender.com (www.biorender.com)."
      }
    ]
  },
  {
    "id": "PMC11326360_multi",
    "image": [
      "images/PMC11326360-f1.png",
      "images/PMC11326360-f2.png",
      "images/PMC11326360-f3.png",
      "images/PMC11326360-f4.png",
      "images/PMC11326360-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Loss-of-function of the Zinc Finger Homeobox 4 (ZFHX4) gene underlies a neurodevelopmental disorder\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) (Micro)deletions identified in probands 1–20 (#) are represented by the red bars and the duplication in proband 16 by the purple bar, all affecting ZFHX4 (light blue box). RefSeq coding genes are indicated respectively in blue131. The numbers colored in black corresponding to their CNV, represent an individual with a training DNA sample for methylome analysis. The numbers colored in grey corresponding to each CNV variant, are individuals with their DNA samples used as testing samples for the methylome analysis. Genomic positions are according to hg38; ZFHX4 is located on the reverse strand. (B) Nonsense, frameshift and splice variants in ZFHX4 are identified in probands 21–52 and visualized with IBS 2.0132. Protein and gene structure of the canonical transcript (GenBank: NM_024721.5) are shown in the top and bottom part, respectively. The majority of PTVs are located in exon 2 and 10. Top: LoF variants are present in the ZFHX4 cohort and located in different domains of ZFHX4. Blue dots represent the frameshift variants, the yellow dots the nonsense variant and the brown-grey dot represents the variants of proband 52 which contains a nonsense (Trp2176*) and a frameshift (Asn2188*fs) mutation. The dot has been placed on the position of the nonsense variant (Trp2176*). Bottom: coding exons are indicated as light blue boxes and the UTRs are represented with white boxes.\n\nFigure 2: Figure 2. Hi-C contact frequency matrix for control and proband 1 fibroblast (inversion indicated by red arrows). Close-up of left and right breakpoint region, including observed/expected (O/E) contact frequencies for control and proband 1.\n\nFigure 3: Figure 3. (A) The Euclidean clustering plot depicts ZFHX4 cases in red and the matched controls are shown in blue. The rows represent selected probes for the identified methylation pattern, while columns represent training cases and controls. A clear separation between cases and controls was observed. Methylation levels are color-coded: blue for 0 beta values and red for 1 beta values, with intensity indicating methylation level intensity. (B) The MDS plot demonstrates the differentiation between case and control samples based on selected probes. Cases are represented by red circles and controls by blue circles. C. Utilizing SVM classification trained with ZFHX4 samples against matched controls, as well as 75% of other control samples and samples from other disorders (blue), in addition to the remaining 25% of the database samples used for testing (gray), produced significant findings. Except for the ZFHX4 deletion samples (training), all other conditions and ZFHX4 testing samples (ZFHX4_truncating) exhibited significantly low MVP scores, indicating an enhancement in the specificity of the model. The ZFHX4 testing samples, which encompass truncating variants (ZFHX4_truncating), a large duplication variant (ZFHX4_duplication), an inversion variant (ZFHX4 _inversion) as well as an intragenic deletion (ZFHX4_in_frame_del) were included, enabling the model to predict class probability for ZFHX4 samples. Abbreviations: ADCADN, cerebellar ataxia, deafness, and narcolepsy, autosomal dominant; ARTHS, Arboleda-Tham syndrome; ATRX, alpha-thalassemia/intellectual development syndrome, X-linked; AUTS18, autism, susceptibility to 18; BEFAHRS, Beck-Fahrner syndrome; BFLS, Börjeson-Forssman-Lehmann syndrome; BIS, blepharophimosis intellectual disability SMARCA2 syndrome; CdLS, Cornelia de Lange syndrome1–4; CHARGE, CHARGE syndrome; 16p11.2del, 16p11.2 deletion syndrome; CSS_c.6200, Coffin-Siris syndrome (c.6232G>A [GenBank: NM_006015.4 (ARID1A)]; p.Glu2078Lys) (c.6254T>G [GenBank: NM_006015.4 (ARID1A)];p.Leu2085Arg) (c.6133T>C [GenBank: NM_017519.2 (ARID1B)]; p.Cys2045Arg); CSS4_c.2650, Coffin-Siris syndrome (c.2656A>G [GenBank: NM_001128849.1 (SMARCA4)]; p.Met886Val); CSS9, Coffin-Siris syndrome-9; Down, Down syndrome; Dup7, Williams-Beuren duplication syndrome (7q11.23 duplication syndrome); DYT28, Dystonia-28, childhood onset; EEOC, epileptic encephalopathy, childhood onset; FLHS, Floating-Harbour syndrome; GADEVS, Gabriele de Vries syndrome; GTPTS, Genitopatellar syndrome; HMA, HVDAS_C, Helsmoortel-Van der Aa syndrome (ADNP syndrome [central]); HVDAS_T, Helsmoortel-Van der Aa syndrome (ADNP syndrome [Terminal]); ICF1 Immunodeficiency, centromeric instability, facial anomalies syndrome 1, ICF2_3_4, immunodeficiency, centromeric instability, facial anomalies syndrome 2, 3, and 4; IDDSELD, intellectual developmental disorder with seizures and language delay; Kabuki, Kabuki syndromes 1 and 2; KDM2B, KDM2B-related syndrome; KDM4B, KDM4B-related syndrome; KDVS, Koolen de Vries syndrome; Kleefstra, Kleefstra syndrome 1; LLS, Luscan-Lumish syndrome; MKHK_ID4, Menke-Hennekam syndrome-1, 2; MLASA2, myopathy, lactic acidosis, and sideroblastic anemia-2; MRD23, intellectual developmental disorder, autosomal dominant 23; MRD51, intellectual developmental disorder, autosomal dominant 51; MRX93, intellectual developmental disorder, X-linked, XLID93; MRX97, intellectual developmental disorder, X-linked 97, XLID97; MRXSA, Armfield syndrome; MRXSCJ, syndromic X-linked intellectual disability, Claes-Jensen type; MRXSN, syndromic X-linked intellectual disability, Nascimento type; MRXSSR, syndromic X-linked intellectual disability, Snyder-Robinson type; PHMDS, Phelan-McDermid syndrome; PRC2, RENS1, Renpenning syndrome; RMNS, Rahman syndrome; RSTS, Rubinstein-Taybi syndrome-1, 2; RSTS1, Rubinstein-Taybi syndrome-1; RSTS2, Rubinstein-Taybi syndrome-2; SBBYSS, Say-Barber-Biesecker-Young-Simpson syndrome; Sotos, Sotos syndrome; TBRS, Tatton-Brown-Rahman syndrome; VCFS_comp, velocardiofacial syndrome; VCFS_core, velocardiofacial syndrome; WDSTS, Wiedemann-Steiner syndrome; WHS, Wolf-Hirschhorn syndrome; and Williams, Williams-Beuren deletion syndrome (7q11.23 deletion syndrome).\n\nFigure 4: Figure 4. (A) ZFHX4 expression levels during in vitro neural differentiation. RNA was sampled at the following stages: iPSCs, NSC (neural stem cells), neural progenitor cells (NPC) and direct differentiated neurons (Ns). An increasing expression is observed upon differentiation. The median expression value is indicated by the middle horizontal line. The whiskers indicate the minimum and maximum values. CNRQ, calibrated normalized relative quantity. (B) Endogenous ZFHX4 (399 kDa) levels in HEK293T, iPSCs, and NPCs as detected with western blot using the ZFHX4 antibody (top) and a vinculin antibody as a loading control (bottom). (C) ZFHX4 levels in developing human brain. ZFHX4 expression in the developing human brain (normalized RPKM data) showing higher expression during early prenatal development followed by decreased expression upon brain maturation. Data obtained from BrainSpan: http://www.brainspan.org. (D) Human embryonic craniofacial tissue bulk RNA-seq is visualized in a plot, showing an increase in ZFHX4 in craniofacial samples from five carnegie stages (CS13, CS14, CS15, CS17 and CS22)133.\n\nFigure 5: Figure 5. (A) The enriched ZFHX4 interacting proteins in NPCs shown in a volcano plot. For each detected protein, the log2 fold change (FC) between the ZFHX4 IP-enriched samples and the IgG controls is shown on the x axis, while the −log10 of the p value is shown on the y axis. The horizontal dashed line indicates the −log10 value of a p value equal to 0.05. Proteins with an FDR < 0.05, log2 FC > 2 and log2 FC < −2 are, respectively, highlighted in blue and red. (B) Hierarchical clustering of potentially interesting proteins. The proteins shown to be differentially abundant between groups are visualized in a heatmap after non-supervised hierarchical clustering of z-scored log 2 PG.MaxLFQ intensities. The heatmap color scale from blue to red represents the level of abundance. The interacting factors which are absent in the IgG control, significant but not absent at the IgG control and significantly enriched protein and absent in the IgG control, are listed in Tables S7 and S8. (C) ZFHX4 interacting factors associated to their biological processes with EnrichR."
      }
    ]
  },
  {
    "id": "PMC11326360_multi_2",
    "image": [
      "images/PMC11326360-f6.png",
      "images/PMC11326360-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Loss-of-function of the Zinc Finger Homeobox 4 (ZFHX4) gene underlies a neurodevelopmental disorder\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Annotation of CUT&RUN consensus peaks reveals ZFHX4 binding to promoter regions. Left: Distribution of the ZFHX4 consensus peaks relative to transcription start sites (TSS). Half of the peaks are found between 0–1 kb of the TSS. Right: Pie chart visualizing the genomic annotation and the percentage of the peaks that overlap a TSS, 5’ UTR, 3’ UTR, exonic, intronic, downstream or distal intergenic regions. This shows that 55.62% of ZFHX4 consensus peaks are found near gene promoters. (B) ZFHX4 binds to genes involved in axonogenesis, forebrain and nervous system development, including the regulation of the neurogenesis and synapse organization; cell and neuron differentiation. The gene ontology (GO) dot plot displays the top 20 enriched biological processes (BPs) ranked by gene ratio (the number of genes related to GO term/total number of significant genes) and the p-adjusted values for these terms (colour, p-value 1e10−7-1e10−5). The size of the dot represents the gene counts per BP. (C) ZFHX4 plays a key role in embryonic, neuron and axon developmental pathways. The Kyoto Encyclopedia of Genes and Genomes (KEGG) dot plot provides all enriched biological pathways ranked by gene ratio (# of genes related to GO term/total number of significant genes) and the p-adjusted values for these terms (color). The size of the dot represents the gene counts per pathway.\n\nFigure 7: Figure 7. (A) Gene structure of the zebrafish zfhx4 and ZFHX4. Top: The coding exons of ZFHX4 are shown as light grey boxes and light blue boxes for the CDS (coding sequence), and untranslated regions in red (5’-UTR) and green (3’-UTR). Bottom: The coding exons of zfhx4 are shown as light grey boxes and light blue boxes for the CDS, and untranslated regions in red (5’-UTR) and green (3’-UTR). (B) Representative craniofacial images for zfhx4 and scrambled zebrafish crispants are shown. Left: microscopic ventral view scrambled (top panel) and zfhx4 crispants (bottom panel) of Alcian blue stained craniofacial structures at 5 dpf reveal smaller ethmoid plates and shorter Meckel’s cartilage in the F0 zfhx4 crispant larvae. Right: Adapted image46 from the representation of the cartilage structures of the zebrafish neurocranium (dark blue) at 5 dpf by lines. The red lines and circle show the measurements taken and normalized with the length of the head (purple line). (C) Left: the surface area of the ethmoid plate was measured and normalized to the head length of the larvae. Right: The length of the individual Meckel’s cartilage structures was measured and normalized to the head length of the larvae. The ethmoid plate and the Meckel’s cartilage showed significant differences between crispant larvae compared to scrambled larvae (p-value ≤ 0.001 (***), p-value ≤ 0.0001 (****)) (D) zfhx4 crispants show a consistently lower movement frequency compared to scrambled control larvae during the complete behavior experiment but the trends during light and dark cycles remain similar. Dark periods are indicated with grey boxes. Data is represented as mean ± SEM (n=60/genotype)."
      }
    ]
  },
  {
    "id": "PMC11340756_multi",
    "image": [
      "images/PMC11340756-f1.png",
      "images/PMC11340756-f2.png",
      "images/PMC11340756-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Decoding temporal thermogenesis: coregulator selectivity and transcriptional control in brown and beige adipocytes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Upon cold exposure, BAT, iWAT, and eWAT respond differently. Representative H&E staining images of BAT, iWAT, and eWAT. Upon acute cold stimuli (6 h, 6°C), the size of lipid droplets (LDs) in brown adipocytes is rapidly reduced. Upon prolonged cold stimuli (72 h and 144 h), the shape of brown adipocytes is different from that in the absence of cold stimuli with highly multilocular lipid droplets. Unlike BAT, multilocular beige adipocytes are not present in iWAT upon acute cold stimuli (6 h). At 24 h cold stimuli, multilocular beige adipocytes (red arrow) are recruited in iWAT. In addition, 72 h and 144 h cold stimuli stimulate beige adipocyte recruitment. In contrast, multilocular beige adipocytes are not observed in eWAT. C57BL/6 male mice are housed at room temperature (22°C) and then exposed to cold stimuli. Until 6 h cold stimuli, mice were fasted. Scale bar: 50 µm. LN: lymph node.\n\nFigure 2: Figure 2. Neural pathways contributing to thermogenesis. Diverse hypothalamic subregions such as preoptic area of the hypothalamus (POA), posterior hypothalamus (PH), parvocellular oxytocin neurons of the PVN (PVNOT(parvo)), dorsomedial hypothalamus (DMH), pdyn-expressing dorsal medial region of the ventromedial hypothalamus (dmVMHPdyn), and the dorsal peduncular/dorsal tenia tecta (DP/DTT) region of the prefrontal cortex activate thermogenesis. Sympathetic premotor neurons in the rostral medullary raphe (rMR) control thermogenesis via projections to the intermediolateral nucleus (IML) spinal cord, which activate dorsal root ganglia (DRG), thereby activating BAT and iWAT. SG: stellate ganglia, T: thoracic, L: lumbar. The figure was created with BioRender.com.\n\nFigure 3: Figure 3. Molecular mechanisms of distinct brown and beige fat thermogenesis during cold stimuli. Upon cold stimuli, mammals maintain their body temperature by enhancing thermogenesis in several fat depots. Sympathetic neurons release norepinephrine (NE), which binds to β-adrenoreceptors (AR). This binding activates adenylyl cyclase (AC), elevating cyclic AMP (cAMP) levels and increasing PKA activity. Additionally, natriuretic peptides (NP) bind to natriuretic peptide receptor a (NPRA), which activates guanylyl cyclase (GC) to increase cyclic GMP (cGMP) concentrations, leading to PKG activation. Both activated PKA and PKG phosphorylates CREB and p38 MAPK. Further, p38 MAPK phosphorylates and activates ATF2 and PGC-1α, promoting the expression of thermogenic genes. PGC-1α interacts with thyroid receptors (TRs), PPARγ/RXRα, and IRF4 to stimulate the expression of thermogenic genes. Moreover, acute cold exposure rapidly downregulates RNF20 via PKA signalling, leading to GABPα accumulation and activation. In turn, GABPα contributes to potentiating brown fat thermogenesis by stimulating the expression of thermogenic and mitochondrial genes. In iWAT, prolonged cold exposure gradually upregulates RNF20, which activates PPARγ by degrading NCoR1, promoting beige fat recruitment. PPARγ binds with EBF2, PGC-1α, and PRDM16, which stimulates the expression of adipogenic and thermogenic genes in beige fat. Key transcriptional co-regulators controlling genetic programming for beige fat recruitment are also depicted. Gs: G protein subunit."
      }
    ]
  },
  {
    "id": "PMC11343561_multi",
    "image": [
      "images/PMC11343561-f1.png",
      "images/PMC11343561-f2.png",
      "images/PMC11343561-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Spectrum of Leukodystrophy and Genetic Leukoencephalopathy in Indian Population Diagnosed by Clinical Exome Sequencing and Clinical Utility\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. n = number; VUS = variants of uncertain significance; WM = white matter.\n\nFigure 2: Figure 2. ALD = adrenoleukodystrophy; ALSP = adult-onset leukoencephalopathy with axonal spheroids and pigmented glia; CNV = copy number variant; HLD = hypomyelinating leukodystrophy; IEM = inborn errors of metabolism; MLC = megalencephalic leukoencephalopathy with subcortical cysts; MLD = metachromatic leukodystrophy; n = number; NCL = neuronal ceroid lipofuscinosis; PMLD = Pelizaeus-Merzbacher-like disease; PMD = Pelizaeus-Merzbacher disease; VUS = variants of uncertain significance.\n\nFigure 3: Figure 3. MELAS = mitochondrial myopathy, encephalopathy, lactic acidosis, and stroke-like episodes; n = number; OMIM = Online Mendelian Inheritance in Man."
      }
    ]
  },
  {
    "id": "PMC11357481_multi",
    "image": [
      "images/PMC11357481-f1.png",
      "images/PMC11357481-f2.png",
      "images/PMC11357481-f3.png",
      "images/PMC11357481-f4.png",
      "images/PMC11357481-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Vigeo Promotes Myotube Differentiation and Protects Dexamethasone-Induced Skeletal Muscle Atrophy via Regulating the Protein Degradation, AKT/mTOR, and AMPK/Sirt-1/PGC1α Signaling Pathway In Vitro and In Vivo\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Effects of Vigeo on calf muscle properties in Dex-induced muscle atrophy in mice. (A) Mice with changes in body weight in each group with Dex-induced muscle atrophy. (B) Quantification of gastrocnemius (GA), soleus (SOL), tibialis anterior (TA), and extensor digitorum longus (EDL) muscle wet weight per body weight. (C) Radiological images of the calf muscles in four orientations: anterior, posterior, lateral, and medial. (D) Quantification of muscle volume in each group. n = 5 per group. Statistical analysis was performed using a one-way ANOVA test, the values are expressed as the mean ± SD of five mice. ** p < 0.01, *** p < 0.001 vs. normal control; # p < 0.05, ## p < 0.01, ### p < 0.001 as compared with Dex control.\n\nFigure 2: Figure 2. Effect of Vigeo on the muscle fiber cross-sectional area (CSA). (A) Representative hematoxylin and eosin (H&E) staining of GA muscle in each group. (B) Quantification of CSA of mice calf muscle is expressed as a relative percentage compared with control area. Quantification of muscle volume in each group. n = 5 per group. The values are expressed as the mean ± SD of five mice. *** p < 0.001 vs. normal control.; ### p <0.001 as compared with Dex control. (C) Distribution of the muscle fibers according to the CSA ranges (200–1800 μm2).\n\nFigure 3: Figure 3. Effect of Vigeo on mRNA and protein expression levels of muscle atrophy markers in mice GA muscle tissues. (A) The mRNA expression levels of atrogin-1 and MuRF-1 were analyzed by quantitative real-time RT-PCR in GA muscle from each group. (B) The protein expression level of atrogin-1 and MuRF-1 was also confirmed with western blot analysis. Lanes 1 and 2 are the two randomly selected samples of each group. (C) The relative protein band intensity is represented as a relative percentage against the β-actin control blot. Data are expressed as the mean ± SD. * p < 0.05, ** p < 0.01, *** p < 0.001 vs. Normal control; ## p < 0.01, ### p < 0.001 as compared with Dex control.\n\nFigure 4: Figure 4. Effect of Vigeo on the expression of the MyHC and the formation of multi-nucleated myofibers in C2C12 myotube differentiation. (A) C2C12 cells were incubated with the indicated concentration of Vigeo (0, 10, 25, and 50 μg/mL). The cytotoxicity of Vigeo in C2C12 was analyzed by XTT assay. C2C12 myoblasts were cultured in the presence or absence of Vigeo 50 μg/mL with DM media for 5 d and followed by treatment with Dex 100 μM for 48 h. (B) Immunofluorescence staining of myotubes for MyHC (green) and DAPI (blue) was confirmed. (C) The graph presented shows the numbers of myotubes with three or more nuclei and the comparison of diameter for width and length of myotubes among the four groups. (D) Quantitative real-time RT-PCR and (E) western blot analysis of myoblast differentiation markers containing MyHc1, MyoD, and myogenin. Data are expressed as the mean ± SD. * p < 0.05, ** p < 0.01, *** p < 0.001 vs. Normal control; # p < 0.05, ## p < 0.01, ### p < 0.001 as compared with control at the indicated time (n = 3).\n\nFigure 5: Figure 5. Effect of Vigeo on the myoblast differentiation and myotube atrophy in C2C12 cells. C2C12 cells were cultured with or without Vigeo (25 μg/mL) for indicated times (0, 2, 4, 6 days) in DM. (A) Quantitative real-time RT-PCR and (B) western blot were used for the analysis of mRNA and protein expression levels against myoblast differentiation markers including MyHC1, myogenin, and MyoD. Data represent means ± SD (n = 3). * p < 0.05, *** p < 0.001 vs. control at 0 day. # p < 0.05, ### p < 0.001 as compared with control at the indicated time."
      }
    ]
  },
  {
    "id": "PMC11362147_multi",
    "image": [
      "images/PMC11362147-f1.png",
      "images/PMC11362147-f2.png",
      "images/PMC11362147-f3.png",
      "images/PMC11362147-f4.png",
      "images/PMC11362147-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peds1 deficiency in zebrafish results in myeloid cell apoptosis and exacerbated inflammation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. One-cell stage zebrafish eggs were microinjected with std or peds1 crRNA/Cas9 complexes and the following parameters were evaluated: (A) Larval length and representative images (brightfield channel) at 3- and 5 dpf, (B) Nfkb fluorescent reporter expression levels and representative images (green channel; Tg(NFkB-RE:eGFP)) at 3 and 5 dpf analyzed by fluorescence microscopy, (C) Il1b fluorescent reporter expression levels and representative images (green channel; Tg(il1b:GFP-F)ump3) at 3 dpf analyzed by fluorescence microscopy. D Transcript levels of the indicated genes analyzed at 3 dpf by RT-qPCR. E, F Number of neutrophils and macrophages and representative images of microinjected larvae after 48 h of treatment with caspase 3 inhibitor (C3I) or vehicle (DMSO) were quantitated by fluorescence microscopy (red channel; Tg(lyz:DsRED2) and Tg(mfap4.1:Tomato), respectively). G, H Hematopoietic stem and progenitor cells (green channel; Tg(-6.0itga2b:eGFP)) and erythrocytes (red channel: Tg(gata1a:dsRED)) number were quantitated by fluorescence microscopy. I, J Number of neutrophils and macrophages and representative images of larvae microinjected to specifically express peds1 in neutrophils using the neutrophil-specific myeloperoxidase (mpx) promoter and analyzed by fluorescence microscopy. Each point represents one larva and the mean ± SEM of each group is also shown. P-values were calculated using one-way ANOVA Tukey’s and multiple range or unpaired Student’s t-test. n.s, not significant, *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.001. auf arbitrary units of fluorescence.\n\nFigure 2: Figure 2. A Schematic of the experimental procedure used for chronic skin inflammation assays. Spint1a-deficient one-cell stage eggs were microinjected with std or peds1 crRNA/Cas9 complexes and imaged at 3 and 5 dpf. Treatments of interest were added to dechorionated embryos at 1 dpf by bath immersion and renewed daily. Spint1a-deficient larvae showed chronic skin inflammation with increased skin neutrophil infiltration, Nfkb fluorescent reporter expression levels and keratinocyte aggregates. B Analysis and representative images (brightfield channel) of larval length at 3 and 5 dpf. C Number of keratinocyte aggregates in the skin (red arrows) and representative images (brightfield channel) at 3 dpf. D Analysis and representative images of Nfkb fluorescent reporter expression levels (green channel; Tg(NFkB-RE:eGFP)sh235) at 3 dpf by fluorescence microscopy. E Total number and percentage of neutrophils in the skin and representative merge images (brightfield and red channel; Tg(lyz:DsRED2)nz50) quantitated by fluorescence microscopy. F Number of skin aggregates and (G) percentage of skin neutrophils quantitated in crstd and crpeds1 spint1a-/- larvae treated for 48 h with 20 µM HsVEPE1, 20 µM HsAEPE1 or vehicle (DMSO). H Representative merge images (brightfield and red channel; Tg(lyz:DsRED2)nz50) of each treatment analyzed in (F) and (G) by microscopy fluorescence are shown. Each point represents one larva and the mean ± SEM of each group is also shown. P-values were calculated using one-way ANOVA and Tukey’s multiple range or unpaired Student’s t-test, as appropriate. n.s, not significant, *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.001. auf arbitrary units of fluorescence.\n\nFigure 3: Figure 3. A Schematic of the experimental procedure used for tail injury assays. One-cell stage zebrafish eggs were microinjected with std or peds1 crRNA/Cas9 complexes. At 3 dpf larvae were tail amputated and then inflammation and immune cell recruitment at the injury site (dotted lines) were analyzed at 3, 6, 24 and 48 h post-wounding (hpw) by fluorescence microscopy. The wound area is defined as the region between the amputation edge and the end of the caudal hematopoietic tissue (CHT). B, C Number of neutrophil and macrophages recruited at the injury site and representative merge images (brightfield and red channel; Tg(lyz:DsRED2)nz50 and Tg(mfap4.1:Tomato)xt12, respectively). D Number of M1-like macrophages (Tnfa+) recruited at the injury site and representative merge images (red channel: Tg(mfap4.1:Tomato)xt12 and green channel: Tg(tnfa:eGFP-F)ump5). E Analysis of H2O2 release at the wound site using the fluorogenic substrate acetyl-pentafluor-obenzene sulphonyl fluorescein. E–G Analysis and representative images of Il1b (green channel; Tg(il1b:GFP-F)ump3) and Nfkb fluorescent reporter expression levels (green channel; Tg(NFkB-RE:eGFP)sh235) at the wound site. Each point represents one larva and the mean ± SEM of each group is also shown. P-values were calculated using one-way ANOVA and Tukey’s multiple range. n.s, not significant, *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.001. auf arbitrary units of fluorescence.\n\nFigure 4: Figure 4. A Schematic of the experimental procedure used for tail injury and regeneration assays. Three dpf larvae previously microinjected with std or peds1 crRNA/Cas9 complexes alone or in combination with cril1b were tail fin amputated and regeneration was evaluated by measuring regenerated fin areas up to 5 dpf (yellow). B, C Measurement of regenerated fin areas and representative images (brightfield channel). D Analysis and representative images of Il1b fluorescent reporter expression levels (green channel; Tg(il1b:GFP-F)ump3) by microscopy fluorescence. Each point represents one larva and the mean ± SEM of each group is also shown. P-values were calculated using one-way ANOVA and Tukey’s multiple range. n.s, not significant, *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.001. auf arbitrary units of fluorescence.\n\nFigure 5: Figure 5. A Schematic of the experimental procedure used for infection assays. Single-cell zebrafish embryos microinjected with std or peds1 crRNA/Cas9 complexes were dechorionated and infected at 2 dpf through either the otic vesicle (neutrophil recruitment) or yolk sac (larval survival) with Salmonella enterica serovar Thyphimurium (ST). Treatments of interest were added daily from 1 dpf by immersion and the number of surviving larvae was counted daily for the next 5 days. B Survival analysis of crstd and crpeds1 larvae infected with ST and treated with 20 µM HsVEPE1 or vehicle (DMSO). C Survival analysis of crstd and crpeds1 larvae infected with ST and treated with 20 µM HsAEPE1 or vehicle (DMSO). D Survival analysis of crstd and crpeds1 larvae infected with ST and treated with caspase 3 inhibitor (C3I, 50 µM) or vehicle (DMSO). E, F Number of neutrophil in the otic vesicle and body at 1 and 6 h post-infection in crstd and crpeds1 larvae treated with 50 µM C3I or vehicle (DMSO) counted by fluorescence microscopy (red channel; Tg(lyz:DsRED2)nz50). G Survival analysis of crstd and crpeds1 larvae injected in combination with antisense (As) or csf3a mRNA and infected with ST. H Number of neutrophil in whole body in uninfected crstd and crpeds1 larvae of 3 dpf treated with 50 µM C3I or vehicle (DMSO) counted by fluorescence microscopy (green channel; (mpx:eGFP)i114). B–D and G A log-rank test was used to calculate the statistical differences in the survival of the different experimental groups. E, F Each point represents one larva and the mean ± SEM of each group is also shown. P-values were calculated using one-way ANOVA and Tukey’s multiple range. n.s not significant, *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.001."
      }
    ]
  },
  {
    "id": "PMC11362147_multi_2",
    "image": [
      "images/PMC11362147-f6.png",
      "images/PMC11362147-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Peds1 deficiency in zebrafish results in myeloid cell apoptosis and exacerbated inflammation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A Generation of a DKO line by whole deletion of peds1a and peds1b genes using CRISPR-Cas9. B–F Total plasmalogen and precursor quantification (B), larval length (C), number of neutrophil (D) and macrophage (E), and transcript levels of nfkb1, il1b, tnfa and clxcl8a genes, assayed by RT-qPCR (F). Each point represents one larva and the mean ± SEM of each group is also shown. *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001. ROI region of interest, CHT caudal hematopoietic tissue.\n\nFigure 7: Figure 7. Inhibition of plasmalogen synthesis promotes a proinflammatory stage with increased neutrophil and macrophage apoptosis. Plasmalogen deficiency also exacerbates chronic skin inflammation, impairs inflammation resolution and tissue regeneration, and results in increased susceptibility to infection."
      }
    ]
  },
  {
    "id": "PMC11369193_multi",
    "image": [
      "images/PMC11369193-f1.png",
      "images/PMC11369193-f2.png",
      "images/PMC11369193-f3.png",
      "images/PMC11369193-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural insights into human ABCD3-mediated peroxisomal acyl-CoA translocation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a A diagram showing the substrate specificity of ABCD1–3. All three transporters locate on the peroxisome membrane and are indicated as a pair of ellipses in different colors. Each receptor’s corresponding substrates are highlighted with a rectangle of the same color as the receptor. DHCA-CoA/THCA-CoA, di-/tri-hydroxycholestanoyl acyl-CoA. b Substrate concentration-dependent ATPase activity of chABCD3 in the detergent of LMNG + CHS with 2 mM ATP upon addition of phytanoyl-CoA. The data points were fitted with a Michaelis-Menten equation. c ATPase activity of chABCD3 in the presence of various fatty acyl-CoAs. All data points for b and c represent means of three independent measurements in the detergent of LMNG + CHS. Error bars represent the means ± SD. Student’s t-test was used in the comparison of the basal ATPase activity and substrate-stimulated ATPase activity. The P values of phytanoyl-CoA, C22:0-CoA, C24:0-CoA, C26:0-CoA are 0.0000436, 0.0417, 0.00736 and 0.0672, respectively. *P < 0.05, **P < 0.01, ***P < 0.001. d Refined cryo-EM maps of two ABCD3 structures. The cryo-EM maps are colored by UCSF ChimeraX 1.2.5 according to the local resolution of the cryo-EM estimated by cryoSPARC 3.2.\n\nFigure 2: Figure 2. a, b Side (a) and top (b) views of the overall structure of phytanoyl-CoA-bound ABCD3. Two subunits of ABCD3 are colored in yellow and teal, respectively. The peroxisome membrane boundaries are indicated by two blue lines. The two phytanoyl-CoA molecules are shown as magenta sticks. The density maps of phytanoyl-CoA molecules are shown as blue mesh, and are contoured at 5σ. c The phytanoyl-CoA-binding residues are shown as sticks, and hydrogen bonds (≤ 3.5 Å) and salt bridges (≤ 4.0 Å) are indicated as blue dotted lines. The hydrophobic residues surrounding the fatty acyl chain within 4.5 Å are shown as sticks. The density map of residues shown as blue mesh are contoured at 7σ. d Relative ATPase activities of chABCD3 and mutants in the detergent of LMNG + CHS with 2 mM ATP upon addition of phytanoyl-CoA. The relative activity represents the substrate-stimulated ATPase activity of chABCD3 or its variants each harboring a single mutation in the residues at the substrate-binding site. Each data point is the average of three independent experiments, and error bars represent the means ± SD. Student’s t-test was used for the comparison of the phytanoyl-CoA-stimulated ATPase activites between WT chABCD3 and its variants. The P values of E111A, K322A, Y330A are 0.0000802, 0.0000169, and 0.000278, respectively. *P < 0.05, **P < 0.01, ***P < 0.001.\n\nFigure 3: Figure 3. a Side and top views of the superposition of the phytanoyl-CoA-bound ABCD3 (teal) against the C22:0-CoA-bound ABCD1 (lightpink). TMs are sequentially numbered and shown as cartoons. The phytanoyl-CoA molecules are shown as magenta sticks, and the C22:0-CoA molecules are shown as blue sticks. b Relative ATPase activities of chABCD3 and mutants in the detergent of LMNG + CHS with 2 mM ATP upon addition of phytanoyl-CoA. The relative activity represents the substrate-stimulated ATPase activity of chABCD3 or its mutants each harboring a single mutation of the conserved residues at the CoA substrate-binding site found in ABCD1. Each data point is the average of three independent experiments, and error bars represent the means ± SD. Student’s t-test was used for the comparison of the phytanoyl-CoA-stimulated ATPase activites between WT chABCD3 and its variants. The P values of R96A, S205A, K209A, Y323A, R373A are 0.0000298, 0.00000464, 0.00000578, 0.00000386 and 0.0000235, respectively. *P < 0.05, **P < 0.01, ***P < 0.001.\n\nFigure 4: Figure 4. a Cartoon representation of ATP-bound ABCD3. Two subunits of ABCD3 are colored in yellow and teal, respectively. ATP molecules are displayed as teal spheres. TMs are sequentially labeled. b Side and top views of the superposition of the ATP-bound ABCD3 (gray) against the phytanoyl-CoA-bound ABCD3 (yellow). TMs are sequentially numbered, and phytanoyl-CoA molecules are shown as magenta sticks. Cα atoms of Ile273 are displayed as spheres. The shifts of TM2, TM4, TM5′ and TM6′ are indicated by green, red, purple and blue arrows, respectively. c Proposed snapshots of the translocation cycle for the ABCD3-mediated phytanoyl-CoA translocation. At first, the CoAs enter the translocation cavity by diffusion while the fatty acid moieties stay in the membrane approaching ABCD3 (State 1). During the entry process, the CoA moiety points towards the peroxisomal space (State 2). After bound to the next binding sites, phytanoyl-CoA fully enters, with its CoA moiety pointing to the cytosol side, and the fatty acid is embraced by more TMs (State 3). The fully bound substrate triggers conformational change of ABCD3, facilitating the binding of ATP and a further moving of the CoA moiety towards the cytosol (State 4). After the hydrolysis of ATP, phytanoyl-CoA molecules are fully transported. Alternately, it is possible that phytanoyl-CoA is digested into CoA and phytanic acid, after which the phytanic acid is translocated into the peroxisome while CoA is released (State 5)."
      }
    ]
  },
  {
    "id": "PMC11375543_multi",
    "image": [
      "images/PMC11375543-f1.png",
      "images/PMC11375543-f2.png",
      "images/PMC11375543-f3.png",
      "images/PMC11375543-f4.png",
      "images/PMC11375543-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Bioinformatic Analyses and Integrated Machine Learning to Predict prognosis and therapeutic response Based on E3 Ligase-Related Genes in colon cancer\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Presentation and functional annotation of differentially expressed ERGs. (A) Heatmap showing fifty differentially expressed ERGs, with red dots indicating significantly upregulated genes and blue dots indicating significantly downregulated genes; (B) Volcano map of differentially expressed ERGs between colon tissues and normal tissues; Histogram depiction (C) in the aspects of the BP, CC, MF categories; Histogram depiction (D) of the top 16 enriched pathways.\n\nFigure 2: Figure 2. WGCNA of ERGs and identification of E3-related hub genes. (A) Analysis of the scale-free index and mean connectivity for the confirmation of soft-thresholding powers; (B) Hierarchical clustering dendrogram of ERGs in a variety of modules; (C) Correlation analysis between different tissues and the module eigengenes; (D) Scatter plots of GS score and MM for ERGs in the turquoise module.\n\nFigure 3: Figure 3. Consensus clustering. (A) Venn diagram analysis showing the overlapping ERGs of the differentially expressed ERGs and hub genes from WGCNA; (B) The relative change in the area under the CDF curve from k = 2 to 9;(C) Empirical CDF plots from 2 to 9; (D) Consensus matrix heatmap for K = 2; (E) PCA analysis based on the two clusters; (F) Kaplan-Meier curves of OS in the two clusters in colon cancer; (G) GSVA representing the different biological pathways between the two clusters;(H) Correlation between two clusters and the tumor microenvironment;(I)Comparison of immune-related cells between cluster A and B;(J) Comparison of immune checkpoints between cluster A and B;(K) Comparison of immune functions between cluster A and B.\n\nFigure 4: Figure 4. A prognostic model was constructed and validated based on 10 machine learning algorithms and 92 algorithm combinations. (A) A total of 92 kinds of prognostic models though LOOCV framework and the C-index of each model in all validation datasets; (B) Differential expression of the 12 risk genes between high- and low- risk subgroup; (C,E,G,I,K)Kaplan-Meier survival curves revealed that patients in the high-risk group had a worse prognosis compared with those in low-risk group in the training and validation dataset. (D,F,H,J,L) ROC curves validated the prognostic capability of the risk model based on risk genes in the training and validation dataset.\n\nFigure 5: Figure 5. Cox regression analyses of OS and the establishment of a nomogram model. (A) Forest plot of univariate regression analyses; (B) Forest plot of multivariate Cox regression to identify the independent prognostic factors; (C) Distribution of tumor stage in the high- and low-risk groups in the TCGA cohort (p=0.001);(D) A nomogram model integrating the risk score and clinical features for the prediction of OS in colon cancer patients in the whole TCGA dataset; (E) Calibration plots of 1-, 3- and 5-year OS probabilities of the nomogram model; (F-I) AUC curves of 1-, 3-, and 5-year OS verified the potential prediction value of the prognostic indicators."
      }
    ]
  },
  {
    "id": "PMC11375543_multi_2",
    "image": [
      "images/PMC11375543-f6.png",
      "images/PMC11375543-f7.png",
      "images/PMC11375543-f8.png",
      "images/PMC11375543-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Bioinformatic Analyses and Integrated Machine Learning to Predict prognosis and therapeutic response Based on E3 Ligase-Related Genes in colon cancer\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Clinical correlation analysis and stratified analysis of the high- and low-risk subgroups. (A) A heatmap of the correlations between clinical features and risk subgroups, as well as risk genes;(B-G) A strip chart revealed the difference of clinicopathological features between different risk subgroups(***p < 0.001; **p < 0.01;*p < 0.05); Kaplan-Meier curves showing the prognostic value of different risk subgroups for the patients separated by each clinicopathological feature. (H,I) Age; (J,K) Gender; (L,M) T Stage; (N,O) N stage; (P,Q) M stage; and (R,S) stage.\n\nFigure 7: Figure 7. Relationships between the risk signature and immune infiltration, immune checkpoint genes and somatic mutation features. (A) Correlation between risk scores and immune cell abundance based on different software programs;(B) The proportion of 22 immune cells between the high- and low-risk subgroups;(C) The discrepancy of tumor microenvironment between high- and low-risk subgroups; (D) Comparison of immune functions between the different risk groups; (E) Comparison of immune cell between the different risk groups;(F-K) Pearson correlation analysis between the risk score and infiltration of six types of immune cells; (L) Correlations between immune checkpoints and risk scores as well as risk genes; (M,N) Waterfall plot of somatic mutation characteristics in the high- and low-risk subgroups; (O,P) The relationships between the TMB and risk signatures; (Q) Correlation analysis between risk scores and the mutated gene(TP53). ***p < 0.001; **p < 0.01; *p < 0.05.\n\nFigure 8: Figure 8. Comparison of the two risk groups in routine drug sensitivity, molecular typing of immune escape and pathways. (A-O) Correlations between the two risk subgroups and sensitivity to routine antitumor drugs. (P)The high-risk group had higher TIDE scores than the low-risk group; (Q-T) Comparison of immunophenoscore (IPS) between different risk subgroups; (U,V,W) GSEA and GSVA representing the different biological pathways between the high- and low-risk subgroups. P values are presented as follows: ***p < 0.001; **p < 0.01; *p < 0.05; ns: not significant;\n\nFigure 9: Figure 9. PRELP inhibit the migration and proliferation of Hct116 and Lovo cells. (A,B) PRELP inhibited the migration of Hct116 and Lovo cells based on scratch wound analysis. Scale bar: 1000μm. (C) Migration rate quantitative analysis in (A,B). (D,E) CCK-8 assay revealed that PRELP inhibited the proliferation of Hct116 and Lovo cells. (F,G) Detection of the expression of PRELP after exogenous transfection by qRT-PCR and WB analysis. *P < 0.05, **P < 0.01, ***P < 0.001 compared with the control group."
      }
    ]
  },
  {
    "id": "PMC11376382_multi",
    "image": [
      "images/PMC11376382-f1.png",
      "images/PMC11376382-f2.png",
      "images/PMC11376382-f3.png",
      "images/PMC11376382-f4.png",
      "images/PMC11376382-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Development of a rapamycin-inducible protein-knockdown system in the unicellular red alga Cyanidioschyzon merolae\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A constitutive protein knockdown utilizing the human FRB domain and its derivative in C. merolae. A) A schematic illustration of the degradation process of an FRB-conjugated target protein. The presence of FRB leads to the destabilization of the target protein, ultimately resulting in the degradation of both the FRB and the target protein. B) The structures of mVenus (the target protein here) and the 4 types of human FRB-fused mVenus expressed in C. merolae. FRB, 3×FRB, FRB*, and 3×FRB* tags were attached to the carboxy-terminus of mVenus. FRB* contains 3 mutations (K72P, T75L, and W78F), denoted with + in the illustration, which has been reported to exhibit a higher destabilizing effect than the WT FRB (Stankunas et al. 2003). Although not indicated in the illustration, there is a 6×G peptide linker between mVenus and any FRB tag. C) Immunoblotting comparing the efficiency of the 4 different types of FRB tags in reducing mVenus level in the cells. The left panel shows the immunoblot using the anti-GFP antibody, which reacts with mVenus, to compare the levels of mVenus in the cells expressing mVenus alone or mVenus conjugated with the 4 types of FRB tags. The WT cell was used as a negative control. The immunoblot using the eukaryotic translation elongation factor 2 (eEF-2) antibody and the Coomassie brilliant blue (CBB)-stained PVDF membrane are also shown as loading controls. The predicted molecular weights based on the amino acid sequence of mVenus, mVenus-FRB, mVenus-3×FRB, mVenus-FRB*, and mVenus-3×FRB* are 26, 37, 58, 37, and 58 kDa, respectively. The right panel shows a bar graph quantifying the protein levels. The signal intensity of mVenus alone was set as 100%. The values represent the mean of technical triplicate of the immunoblotting results, and the bars indicate the Sd. Note that both 3×FRB-fused and 3×FRB*-fused mVenus proteins were undetectable in the immunoblotting. D) An illustration, as well as the differential interference contrast (DIC) and fluorescent micrographs of the C. merolae cell in the G1 phase. The cell possesses a single chloroplast and mitochondrion. The chloroplast emits red fluorescence. The scale bar represents 2 µm in all images in D). E) Fluorescent microscopic images of the cells expressing mVenus or that conjugated with the 4 different kinds of FRB tag. WT served as a negative control. The images in the left and right column represent autofluorescence from chloroplasts (Chl) and mVenus fluorescence, respectively. For the images of Chl, those of the bright field (BF) were merged. The scale bar represents 5 µm in all images in E).\n\nFigure 2: Figure 2. Application of an FRB-tag-mediated knockdown for RB protein. A) A schematic illustration of the function of RB as a negative regulator of G1/S transition. RB directly binds E2F and inhibits E2F-DP heterodimer to transcribe S-phase genes. The arrow line indicates positive regulation of the transcription of S-phase genes by E2F, whereas the T-shaped line indicates negative regulation by RB. CDK-cyclin accumulates in accordance with cellular growth during the G1 phase, phosphorylating RB, which results in RB inactivation and allows E2F-DP to transcribe S-phase genes. B) The structures of HA-RB and the 4 types of FRB-inserted HA-RB variants expressed in C. merolae. FRB, 3×FRB, FRB*, and 3×FRB* were inserted between HA and the amino terminus of RB. FRB* contains 3 mutations (K72P, T75L, and W78F), denoted with a + in the illustration. Although not indicated in the illustration, a GGGGS peptide linker was inserted between 3× HA and RB in the HA-RB protein. Additionally, a 6×G peptide linker was inserted between each FRB tag and RB. C) Immunoblotting comparing the efficiency of the 4 different types of FRB tags in reducing RB level in the cells. RB and HA-RB were detected using the anti-RB and an anti-HA antibody, respectively. For each strain other than WT, the results of 2 independent transformants (#1 and #2) are shown. The predicted molecular weights based on the amino acid sequence of RB, HA-RB, HA-FRB-RB, HA-3×FRB-RB, HA-FRB*-RB, and HA-3×FRB*-RB are 101, 105, 115, 136, 115, and 136 kDa, respectively. The values below the bands indicate the relative signal intensities of RB, HA-RB, and HA-FRB-RB proteins. The average signal intensity of 2 independent clones (#1 and #2) of HA-RB was set to 100%. The CBB-stained PVDF membrane is also shown as a loading control. D) DIC images of WT, HA-RB, and the 3 kinds of HA-FRB-RB strains. The results for Clone #1 are presented for each strain. Images of Clone #1 and Clone #2 for each strain are provided in Supplementary Fig. S1. The scale bar represents 5 µm in all images in D). E) A box plot comparing the cell volume of WT, HA-RB, the 3 types of HA-FRB-RB, and RB-KO strains. The results for 2 independent clones (#1 and #2) are shown for each transformant. The box extends from the first to the third quartile, with the vertical line representing the median, the cross indicating the mean, and the error bar indicating the Sd. NS, not significant; *P < 0.01 (Student’s t-test; pairwise comparisons between the 2 clones). The histograms representing the distribution of cell volume in respective strains are shown in Supplementary Fig. S1.\n\nFigure 3: Figure 3. Diagram of a rapamycin-inducible protein-knockdown system. A) The flow of ubiquitination of a substrate protein through the SCF E3 ligase complex, which results in degradation of the substrate protein in proteasome. An E1 ubiquitin-activating enzyme initiates ubiquitination by activating and transferring a ubiquitin to an E2 ubiquitin-conjugating enzyme. The E2 enzyme then ubiquitinates a substrate protein captured by the SCF complex. The SCF complex consists of a F-box protein, SKP1, CUL1, and RBX1. The F-box proteins determine the substrate specificity for the SCF complex. SKP1 mediates the interaction between F-box proteins and CUL1, which serves as a primary scaffold protein. RBX1 connects CUL1 to the E2 ubiquitin-conjugating enzyme. B) The experimental design of the rapamycin-inducible protein-knockdown system. The SCF E3-ligase complex was employed for ubiquitination of a target protein. The rapamycin-mediated heterodimerization of FRB domain (of TOR kinase) and FKBP protein was utilized to facilitate the incorporation of the target protein (mVenus, in this case) into the SCF complex. By fusing the human FRB domain to a target protein and expressing an SCF complex component fused with the human FKBP, followed by the addition of rapamycin, the target protein is expected to be captured by the SCF complex and degraded via the ubiquitin-proteasome pathway. In this study, we evaluated the efficiency of fusing FKBP to SKP1, CUL1, or RBX1 as SCF components for the degradation of mVenus-FRB upon the addition of rapamycin. C) The structures of mVenus-FRB, HA-FKBP-SKP1, HA-FKBP-CUL1, and HA-FKBP-RBX1 expressed in C. merolae.\n\nFigure 4: Figure 4. Evaluation of the rapamycin-inducible protein-knockdown system in C. merolae. A) Immunoblotting using the anti-HA antibody confirmed the expression of HA-FKBP-SKP1, HA-FKBP-CUL1, and HA-FKBP-RBX1 in the mVRD-SKP1, mVRD-CUL1, and mVRD-RBX1 strains, respectively, where mVenus-FRB is also expressed. The predicted molecular weights based on the amino acid sequence of mVenus-FRB, HA-FKBP-SKP1, HA-FKBP-CUL1, and HA-FKBP-RBX1 are 37, 37, 127, and 29 kDa, respectively. WT and mV-FRB strains were used as negative controls. B) Immunoblotting comparing the efficiency of rapamycin-induced degradation of mVenus-FRB in the mVRD-SKP1, mVRD-CUL1, and mVRD-RBX1 strains. For each culture, 500 nm rapamycin or DMSO (a control) was added and the cells were harvested 2 h after the addition. The mV-FRB was used as a negative control. mVenus-FRB protein was detected with the anti-GFP antibody. The CBB-stained PVDF membrane is also shown as a loading control. The values below the bands indicate the relative signal intensities of the mVenus-FRB protein. The average and Sd of immunoblotting of 3 independent transgenic clones are indicated for each strain. The signal intensity in each strain in the absence of rapamycin was set to 100%. C) Degradation efficiency of mVenus-FRB at different concentrations of rapamycin. Immunoblotting showing the relative level of mVenus-FRB protein in the mVRD-SKP1 and mVRD-CUL1 culture 2 h after the addition of 0, 10, 50, 100, 500, 1,000, and 2,500 nm rapamycin. The accompanying graph shows the change in mVenus-FRB protein level obtained from biological triplicates. The signal intensity in each strain in the absence of rapamycin was set to 100%. The degradation concentrations (DC50) in mVRD-SKP1 and mVRD-CUL1, as shown in the graph, were calculated using the quartic approximation equations in Microsoft Excel. D) Degradation kinetics of mVenus-FRB protein. Immunoblotting showing the time course of the changes in the relative level of mVenus-FRB protein in mVRD-SKP1 and mVRD-CUL1 culture after the addition of 500 nm rapamycin. The accompanying graph illustrates the changes in mVenus-FRB protein levels, quantified from biological triplicate immunoblotting. The signal intensity just before the rapamycin addition in each strain was set to 100%. The half-lives (t1/2) of mVenus-FRB in the mVRD-SKP1 and mVRD-CUL1 strains, as shown in the graph, were calculated using the quartic approximation equations in Microsoft Excel.\n\nFigure 5: Figure 5. Application of the rapamycin-inducible knockdown system for the chloroplast division protein DRP5B. A) The structures of mVenus-FL-FRB-DRP5B and HA-FKBP-SKP1 expressed in the DRP5BRD-SKP1. mVenus, 4×FLAG (FL), and FRB were fused to the amino-terminus of DRP5B for visualizing protein localization, immunological protein detection, and rapamycin-inducible interaction with HA-FKBP-SKP1, respectively. A GSGSG peptide linker was inserted between mVenus and FL. Additionally, a 6×G peptide linker was inserted between FRB and DRP5B. The structure of the HA-FKBP-SKP1 is shown in Fig. 3. B) Immunoblotting confirmed expression of mVenus-FL-FRB-DRP5B and HA-FKBP-SKP1 in the DRP5BRD-SKP1 knock-in strain. An anti-DRP5B antibody detected DRP5B protein in WT, while in DRP5BRD-SKP1 strain, only mVenus-FL-FRB-DRP5B protein was detected indicating that mVenus-FL-FRB-DRP5B was successfully integrated into the chromosomal DRP5B locus. The arrow indicates a nonspecific band. Anti-FLAG and anti-HA antibodies detected mVenus-FL-FRB-DRP5B and HA-FKBP-SKP1, respectively, in the DRP5BRD-SKP1 strain. The CBB-stained PVDF membrane is also shown as a loading control. The predicted molecular weights based on the amino acid sequence of DRP5B, mVenus-FL-FRB-DRP5B, and HA-FKBP-SKP1 are 106, 146, and 37 kDa, respectively. The values below the bands indicate the relative signal intensities of the DRP5B (DRP5B or mV-FL-FRB-DRP5B) protein. The signal intensity of DRP5B in WT was set to 100%. C) Rapamycin-induced degradation of mVenus-FL-FRB-DRP5B protein in the DRP5BRD-SKP1 strain. Cell cycle progression and accompanying chloroplast division were synchronized under the LD cycle. The white and black bars above the immunoblot represent light and dark periods, respectively. Immunoblotting using the anti-FLAG antibody shows the change in the level of mVenus-FL-FRB-DRP5B protein during the LD cycle. DMSO, as a negative control, or 500 nm rapamycin was added at Hour 9 (indicated by the red arrowhead), which corresponds to 3 h prior to the peak of mVenus-FL-FRB-DRP5B protein level in the culture without rapamycin. The change in α-tubulin (detected by the anti-α-tubulin antibody; expressed specifically during S and M phases in C. merolae; Fujiwara, Tanaka, et al. 2013) is also shown. The CBB-stained PVDF membrane is shown as a loading control. The values below the bands indicate the relative signal intensities of the mV-FL-FRB-DRP5B protein. The signal intensity at Hour 12 in the absence of rapamycin was set to 100%. D) DIC and fluorescent microscopy of the DRP5BRD-SKP1 cells. The images were aligned in the order of cell cycle progression (note that the images are not from an identical cell). The top panels represent the cell before, during, and after chloroplast division. The lower panels are merged images of the mVenus fluorescence of mVenus-FL-FRB-DRP5B and the autofluorescence from chloroplasts (Chl). As observed in WT cells (Miyagishima et al. 2003), mVenus-FL-FRB-DRP5B proteins localize at the chloroplast division site. As in WT cells, in DRP5BRD-SKP1 cells, the chloroplast division synchronously occurs between Hours 12 and 15 under the LD. The green structures within the cell are chloroplasts. The scale bar represents 2 µm in all images in D). E) The chloroplast division defect caused by the degradation of mVenus-FL-FRB-DRP5B. DIC and fluorescent images of DMSO- or rapamycin-treated DRP5BRD-SKP1 cells at Hours 12, 18, and 24 under LD are shown. In the DMSO-treated culture, cells with dividing chloroplast and the mVenus-FL-FRB-DRP5B signal at the division site accumulated at Hour 12, while most of the cells had completed chloroplast division at Hour 18. In contrast, in the rapamycin-treated culture, mVenus-FL-FRB-DRP5B was faintly detectable, and constriction of the chloroplast division site was not observed in any cells at Hour 12. At Hours 18 and 24, irregularly shaped cells with a single chloroplast accumulated. The scale bar represents 5 µm in the upper and middle images in E). The bottom panels show the phase-contrast (PC), DAPI-staining, and immunofluorescent images of the DRP5BRD-SKP1 cells. The bottom-left image represents a typical telophase cell in which chloroplast division and following mitochondrial division and chromosome segregation have been completed. The bottom-right image represents an irregularly shaped cell in which chloroplast division has been blocked, while mitochondrial division and chromosome segregation have been completed. n, nuclear DNA; mn, mitochondrial nucleoid DNA; cn, chloroplast nucleoid DNA. The scale bars represent 2 µm in the bottom images in E). F) A bar graph comparing the percentage of cells with an irregular shape, possessing a single chloroplast and 2 nuclei between the DMSO-treated and the rapamycin-treated cultures at Hour 18. DAPI-stained cells were counted (n > 300). The averages and Sd were calculated from biological triplicates."
      }
    ]
  },
  {
    "id": "PMC11387402_multi",
    "image": [
      "images/PMC11387402-f1.png",
      "images/PMC11387402-f2.png",
      "images/PMC11387402-f3.png",
      "images/PMC11387402-f4.png",
      "images/PMC11387402-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Lipidomic biomarkers in plasma correlate with disease severity in adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Lipidomics analysis of plasma samples from 92 male ALD patients and 12 healthy male controls. A Partial least squares discriminant analysis (PLS-DA) and principal component analysis (PCA) analysis. B Volcano plot of lipid levels. The vertical axis shows the p-value (−log10) from Welch’s t-tests between ALD and controls, and the horizontal axis shows the fold change (log2) between ALD and controls. Colored dots are lipids with a p-value < 0.05. C Box plots (whiskers are determined using Tukey) of elevated lipids in ALD compared to controls. D Trend lines showing log fold change (logFC) and total chain length of lysophosphatidylcholine (LPC), phosphatidylcholine (PC), and triglyceride (TG) lipids in ALD compared to controls. E Heatmap showing log fold change, total chain unsaturation, and chain length for LPC, PC, and TG. Welch’s t-test or Mann–Whitney U test was used to determine significant differences between groups (****P ≤ 0.0001).\n\nFigure 2: Figure 2. Lipidomics analysis of plasma samples from patients with cerebral ALD (CALD) (n = 24) and patients without CALD (noCALD) (all ages, n = 68). A Volcano plot of lipid levels. The vertical axis shows the p-value (−log10) from Welch’s t-tests between CALD (n = 24) and noCALD (all ages, n = 68), and the horizontal axis the fold change (log2) between CALD and noCALD (all ages). Colored dots are lipids with a p-value < 0.05. B Box plots (whiskers are determined using Tukey) of elevated lipid levels in CALD compared to noCALD (all ages), and noCALD >55 years (n = 21) are shown. Yellow dots on the graph represent patients who were sampled both before and after the onset of CALD (n = 3). C Trend lines showing log fold change (logFC) and total chain length of lysophosphatidylchloline (LPC), phosphatidylcholine (PC), and triglyceride (TG) lipids comparing patient groups with controls (CALD: red, noCALD all ages: blue, noCALD >55: green). D Heatmap showing the log fold change, total chain unsaturation, and chain length for LPC, PC, and TG when CALD is compared to noCALD (all ages). Welch’s t-test or Mann–Whitney U test was used to determine significant differences between groups (**P ≤ 0.01; ***P ≤ 0.001), (****P ≤ 0.0001).\n\nFigure 3: Figure 3. Lipidomics analysis of plasma samples from patients with adrenal insufficiency (AI) (n = 50) and patients without AI (NoAI) (all ages, n = 42). A Volcano plot of lipid levels. The vertical axis shows the p-value (−log10) from Welch’s t-tests between AI and NoAI, and the horizontal axis shows the fold change (log2) between AI and noAI (all ages). Colored dots are lipids with a p-value of <0.05. B Box plots (whiskers are determined using Tukey) of elevated lipid levels in AI compared to noAI (all ages), and noAI >55 years (n = 20) are shown. C Trend lines showing log fold change (logFC) and total chain length of LPC, PC, and TG lipids when comparing patient groups to controls (AI: red, noAI all ages: blue, noAI >55: green). D Heatmap showing log fold change, total chain unsaturation, and chain length for lysophosphatidylcholine (LPC), phosphatidylcholine (PC), and triglyceride (TG) when AI is compared to noAI (all ages). Welch’s t-test or Mann–Whitney U test was used to determine significant differences between groups (***P ≤ 0.001), (****P ≤ 0.0001).\n\nFigure 4: Figure 4. Lipidomics analysis of plasma samples from patients with mild (EDSS≤6) spinal cord disease aged >55 years (n = 17) and severe (EDSS>6) spinal cord disease (n = 15) patients. A Volcano plot of lipid levels. The vertical axis shows the p-value (−log10) from Welch’s t-tests between mild and severe patients, and the horizontal axis shows the fold change (log2) between mild and severe patients. Colored dots are lipids with a p-value of <0.05. B Box plots (whiskers are determined using Tukey) of elevated lipid levels in severe compared to mild are illustrated. C Trend lines showing log fold change (logFC) and total chain length of lysophosphatidylcholine (LPC), phosphatidylcholine (PC), and triglyceride (TG) lipids when comparing patient groups to controls (severe: red, mild: green). D Heatmap showing log fold change, total chain unsaturation, and chain length for LPC, PC, and TG when severe is compared to mild. Welch’s t-test or Mann–Whitney U test was used to determine significant differences between groups (*P ≤ 0.05).\n\nFigure 5: Figure 5. Lipidomics analysis of plasma samples from 65 female ALD patients and 12 healthy female controls. A Partial least squares discriminant analysis (PLS-DA) and principal component analysis (PCA) analysis. B Volcano plot of lipid levels. The vertical axis shows the p-value (−log10) from Welch’s t-tests between female ALD patients and controls, and the horizontal axis shows the fold change (log2) between female ALD patients and controls. Colored dots are lipids with a p-value < 0.05. C Box plots (whiskers are determined using Tukey) of lipids that are elevated in female ALD patients compared to controls and are associated with spinal cord disease severity. D Trend lines illustrating the log fold change (logFC) and total chain length of lysophosphatidylcholine (LPC), phosphatidylcholine (PC), and triglyceride (TG) lipids when patient groups are compared to controls (severe: red, mild: blue). E Heatmap showing the log fold change, total chain unsaturation, and chain length for LPC, PC, and TG when the severe group was compared to the mild group. F Linear correlation between plasma LPC(26:0) levels and the X-inactivation in female ALD patients (n = 28, Pearson correlation coefficient: 0.79). Orange dot represents the female patient with cerebral ALD. Welch’s t-test or Mann–Whitney U test was used to determine significant differences between groups (**P ≤ 0.01; ****P ≤ 0.0001)."
      }
    ]
  },
  {
    "id": "PMC11418141_multi",
    "image": [
      "images/PMC11418141-f1.png",
      "images/PMC11418141-f2.png",
      "images/PMC11418141-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Gene therapy for the leukodystrophies: From preclinical animal studies to clinical trials\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A classification system for leukodystrophies based on cellular mechanisms and pathophysiology, adapted from van der Knaap and Bugiani [2]. This is not a comprehensive list of the leukodystrophies.\n\nFigure 2: Figure 2. Molecular and cellular mechanisms disrupted by leukodystrophy pathophysiology in the setting of the brain tissue microenvironment. Abbreviations: 4H: Hypomyelination with hypogonadotropic hypogonadism and hypodontia or POL-III related disorders; X-ALD: X-linked adrenoleukodystrophy; GLD: Globoid cell leukodystrophy; MLD: Metachromatic leukodystrophy; TSD: Tay-Sachs disease; SD: Sandhoff disease; ADLD: Autosomal dominant leukodystrophy; CD: Canavan disease; ALSP: Adult-onset leukoencephalopathy with axonal spheroids and pigmented glia (CSF1R-related leukoencephalopathy); PMD: Pelizaeus-Merzbacher disease; AxD: Alexander disease; CADASIL: Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy.\n\nFigure 3: Figure 3. Depiction of the different modalities of gene-based therapies currently in use for leukodystrophy clinical trials, including ex vivo LV-mediated gene therapies (left panel), in vivo AAV-mediated gene therapies (middle panel), and antisense oligonucleotide therapies (right panel). Abbreviations: X-ALD: X-linked adrenoleukodystrophy, MLD: Metachromatic leukodystrophy, GLD: Globoid cell leukodystrophy, CD: Canavan disease, GAN: Giant axonal neuropathy; TSD: Tay-Sachs disease; SD: Sandhoff disease; PMD: Pelizaeus-Merzbacher disease."
      }
    ]
  },
  {
    "id": "PMC11434102_multi",
    "image": [
      "images/PMC11434102-f1.png",
      "images/PMC11434102-f2.png",
      "images/PMC11434102-f3.png",
      "images/PMC11434102-f4.png",
      "images/PMC11434102-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Uremic Toxin Receptor AhR Facilitates Renal Senescence and Fibrosis via Suppressing Mitochondrial Biogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. AhR was increased in the kidneys of IR‐ or IS‐treated mice. a) Schematic of IR mice preparation. b) Concentration of serum BUN, creatinine and IS in mice after IR surgery. *** P < 0.001 versus sham group (n = 6). c) Masson, SA‐β‐gal staining and immunohistochemistry of AhR micrographs in mouse kidneys after IR surgery. Scale bar, 50 µm. d) Western blot images and quantitative analysis of AhR in mouse kidneys after IR surgery. *** P < 0.001 versus sham group (n = 6). e) Schematic of IS‐treated mice preparation. f) Concentration of serum BUN, creatinine and IS in mice after IS treatment. ** P < 0.01 versus vehicle group. N.S., no significant difference versus vehicle group (n = 6). g) Masson, SA‐β‐gal staining and immunohistochemistry of AhR micrographs in mouse kidneys after IS treatment. Scale bar, 50 µm. h) Western blot images and quantitative analysis of AhR in mouse kidneys after IS treatment. ** P < 0.01 versus vehicle group (n = 6). i,j) Western bolt images and quantitative analysis of AhR in mouse tubular epithelial cells (mTECs) treated with the indicated concentrations of IS for prespecified durations. * P < 0.05, ** P < 0.01, *** P < 0.001 versus control (Con) group (n = 3). k) Co‐immunofluorescence of AhR and p21 in mouse kidneys after IR or IS treatment. Scale bar, 25 µm. Data were shown as mean ± SD. Statistical analysis was performed by two‐tailed unpaired Student's t‐test (the right panel of b, the left and middle panel of f, h), two‐tailed unpaired Welch’ t‐test (the left and middle panel of b, d, the right panel of f), and one‐way ANOVA with Tukey's multiple comparisons test (i, j).\n\nFigure 2: Figure 2. Renal tubular epithelial cell‐specific knockout of AhR mitigated the decline in renal function, senescence and fibrosis in IR mice. a) Serum BUN, creatinine and IS concentrations in mice from different groups. *** P < 0.001 versus Cre−AhRfl/fl +sham group, # P < 0.05, ## P < 0.01 versus Cre−AhRfl/fl +IR group (n = 5 or 6). b) HE, PAS, Masson, Sirius red and SA‐β‐gal staining micrographs of kidneys in mice from different groups. Scale bar, 50 µm. Evaluation of tubular injury score based on HE staining. Fibrotic area evaluation based on Masson staining. *** P < 0.001 versus Cre−AhRfl/fl +sham group, # P < 0.05 versus Cre−AhRfl/fl +IR group (n = 6). c) Western blot images and quantitative analysis of fibrosis markers FN and α‐SMA, and senescence markers p16INK4A and p21 in kidneys from different groups of mice. *** P < 0.001 versus Cre−AhRfl/fl +sham group, ## P < 0.01, ### P < 0.001 versus Cre−AhRfl/fl +IR group (n = 6). d) The relative mRNA abundance of fibrosis markers FN, Col I, and α‐SMA in kidneys from different groups of mice. *** P < 0.001 versus Cre−AhRfl/fl +sham group, ## P < 0.01 versus Cre−AhRfl/fl +IR group (n = 6). e) The relative mRNA abundance of senescence markers p16INK4A , p21, and secretory factors IL‐1β, TNF‐α, IL‐6, and TGFβ1 in kidneys from different groups of mice. *** P < 0.001 versus Cre−AhRfl/fl +sham group, # P < 0.05, ## P < 0.01, ### P < 0.001 versus Cre−AhRfl/fl +IR group (n = 6). Data were shown as mean ± SD. Statistical analysis was performed by two‐way ANOVA with Tukey's multiple comparisons test (a‐e).\n\nFigure 3: Figure 3. Renal tubular epithelial cell‐specific knockout of AhR mitigated the decline in renal function, senescence and fibrosis in IS‐treated mice. a) Serum BUN, creatinine and IS concentration in different groups of mice. *** P < 0.001 versus Cre−AhRfl/fl +vehicle group. N.S., no significant difference versus Cre−AhRfl/fl +vehicle group or Cre−AhRfl/fl +IS group (n = 5 or 6). b) HE, PAS, Masson, Sirius red and SA‐β‐gal staining micrographs of kidneys from different groups of mice. Scale bar, 50 µm. Evaluation of tubular injury score based on HE staining. Fibrotic area evaluation based on Masson staining. *** P < 0.001 versus Cre−AhRfl/fl +vehicle group, # P < 0.05 versus Cre−AhRfl/fl +IS group (n = 6). c) Western blot images and quantitative data showing FN, α‐SMA, p16INK4A, and p21 in kidneys from different groups of mice. *** P < 0.001 versus Cre−AhRfl/fl +vehicle group, # P < 0.05, ## P < 0.01, ### P < 0.001 versus Cre−AhRfl/fl +IS group (n = 6). d) qPCR showing the mRNA levels of p16INK4A , p21, IL‐1β, TNF‐α, IL‐6, and TGFβ1 in kidneys from different groups of mice. *** P < 0.001 versus Cre−AhRfl/fl +vehicle group, # P < 0.05, ## P < 0.01 versus Cre−AhRfl/fl +IS group (n = 5). Data were shown as mean ± SD. Statistical analysis was performed by two‐way ANOVA with Tukey's multiple comparisons test (a‐d).\n\nFigure 4: Figure 4. AhR promoted IS‐induced cell senescence and ECM production in mTECs or primary TECs. The mTECs were transfected with AhR siRNA (si‐AhR) for 12 h and then treated with IS (1000 µmol L−1) for an additional 36 h. a) Western blot images and quantitative data of FN, α‐SMA, p16INK4A, and p21 in mTECs. ** P < 0.01, *** P < 0.001 versus Con group, # P < 0.05, ## P < 0.01 versus IS group (n = 3). b) The relative mRNA abundance of p16INK4A , p21, IL‐1β, TNF‐α, IL‐6, and TGFβ1 in mTECs. * P < 0.05, ** P < 0.01 versus Con group, # P < 0.05 versus IS group (n = 3). c) The SA‐β‐gal staining micrographs and quantitative data showing mTEC senescence. Scale bar, 50 µm. ** P < 0.01 versus Con group, # P < 0.05 versus IS group (n = 3). Primary TECs isolated from Cre−AhRfl/fl mice (Cre− ) or Cre+AhRfl/fl mice (Cre+ ) were treated with IS (1000 µmol L−1) for 36 h. d) Western blot images and quantitative data of AhR, FN, α‐SMA, p16INK4A, and p21 in primary TECs. *** P < 0.001 versus Cre− +Con group, # P < 0.05, ## P < 0.01 versus Cre− +IS group (n = 3). e) The relative mRNA abundance of p16INK4A , p21, IL‐1β, TNF‐α, IL‐6, and TGFβ1 in primary TECs. ** P < 0.01, *** P < 0.001 versus Cre− +Con group, # P < 0.05 versus Cre− +IS group (n = 3). f) The SA‐β‐gal staining micrographs and quantitative data showing TEC senescence. Scale bar, 50 µm. *** P < 0.001 versus Cre− +Con group, # P < 0.05 versus Cre− +IS group (n = 3). The mTECs were treated with IS (1000 µmol L−1) or adenovirus harboring AhR gene (Ad‐AhR) for 36 h. g) Western blot images and quantitative analysis of FN, α‐SMA, p16INK4A, and p21 expressions in mTECs. * P < 0.05, ** P < 0.01 versus Ad‐Con group, # P < 0.05, ## P < 0.01 versus IS+Ad‐Con group (n = 3). h) The relative mRNA abundance of cell senescence markers p16INK4A and p21 as well as secretory factors IL‐1β, TNF‐α, IL‐6, and TGFβ1 in mTECs. * P < 0.05 versus Ad‐Con group, # P < 0.05, ## P < 0.01, ### P < 0.001 versus IS+Ad‐Con group (n = 3). Data were shown as mean ± SD. Statistical analysis was performed by one‐way ANOVA with Tukey's multiple comparisons test (a‐c) and two‐way ANOVA with Tukey's multiple comparisons test (d‐h).\n\nFigure 5: Figure 5. Renal tubular epithelial cell knockout of AhR blunted the suppression of mitochondrial biogenesis in the kidneys of IR‐ or IS‐treated mice. a) Western blot images and quantitative data of the protein levels of PGC1α, TFAM, and TOM20 in the kidneys of mice with or without IR surgery. *** P < 0.001 versus Cre−AhRfl/fl +sham group, # P < 0.05 versus Cre−AhRfl/fl +IR group (n = 6). b) The renal oxygen consumption rate (OCR) and mitochondrial DNA (mtDNA) copies of mice with or without IR surgery. *** P < 0.001 versus Cre−AhRfl/fl +sham group, # P < 0.05 versus Cre−AhRfl/fl +IR group (n = 6). c) qPCR showing the mRNA levels of 13 mtDNA in the kidneys of mice with or without IR surgery. * P < 0.05, ** P < 0.01, *** P < 0.001 versus Cre−AhRfl/fl +IR group (n = 6). d) Western blot images and quantitative data of the protein levels of PGC1α, TFAM and TOM20 in the kidneys of mice with or without IS treatment. *** P < 0.001 versus Cre−AhRfl/fl +vehicle group, # P < 0.05 versus Cre−AhRfl/fl +IS group (n = 6). e) Renal OCR and mtDNA of mice with or without IS treatment. *** P < 0.001 versus Cre−AhRfl/fl +vehicle group, # P < 0.05 versus Cre−AhRfl/fl +IS group (n = 6). f) qPCR showing the mRNA levels of 13 mtDNA in the kidneys of mice with or without IS treatment. * P < 0.05, ** P < 0.01, *** P < 0.001 versus Cre−AhRfl/fl +vehicle group, # P < 0.05 versus Cre−AhRfl/fl +IS group (n = 5). Data were shown as mean ± SD. Statistical analysis was performed by two‐tailed unpaired Student's t‐test (mt‐Nd1, mt‐Nd2, mt‐Nd4, mt‐Nd5, mt‐Co2, mt‐Co3, Atp6, Atp8, mt‐Cytb of c), two‐tailed unpaired Welch’ t‐test (mt‐Nd3, mt‐Nd4l, mt‐Nd6, mt‐Co1 of c), and two‐way ANOVA with Tukey's multiple comparisons test (a, b, d, e, f)."
      }
    ]
  },
  {
    "id": "PMC11434102_multi_2",
    "image": [
      "images/PMC11434102-f6.png",
      "images/PMC11434102-f7.png",
      "images/PMC11434102-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Uremic Toxin Receptor AhR Facilitates Renal Senescence and Fibrosis via Suppressing Mitochondrial Biogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. AhR promoted IS‐induced the suppression of mitochondrial biogenesis in mTECs or primary TECs. a) Western blot images and quantitative data of PGC1α, TFAM and TOM20 in mTECs. ** P < 0.01 versus Con group, # P < 0.05 versus IS group (n = 3). b) The measurement of OCR, mtDNA copies, and the ATP content in mTECs. ** P < 0.01 versus Con group, # P < 0.05 versus IS group (n = 3). c) Representative images of Mitotracker staining in mTECs. Scale bar, 10 µm. MiNa‐based quantification of the mitochondrial morphological parameters, including individual mitochondria, mitochondrial networks, and mitochondrial length. *** P < 0.001 versus Con group, # P < 0.05, ## P < 0.01, ### P < 0.001 versus IS group (n = 3). d) Western blot images and quantitative data of PGC1α, TFAM and TOM20 in primary TECs. ** P < 0.01 versus Cre− +Con group, # P < 0.05 versus Cre− +IS group (n = 3). e) The measurement of OCR, mtDNA copies and the ATP content in primary TECs. ** P < 0.01, *** P < 0.001 versus Cre− +Con group, # P < 0.05 versus Cre− +IS group (n = 3). f) Representative images of Mitotracker staining in primary TECs. Scale bar, 10 µm. MiNa‐based quantification of the mitochondrial morphological parameters, including individual mitochondria, mitochondrial networks, and mitochondrial length. *** P < 0.001 versus Cre− +Con group, # P < 0.05, ## P < 0.01 versus Cre− +IS group (n = 3). g) Western blot images and quantitative analysis of PGC1α, TFAM and TOM20 expressions in mTECs. * P < 0.05, ** P < 0.01 versus Ad‐Con group, # P < 0.05 versus IS+Ad‐Con group (n = 3). h) The measurement of OCR, mtDNA copies and the ATP content in mTECs. * P < 0.05, ** P < 0.01, *** P < 0.001 versus Ad‐Con group, # P < 0.05 versus IS+Ad‐Con group (n = 3). i) Representative images of Mitotracker staining in mTECs. Scale bar, 10 µm. MiNa‐based quantification of the mitochondrial morphological parameters, including individual mitochondria, mitochondrial networks, and mitochondrial length. *** P < 0.001 versus Ad‐Con group, # P < 0.05, ## P < 0.01, ### P < 0.001 versus IS+Ad‐Con group (n = 3). Data were shown as mean ± SD. Statistical analysis was performed by one‐way ANOVA with Tukey's multiple comparisons test (a‐c) and two‐way ANOVA with Tukey's multiple comparisons test (d‐i).\n\nFigure 7: Figure 7. Overexpression of PGC1α alleviated IS‐induced cell senescence and ECM production. The mTECs were treated with IS (1000 µmol L−1) or adenovirus harboring PGC1α gene (Ad‐PGC1α) for 36 h. a) Western blot images and quantitative analysis showing the expressions of PGC1α, TFAM and TOM20 in mTECs. * P < 0.05, ** P < 0.01 versus Con group, # P < 0.05, ### P < 0.001 versus IS group (n = 3). b) Western blot images and quantitative analysis showing the expressions of FN, α‐SMA, p16INK4A and p21 in mTECs. ** P < 0.01 versus Con group, # P < 0.05 versus IS group (n = 3). c) qPCR analysis of the relative mRNA levels of p16INK4A , p21, IL‐1β, TNF‐α, IL‐6, and TGFβ1 in mTECs. * P < 0.05, ** P < 0.01 versus Con group, # P < 0.05 versus IS group (n = 3). d) The SA‐β‐gal staining micrographs and quantitative analysis showing the mTEC senescence. Scale bar, 50 µm. *** P < 0.001 versus Con group, # P < 0.05 versus IS group (n = 3). Data were shown as mean ± SD. Statistical analysis was performed by one‐way ANOVA with Tukey's multiple comparisons test (a‐d).\n\nFigure 8: Figure 8. AhR promoted PGC1α degradation via ubiquitin modification. a) Immunofluorescence micrographs and Western blot presenting AhR distribution in mTECs after IS treatment (1000 µmol L−1) for 12 h, with or without transfection using adenovirus carrying AhR gene (Ad‐AhR) for 36 h. b) Western blot images and quantitative data detecting the PGC1α in mTECs with IS treatment (1000 µmol L−1) for 36 h. Cells were treated with cycloheximide (CHX, 10 µmol L−1) for the indicated durations before being harvested. * P < 0.05, ** P < 0.01 versus Con group (n = 3). c) Western blot images and quantitative data detecting the PGC1α in mTECs subjected to 36‐h IS treatment (1000 µmol L−1) in the presence of MG132 (20 µmol L−1) for 4 h. ** P < 0.01 versus Con group, # P < 0.05 versus IS group (n = 3). d) Co‐IP of AhR and PGC1α in mTECs cotransfected with Ad‐AhR and Ad‐PGC1α with IS stimulation (1000 µmol L−1) for 48 h. The lysates were immunoprecipitated with control IgG, anti‐AhR, or anti‐PGC1α antibodies, followed by Western blot with the indicated antibody (n = 3). e,f) IP analyzing the ubiquitination of PGC1α in mTECs. The cells were transfected with AhR siRNA (si‐AhR; e) or treated with AhR inhibitor CH‐223191 (10 µmol L−1; f) in the presence of IS (1000 µmol L−1) for 48 h. MG132 (20 µmol L−1) was added to the medium 4 h before cell harvest. The lysates were immunoprecipitated with anti‐PGC1α antibody, followed by Western blot with anti‐ubiquitin (Ub) antibody (n = 3). g) Schematic of full‐length and truncated AhR mutants. Western blot images and quantitative data detecting the PGC1α in mTECs. The cells were transfected with Myc‐tagged pcDNA, AhR full‐length (WT), 110–119 amino acid‐deletion mutant (Δα), or acidic domain‐deletion mutant (Δacid) vectors with IS stimulation (1000 µmol L−1) for 48 h. ** P < 0.01, N.S. (no significant difference) versus pcDNA group (n = 3). h) Co‐IP of AhR or mutants with PGC1α in HEK293T cells cotransfected with plasmids encoding Flag‐tagged PGC1α and Myc‐tagged AhR WT, AhR Δα or AhR Δacid with IS stimulation (1000 µmol L−1) for 48 h. The lysates were immunoprecipitated with anti‐Myc antibody, followed by Western blot with anti‐Flag antibody (n = 3). i) IP of AhR or mutants with PGC1α in HEK293T cells cotransfected with plasmids encoding Flag‐tagged PGC1α and Myc‐tagged AhR WT, AhR Δα or AhR Δacid in the presence of IS (1000 µmol L−1) for 48 h. MG132 (20 µmol L−1) was added to the medium 4 h before cell harvest. The lysates were immunoprecipitated with anti‐Flag antibody, followed by Western blot with anti‐Ub antibody (n = 3). j) IP analysis of PGC1α ubiquitination in mTECs transfected with cullin 4B siRNA (si‐cullin 4B) in the presence of IS (1000 µmol L−1) for 48 h. MG132 (20 µmol L−1) was added to the medium 4 h before cell harvest. The lysates were immunoprecipitated with anti‐PGC1α antibody, followed by Western blot with anti‐ubiquitin (Ub) antibody (n = 3). Data were shown as mean ± SD. Statistical analysis was performed by two‐way ANOVA with Tukey's multiple comparisons test (b, c, g)."
      }
    ]
  },
  {
    "id": "PMC11463487_multi",
    "image": [
      "images/PMC11463487-f1.png",
      "images/PMC11463487-f2.png",
      "images/PMC11463487-f3.png",
      "images/PMC11463487-f4.png",
      "images/PMC11463487-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Mitochondrial Ubiquitin Ligase MARCHF5 Cooperates with MCL1 to Inhibit Apoptosis in KSHV-Transformed Primary Effusion Lymphoma Cell Lines\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A-B. Top co- and anti-dependencies of A. MCL1 or B. MARCHF5 from the Cancer Dependency Map 23Q4. The top 100 genes are listed in Table S1. C. Median fold changes of gRNAs targeting MCL1 or MARCHF5 in our gene essentiality CRISPR screens in PEL cell lines [15]. D. Western blots of MARCHF5 in a panel of PEL cell lines that are infected with KSHV only or co-infected by KSHV and EBV.\n\nFigure 2: Figure 2. A. Cumulative live cell counts (relative to control gAAVS1) of BC-3 Cas9 or BCBL-1 iCas9 cells expressing gRNAs targeting MARCHF5 or AAVS1. B. Western blots of MARCHF5 from cells in panel A. Statistical differences were calculated using two-way ANOVA with Tukey’s multiple comparison post-hoc test (n=3). Adjusted p values reflect post-hoc comparisons between gAAVS1 to either MARCHF5 gRNA at the specific time point. Error bars, standard error of the mean.\n\nFigure 3: Figure 3. A. Western blots of MARCHF5 or FLAG in BCBL-1 iCas9 cells expressing gRNAs targeting MARCHF5 or AAVS1 and MARCHF5 cDNAs. B. Cumulative live cell counts (relative to control gAAVS1) of BCBL-1 iCas9 cells in panel A after the addition of Dox. Statistical differences were calculated using two-way ANOVA with Tukey’s multiple comparison post-hoc test (n=6–8). Adjusted p values reflect post-hoc comparisons between gAAVS1 to either MARCHF5 gRNA at the specific time point. Error bars, standard error of the mean.\n\nFigure 4: Figure 4. A. Apoptotic activity measured by Caspase-Glo 3/7 Assay or B. Annexin V-7AAD staining of cells from Fig. 3. Statistical differences were calculated using one-way ANOVA with Tukey’s multiple comparison post-hoc test (n=3–5). Adjusted p values reflect post-hoc comparisons between gAAVS1 to either MARCHF5 gRNA. Error bars, standard error of the mean.\n\nFigure 5: Figure 5. Western blots of lytic proteins and MAVS signaling pathway in wildtype or MARCHF5 KO BC-3 Cas9 or BCBL-1 iCas9 cells."
      }
    ]
  },
  {
    "id": "PMC11463487_multi_2",
    "image": [
      "images/PMC11463487-f6.png",
      "images/PMC11463487-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The Mitochondrial Ubiquitin Ligase MARCHF5 Cooperates with MCL1 to Inhibit Apoptosis in KSHV-Transformed Primary Effusion Lymphoma Cell Lines\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A. mRNA expression of BH3-only proteins in PEL cell lines from Cell Model Passports. B. Western blots of BH3-only proteins that were targeted for Cas9 KO in BC-3 cells. C. Experimental flow chart of the Fitness Competition Assay. BC-3 Cas9 cells were transduced with a lentivirus encoding the control gAAVS1 and an iRFP670 fluorescent protein or a second lentivirus encoding the targeting gRNA and an eGFP reporter. Equal amounts of control iRFP670 cells were mixed with targeted eGFP cells at the beginning of the growth curve. Fitness indices as reflected by the ratio of eGFP to iRFP670 (eGFP:iRFP670) were measured over 15 days by flow cytometry. D. Fitness indices for each BH3-only KO competition relative to day 0. Statistical differences were calculated using two-way ANOVA with Dunnett’s multiple comparison post-hoc test (n=3). Adjusted p values reflect post-hoc comparisons between gSAFE4501 to BH3-only protein gRNA. Error bars, standard error of the mean.\n\nFigure 7: Figure 7. A. Western blots of PEL cell lines were treated with 1.25 μM MG132 for 4 hours. B. Western blot for MCL1 and NOXA in wildtype or MARCHF5 KO BC-3 Cas9. These protein lysates are the same ones used in Fig. 2 and thus use the same loading control. C. Reciprocal co-immunoprecipitation (co-IP) of the endogenous MARCHF5-NOXA complex in BC-3 cells."
      }
    ]
  },
  {
    "id": "PMC11463529_multi",
    "image": [
      "images/PMC11463529-f1.png",
      "images/PMC11463529-f2.png",
      "images/PMC11463529-f3.png",
      "images/PMC11463529-f4.png",
      "images/PMC11463529-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The p97-UBXD8 complex maintains peroxisome abundance by suppressing pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A. Volcano plot of the (−log10-transformed P value versus the log2-transformed ratio of wildtype/UBXD8 KO) proteins identified from HeLa cells. n = 3 biologically independent samples for each genotype. P values were determined by empirical Bayesian statistical methods (two-tailed t test adjusted for multiple comparisons using Benjamini-Hochberg’s correction method) using the LIMMA R package; for parameters, individual P values and q values, see Supplementary Dataset. Peroxisomal proteins important for biogenesis (dark blue) and metabolism (red) are highlighted. This dataset has been previously published in (Ganji et al., 2023) and is reanalyzed here. B. Schematic of tandem mass tag (TMT) proteomic hits in distinct peroxisomal pathways. C. Peroxisomal proteins identifies in (A) show reduced expression in UBXD8 KO compared to wildtype HeLa and Hek293T cells. D. Quantification of (C). **** : P<0.0001, N=3, Unpaired T-test.\n\nFigure 2: Figure 2. A. HeLa wildtype and UBXD8 KO cells stained for peroxisomes using peroxisomal matrix marker catalase B. Quantification of average peroxisome per cell and average peroxisome size from (A). At least 100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals **** : P<0.0001, N=3, Unpaired T-test. C. Peroxisome abundance in wildtype and UBXD8 KO cells that have either no peroxisomes or less then 10 peroxisomes per cell. D. Rescue of peroxisome number in UBXD8 KO cells transfected with either UBXD8-HA, UBXD8-UBA*-HA, UBXD8-ΔUAS-HA or UBXD8-UBX*-HA. Cells were stained for peroxisomes using peroxisomal matrix marker catalase. E. Quantification of average peroxisome per cell from HeLa wildtype and UBXD8 KO cells as well as UBXD8 KO cells transfected with either UBXD8-HA, UBXD8-UBA*-HA, UBXD8-ΔUAS-HA or UBXD8-UBX*-HA (D). Peroxisome numbers were quantified in cells expressing HA-tagged UBXD8 constructs only. At least 100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals **, **** : P<0.05, 0.0001. Two-way ANOVA with Tukey’s multiple comparisons test. F. Immunoblots of constructs transfected. Scale bar is 10μM.\n\nFigure 3: Figure 3. A. Hela cells were transfected with siRNAs to HRD1, and cells were stained for catalase (see also Supplementary Figure 3). Quantification of number of peroxisomes per cell, at least 100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. ns: not significant, **** : P<0.0001. One-way ANOVA with Dunnett’s multiple comparisons test. B. Quantification of peroxisome per cell in HEK293T wildtype and GP78 KO cells. At least 100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. **** : P<0.0001. Unpaired T-test. C. HeLa wildtype and UBXD2 KO cells stained for peroxisomes using catalase. D. Quantification of peroxisome per cell from (C). At least 100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. NS: not significant. Unpaired T-test. E. Immunoblots of Hela wildtype (untreated or treated with DTT) and UBXD8 KO for ER stress markers BiP and ATF4. N=3, F. rt-qPCR of xbp1 total and xbp1 spliced (xbp1s) mRNA transcripts in wildtype and UBXD8 KO cells treated with 1.5 mM DTT for 4 hours. N=3. NS: Not significant, *, **** : P < 0.01, 0.0001. Two-way ANOVA with Dunnett’s post-hoc analysis. Scale bar is 10μM.\n\nFigure 4: Figure 4. A. Volcano plot of the total cholesterol esters and triacylglycerol species identified using lipidomics of whole cell extracts of HEK-293T cells (−log10-transformed P value versus the log2-transformed ratio of UBXD8 KO: wildtype). VLCFA species indicated for CE (orange) and TG (dark blue). This dataset has been previously published in (Ganji et al., 2023) and is reanalyzed here. B. VLCFA species indicated for phosphatidylserine (PS) (green), phosphatidylethanolamine (PE) (red) and phosphatidylcholine (PC) (violet). Lipids were measured by LC-MS/MS following normalization by total protein amount. (n ≥ 3 biologically independent experiments were performed, each with duplicate samples). This dataset has been previously published in (Ganji et al., 2023) and is reanalyzed here. C. Immunoblots of catalase levels in whole cell lysates of HeLa wildtype and UBXD8 KO cells. D. Quantification of catalase levels in (C). N=3 independent experiments. NS: not significant. Unpaired T-test. E. Catalase activity was quantified using a commercial kit. N=3 independent experiments. ** : P<0.0001, Unpaired T-Test.\n\nFigure 5: Figure 5. A. GFP-UBXD8 and RFP-SKL were transiently transfected into COS-7 or HeLa cells and stained with BODIPY (665/676) to label lipid droplets. B. HeLa cells were transfected with FLAG-tagged wildtype UBXD8 or UBXD8 domain deletions (UBA, UAS and UBX) (in green) and RFP-SKL (in red). C. Quantification of (B) showing number of peroxisomes with UBXD8 localization. 15–20 cells were analyzed in N=3 independent experiments. Scatter plot shows mean and std.dev. ns: not significant, ** : P<0.001. One-way ANOVA with Dunnett’s multiple comparisons test. Scale bar is 5μM."
      }
    ]
  },
  {
    "id": "PMC11463529_multi_2",
    "image": [
      "images/PMC11463529-f6.png",
      "images/PMC11463529-f7.png",
      "images/PMC11463529-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The p97-UBXD8 complex maintains peroxisome abundance by suppressing pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A. Schematic for pexophagy flux reporter. B. Representative images of wildtype and UBXD8 KO cells transfected with GFP-Cherry-PEX26. C. Wildtype and UBXD8 KO cells were transfected with the flux reporter and treated with 150 nM Torin1 for 18 hours. Quantification showing the ratio of GFP: (GFP+mCherry+) in Hela wildtype and UBXD8 KO cells. 50–100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. **, ***, **** : P<0.01, 0.001, 0.0001. Two-way ANOVA with Šidáks multiple comparisons test. D. Representative images of HeLa control or p97 siRNAs and GFP-Cherry-PEX26. E. Quantification showing the ratio of GFP: (GFP+mCherry+) in Hela control, or p97 depleted cells. 50–100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. *, **, **** : P<0.05, 0.001, 0.0001. Two-way ANOVA with Tukey’s multiple comparisons test. F. Immunoblot showing p97. Scale bar is 10 μM.\n\nFigure 7: Figure 7. A. Representative images of HeLa cells transfected with control and UBXD8 or ATG5 siRNAs and stained for catalase. B. Quantification of peroxisomes per cell from (A). 50–100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. **** = P<0.0001. Two-way ANOVA with Dunnett’s multiple comparisons test. C. Immunoblot of UBXD8 and ATG5. D. Representative images of HeLa cells (wildtype and UBXD8 KO) transfected with GFP-USP30. Cells were stained for catalase. E. Quantification of peroxisomes per cell in GFP-USP30 transfected cells. 50–100 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. ***, **** = P< 0.001, 0.0001. Two-way ANOVA with Dunnett’s multiple comparisons test N=3, 2-way ANOVA. F. Immunoblot of GFP-USP30 expression. G. Wildtype and UBXD8 KO HeLa cells were stained with NBR1 and catalase. H. Mander’s colocalization of images in (G). 100–120 cells were analyzed in N=3 independent experiments. Violin plot shows median and 95% confidence intervals. **** :P< 0.0001. Students unpaired T-test. F. Immunoblot of GFP-USP30 expression. Scale bar is 10 μM (A and D) and 5 μM (G).\n\nFigure 8: Figure 8. A. HEK293T cells were treated with 150 nM Torin or 50 nM bafilomycin A (BafA) for 24 hours and then with 100 μg/ml cycloheximide for the indicated time points to stop translation. Immunoblots showing PMP70 half-life. B. Quantification of PMP70 levels normalized to GAPDH from (A). N=3 independent experiments. **, *** : P< 0.01, 0.001. Two-way ANOVA with Tukey’s multiple comparisons test. C. HEK293T cells were transfected with HA-ubiquitin and treated with 150 nM Torin-1 in the presence or absence of 5 μM Bortezomib (Btz) or 50 nM BafA for 24 hours. Cells were lysed in SDS, and denaturing HA immunoprecipitations were performed. Immunoblots of indicated proteins showing increased ubiquitylation of PMP70 in cells treated with Btz or BafA. N=3 independent experiments. D. HEK293T cells were transfected with HA-ubiquitin and siRNAs to control, UBXD8 or p97. Cells were treated with 150 nM Torin-1 for 24 hours. Cells were lysed in SDS, and denaturing HA immunoprecipitations were performed. Immunoblots of indicated proteins showing increased ubiquitylation of PMP70 in cells depleted of UBXD8 and p97. N=3 independent experiments. E. Model showing p97-UBXD8 suppression of pexophagy."
      }
    ]
  },
  {
    "id": "PMC11463635_multi",
    "image": [
      "images/PMC11463635-f1.png",
      "images/PMC11463635-f2.png",
      "images/PMC11463635-f3.png",
      "images/PMC11463635-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Discovery of electrophilic degraders that exploit SNAr chemistry\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A. Structures of electrophilic BRD4 degrader ZZ7-16-073 and negative controls with slight chemical modifications that negate SNAr reactivity. B. HiBiT-BRD4 results for Jurkat cells treated with the indicated compounds for 6 hours. C. Quantitative proteome-wide mass spectrometry in MOLT-4 cells after 3 hours treatment with 10 pM ZZ7-16-073. D. Structure-activity relationships (SAR) of electrophilic BRD4 degraders with an SNAr covalent warhead.\n\nFigure 2: Figure 2. A. HiBiT-BRD4 results for Jurkat cells treated with the indicated inhibitors for 1 hour and then ZZ7-16-073 for 6 hours. B. Ubiquitin-proteasome system (UPS)-focused CRISPR degradation screen for BRD4BD1-eGFP and BRD4BD2-eGFP stability in K562-Cas9 cells treated with 500 nM ZZ7-16-073 for 16 hours. C. HiBiT-BRD4 results for DCAF16-KO Jurkat cells treated with the indicated compounds for 6 hours. D. Co-immunoprecipitation of FLAG-tagged BRD4 and HA-tagged DCAF16 in the presence of the indicated compounds. E. NanoBRET assay suggesting the induced interaction between HaloTag-DCAF16 and Nanoluciferase-BRD4 fusion proteins with the indicated compounds. F. Western blots of BRD4 degradation in WT or DCAF16-KO and mutants K562 cells treated with 100 pM ZZ7-16-073 for 6 hours.\n\nFigure 3: Figure 3. A. Structures of electrophilic BRD4 degrader ZZ7-16-078, ZZ7-17-033, and negative controls of ZZ7-17-033 with slight chemical modifications that negate SNAr reactivity. B. HiBiT results for Jurkat cells treated with the indicated compounds for 6 hours. C. HiBiT-BRD4 results for Jurkat cells treated with the indicated inhibitors for 1 hours and then ZZ7-17-033 for 6 hours. D. Quantitative proteome-wide mass spectrometry in MOLT-4 cells after 3 hours treatment with 100 nM ZZ7-17-033. E. Ubiquitin-proteasome system (UPS)-focused CRISPR degradation screen for BRD4BD1-eGFP or BRD4BD2-eGFP stability in K562-Cas9 cells treated with 1 μM ZZ7-17-033 for 16 hours. F. HiBiT-BRD4 results for WT, DCAF11-KO, or DCAF1-KO Jurkat cells treated with ZZ7-17-033 for 6 hours.\n\nFigure 4: Figure 4. A. Structures of electrophilic promiscuous kinase degraders ZZ7-18-043, ZZ7-18-045, and a negative control of ZZ7-18-045 with slight chemical modification that negate SNAr reactivity. B. Western blots of kinases degradations in MOLT-4 cells treated for 3 hours with 1 μM indicated compounds. C. Quantitative proteome-wide mass spectrometry in MOLT-4 cells after 3 hours treatment with 1 μM ZZ7-18-045. D. Western blots of LIMK2, Aurora A, and Aurora B degradations in Jurkat cells treated with the indicated inhibitors for 1 hour and then ZZ7-18-045 for 3 hours. E. Structures of electrophilic CDK4/6 degrader ZZ7-18-084 and negative controls with slight chemical modifications that negate SNAr reactivity. F. Western blots of CDK4 and CDK6 degradations in Jurkat cells treated with 1 μM indicated compounds for 6 hours. G. Quantitative proteome-wide mass spectrometry in MOLT-4 after 3 hours treatment with 1 μM ZZ7-18-084. H. Western blots of CDK4 and CDK6 degradations in Jurkat cells treated with the indicated inhibitors for 1 hour and then ZZ7-18-084 for 6 hours."
      }
    ]
  },
  {
    "id": "PMC11466755_multi",
    "image": [
      "images/PMC11466755-f1.png",
      "images/PMC11466755-f2.png",
      "images/PMC11466755-f3.png",
      "images/PMC11466755-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A case of adrenomyeloneuropathy caused by a novel point mutation in the ABCD1 gene and functional verification\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The patient exhibited black skin and pigmentation of the areola and navel.\n\nFigure 2: Figure 2. Whole-exome sequencing of the proband and his parents.\n\nFigure 3: Figure 3. Amino acid conservation analysis (red box): the 419Val locus is highly conserved in different species.\n\nFigure 4: Figure 4. (A) The result of protein relative expression; (B) The result of mRNA relative expression (The control group is cells without plasmid, and the NC group is cells without empty plasmid carrying the target sequence.)."
      }
    ]
  },
  {
    "id": "PMC11476013_multi",
    "image": [
      "images/PMC11476013-f1.png",
      "images/PMC11476013-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Role and Function of Peroxisomes in Neuroinflammation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomal functions. Peroxisomes degrade very-long-chain fatty acids (VLCFAs; C ≥ 22) by β-oxidation using acyl-CoA oxidase 1/2/3 (ACOX1/2/3) and multifunctional protein 2 (MFP2)/D-bifunctional protein (DBP). Peroxisomal β-oxidation also degrades the following inflammatory lipid metabolites: prostaglandins (PGs), leukotrienes (LTs), thromboxanes (TXs), and prostacyclin (PC). It is also required for the synthesis of docosahexaenoic acid (DHA) and eicosapentaenoic acid (EPA). Peroxisomes initiate ether-PL synthesis. The peroxisomal enzymes glyceronephosphate O-acyltransferase (GNPAT) and alkylglycerone phosphate synthase (AGPS) synthesize the ether-PL precursor 1-O-alkyl glycerol (OAG) from dihydroxyacetone phosphate (DHAP). Peroxisomes also maintain the cellular ROS level. The peroxisomal enzyme catalase decomposes hydrogen peroxides. This figure was created with Biorender.com.\n\nFigure 2: Figure 2. Peroxisomal impairment triggers inflammatory responses. An impairment to peroxisomal β-oxidation and ROS metabolism causes macrophage activation, the stimulation of the NFκB pathway, and phagocytosis defects. CD8+ T-cell infiltration in the CNS is associated with impaired peroxisomal ROS metabolism. Disruption in peroxisomal ether-PL synthesis activates the microglia, inducing inflammatory cytokine expression and TLR4 endocytosis. This figure was created with Biorender.com."
      }
    ]
  },
  {
    "id": "PMC11478612_multi",
    "image": [
      "images/PMC11478612-f1.png",
      "images/PMC11478612-f2.png",
      "images/PMC11478612-f3.png",
      "images/PMC11478612-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Nutritional Counseling and Mediterranean Diet in Adrenoleukodystrophy: A Real-Life Experience\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Distribution of C26:0 plasma levels (A), C26:0/C22:0 ratio (B) and triglycerides (C) at time T1 in adult patients compliant to nutritional treatment as compared to non-compliant patients. Figure 1B presents an outlier.\n\nFigure 2: Figure 2. Distribution of C26:0 plasma levels (A), C26:0/C22:0 ratio (B) and cholesterol (C) in adult patients compliant to nutritional treatment, comparing T0 vs. T1. Figure 2B presents an outlier.\n\nFigure 3: Figure 3. Distribution of C26:0/C22:0 ratio at time T1 in carriers compliant to nutritional treatment as compared to non-compliant carriers. The figure presents outliers.\n\nFigure 4: Figure 4. Distribution of C26:0/C22:0 ratio (A) and C24:0/C22:0 ratio (B) in carriers compliant to nutritional treatment, comparing T0 vs. T1. Both the figures present outliers."
      }
    ]
  },
  {
    "id": "PMC11540758_multi",
    "image": [
      "images/PMC11540758-f1.png",
      "images/PMC11540758-f2.png",
      "images/PMC11540758-f3.png",
      "images/PMC11540758-f4.png",
      "images/PMC11540758-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Accumulation of dually targeted StGPT1 in chloroplasts mediated by StRFP1, an E3 ubiquitin ligase, enhances plant immunity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. StRFP1 interacts with StGPT1 in yeast and in planta. A Yeast cells were plated on YPDA medium with X-gal, SD/-Leu-Trp (DDO), SD/-Leu-Trp-His (TDO), and SD/-Leu-Trp-His-Ade (QDO). B Total proteins were extracted, followed by IP with GFP-trap beads. GFP-EV and flag-mCherry were used as negative controls. IB, immunoblotting. + indicates expression of constructs in N. benthamiana leaves. Protein size given in kilodalton (kDa), protein loading indicated by Ponceau stain (PS) of Rubisco large subunit. * indicates target protein band. C Luciferase complementation assay (LCA) confirming interaction of StRFP1 and StGPT1. The same leaf was agro-infiltrated with different construct combinations. The fluorescence signal was observed and imaged 48 hours after agro-infiltration. EV, empty vector.\n\nFigure 2: Figure 2. StGPT1 localizes to chloroplast and ER. A Schematic of StGPT1, which contains two domains, cTP and GPT. The GPT domain includes ten TM motifs. B Confocal images showing StGPT1-GFP localized to chloroplast and ER. Amplified image (right) shows StGPT1-GFP co-localized with chloroplast. C Confocal images showing StGPT1-GFP localized to chloroplast. D Confocal images showing StGPT1-GFP localized to chloroplast and ER in same cells. ‘Merged’ one includes the bright field image. E Co-expression of StGPT1-GFP with an ER marker (mCherry-HDEL). Constructs were agro-infiltrated in N. benthamiana leaves. In B-E, each image represents one section confocal image.\n\nFigure 3: Figure 3. StGPT1 positively regulates P. infestans resistance. A Representative image showing disease lesion diameters on overexpression transgenic StGPT1 N. benthamiana lines at 5 days postinoculation (dpi) with P. infestans isolate 88069, wild-type N. benthamiana as negative control. One-way ANOVA was used for statistics analysis (**** p < 0.0001, three independent repeats, n = 64). B Silencing NbGPT1 reduces late blight resistance in N. benthamiana (**** p < 0.0001, three independent repeats, t-test, n = 100). C Representative images showing disease lesion diameters on potato OE- and Ri- lines of StGPT1 at 5 dpi by isolate HB0914-2, wild-type as a negative control. Statistics of disease lesion diameters. One-way ANOVA was used for statistical analysis (*** p < 0.001, three independent repeats, n = 33). Error bars indicate ± SE.\n\nFigure 4: Figure 4. Overexpression of StGPT1 enhances plant immune response. A-B flg22-induced ROS production in StGPT1-OE and StGPT1-RNAi transgenic potato lines, respectively. Leaves were treated with 10 μM flg22 before measuring ROS production. RULs, relative luminescence units. C-D JA or SA content in leaves of StGPT1 transgenic potato lines (** p < 0.01, *** p < 0.001; three to four biological repeats). E-H Relative expression of PTI marker genes StWRKY7, StWRKY8, StACRE31, and StPti5, respectively, in StGPT1 transgenic potato lines (* p < 0.1, ** p < 0.01, *** p < 0.001, **** p < 0.0001, three biological repeats). Error bars indicate ± SE.\n\nFigure 5: Figure 5. Positive regulation of StGPT1 in late blight resistance relies on its chloroplast localization. A Schematic of StGPT1 mutants. B Localization of GFP labeled StGPT1 mutants: one optical section (left), 10 optical sections (right). GFP fluorescence indicates mutants, pink indicates spontaneous chloroplast fluorescence, red indicates mCherry-HDEL (ER maker). C Representative images showing diameters of disease lesions on N. benthamiana leaves at 5 dpi with P. infestans isolate 88069 (** p < 0.01, *** p < 0.001, three independent repeats). One-way ANOVA was used for statistical analysis of GFP-StGPT1, n = 43. t - test was used for statistical analysis of StGPT1ΔcTP-GFP and StGPT1ΔcTP-L-GFP, n = 58 and 56, respectively. D Representative images showing diameters of disease lesions on transgenic GFP-StGPT1 potato leaves at 5 dpi with P. infestans isolate HB0914-2, wild-type as negative control. One-way ANOVA was used for statistical analysis (** p < 0.01, three independent repeats, n = 33). E flg22-induced ROS production in GFP-StGPT1 transgenic potato lines. Leaves were treated with 10 μM flg22 before measurement. RULs, relative luminescence units. EV, empty vector."
      }
    ]
  },
  {
    "id": "PMC11540758_multi_2",
    "image": [
      "images/PMC11540758-f6.png",
      "images/PMC11540758-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Accumulation of dually targeted StGPT1 in chloroplasts mediated by StRFP1, an E3 ubiquitin ligase, enhances plant immunity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. StRFP1 and StGPT1 co-localize on ER and synergically enhance P. infestans resistance. A StGPT1 co-localized with StRFP1 mainly on ER (the bright circle is the center represents the peri-nuclear ER). Bar is 20 μm. B Plots of profiles indicated by arrows (right image) show fluorescence intensity of StGPT1 (green line) and StRFP1 (red line). C Representative image showing diameters of disease lesions on N. benthamiana leaves at 5 dpi with P. infestans isolate 88069. D Plot graph showing differences in lesion diameters. One-way ANOVA was used for statistical analysis, *** p < 0.001, three independent repeats, n = 60. Error bars indicate ± SE. EV, empty vector.\n\nFigure 7: Figure 7. StRFP1 ubiquitinates StGPT1 and promotes it mature chloroplast form accumulation. A Western blot shows that the mature form of StGPT1 accumulated and ubiquitination level increased in the presence of StRFP1. Expression of constructs is indicated by +. Protein size is given in kilodalton (kDa). GFP beads trapped proteins from StGPT1 transgenic N. benthamiana leaves in which StRFP1- or flag-mCherry was transiently expressed. B Relative StGPT1 protein levels in leaves of three StGPT1-GFP transgenic N. benthamiana lines upon transient expression of StRFP1- or flag-mCherry. The StGPT1 protein level was normalized to actin. Data were collected from A and Figure S10. C Co-IP assay shows that StRFP1 or StRFP1H124A interacts with StGPT1. Total proteins were extracted, followed by IP with GFP-trap beads. Flag-mCherry was used as negative control. + indicates expression of constructs in N. benthamiana leaves. Protein size given in kilodalton (kDa), protein loading indicated by Ponceau stain (PS) of Rubisco large subunit. Red arrow indicates mature StGPT1-GFP band."
      }
    ]
  },
  {
    "id": "PMC11550353_multi",
    "image": [
      "images/PMC11550353-f1.png",
      "images/PMC11550353-f2.png",
      "images/PMC11550353-f3.png",
      "images/PMC11550353-f4.png",
      "images/PMC11550353-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"An in vitro and in vivo efficacy evaluation of gene therapy candidate SBT101 in mouse models of adrenomyeloneuropathy and in NHPs\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Increased hABCD1 expression and VLCFA reduction in mixed glial cell cultures following SBT101 administration Human ABCD1 expression (A) and VLCFA levels (B) in mixed glial cell cultures (from Abcd1-Null and WT mice) exposed to SBT101. ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.0001. Data represent mean ±95% confidence interval.\n\nFigure 2: Figure 2. Increased levels of hABCD1 and mtDNA, and reduced VLCFA levels, in Abcd1−/y mice 8 weeks after SBT101 administration Viral genomes copy number (A), hABCD1 expression (B), VLCFA levels (C), and mtDNA levels (D) within the spinal cord of Abcd1−/y mice assessed at 8 weeks after SBT101 administration. ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.0001. Data represent mean ± 95% confidence interval.\n\nFigure 3: Figure 3. Increased levels of hABCD1 and mtDNA, and reduced VLCFA levels in Abcd1−/y mice at 13 and 24 weeks after SBT101 administration Viral genomes copy number (A and E), hABCD1 expression (B and F), VLCFA levels (C and G), and mtDNA levels (D and H) within the spinal cord of Abcd1−/y mice assessed at 13 weeks (A–D) and 24 weeks (E–H) after SBT101 administration. ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.0001. Data represent mean ± 95% confidence interval.\n\nFigure 4: Figure 4. Biochemical improvements following SBT101 administration in Abcd1−/y/Abcd2−/− DKO mice Viral genome distribution (A) and hABCD1 mRNA expression (B) in the spinal cord of Abcd1−/y/Abcd2−/− DKO mice at 18 months of age (approximately 11 months after SBT101 administration). VLCFA levels (C) and inflammatory cytokine TNF-α levels (D) in the lumbar spinal cord of Abcd1−/y/Abcd2−/− DKO mice at 18 months of age. ∗p < 0.05, ∗∗p < 0.01. Data represent mean ± 95% confidence interval.\n\nFigure 5: Figure 5. Improved grip strength in Abcd1−/y/Abcd2−/− DKO mice after SBT101 administration Four-paw grip strength in Abcd1−/y/Abcd2−/− DKO mice at 15 months of age. ∗p < 0.05. Data represent mean ± 95% confidence interval."
      }
    ]
  },
  {
    "id": "PMC11550353_multi_2",
    "image": [
      "images/PMC11550353-f6.png",
      "images/PMC11550353-f7.png",
      "images/PMC11550353-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"An in vitro and in vivo efficacy evaluation of gene therapy candidate SBT101 in mouse models of adrenomyeloneuropathy and in NHPs\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Vector genome biodistribution in the spinal cord and DRG according to delivery method in NHP study 1 Vector genome biodistribution in the spinal cord and DRG was assessed via ddPCR quantification of GFP copies (A) and via immunohistochemical quantification of neuron positivity (B). Plotted values represent mean ± 95% confidence interval. n = 3 NHPs per treatment group, and A1–A3 represent individual NHPs. Percentage neuron positivity is presented as grades 1–5: grade 1, <1%; grade 2, 1%–25%; grade 3, 26%–50%; grade 4, 51%–75%; grade 5, 76%–100%; blanks, unremarkable (no observable GFP immunoreactivity). C2, cervical section 2; ddPCR, droplet digital PCR; DRG, dorsal root ganglia; GFP, green fluorescent protein; HPRT1, hypoxanthine-guanine phosphoribosyltransferase 1; IT-C, intrathecal cervical; IT-L, intrathecal lumbar; L5, lumbar section 5; T5, thoracic section 5; vg/an, vector genomes/animal.\n\nFigure 7: Figure 7. Vector genome biodistribution and hABCD1 mRNA expression Vector genome biodistribution (A, C, and E) and hABCD1 mRNA expression (B, D, and F) in NHP target tissues at 1 month (A and B), 3 months (C and D), and 6 months (E and F) post SBT101 administration in NHP study 4. Data represent mean ± 95% confidence interval. Vector genome copies and hABCD1 mRNA expression were below the limit of detection (LOD) for almost all controls (n = 3; data not plotted). Control NHPs received vehicle control (poloxamer [Kolliphor P188], potassium chloride, potassium dihydrogen phosphate dibasic in sterile water). aOne NHP did not have a calculated measurement. bOne NHP had a measurement below the limit of quantification. cOne NHP had a measurement below the LOD. Vector genome biodistribution and hABCD1 mRNA expression in NHP study 3 and NHP study 5 are shown in Figures S9 and S10, respectively. Vector genome biodistribution and hABCD1 mRNA expression in other tissues are shown in Figures S11–S13. DRG, dorsal root ganglia; hABCD1 human adenosine triphosphate-binding cassette sub-family D member 1; mRNA, messenger RNA; vg/an, vector genomes/animal.\n\nFigure 8: Figure 8. ALT and AST levels post SBT101 administration in NHP study 4 ALT and AST activity were assessed in samples collected before and after a 6-h lumbar infusion of SBT101. (A and B) show samples collected before SBT101 administration on days −14 and −6, and after administration on days 7, 15, 21, 29, 56, 93, and 183. Data represent mean ± 95% confidence interval. Blue shaded areas indicate normal ranges for ALT and AST levels. Control NHPs received vehicle control (poloxamer [Kolliphor P188], potassium chloride, potassium dihydrogen phosphate dibasic in sterile water). (A and B) Data at day 56 and day 93 were based on n = 6 for controls and both low- and medium-dose SBT101 and n = 8 for high-dose SBT101; data at day 183 were based on n = 3 for controls and both low- and medium-dose SBT101 and n = 4 for high-dose SBT101. ALT and AST levels in NHP study 3 and NHP study 5 are shown in Figures S14 and S15, respectively. ALT, alanine aminotransferase; AST, aspartate aminotransferase; vg/an, vector genomes/animal."
      }
    ]
  },
  {
    "id": "PMC11550647_multi",
    "image": [
      "images/PMC11550647-f1.png",
      "images/PMC11550647-f2.png",
      "images/PMC11550647-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Cerebral adrenoleukodystrophy presenting as status epilepticus: Unveiling the neurological maze\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Hyperpigmentation in perioral region and gums shown with red arrows.\n\nFigure 2: Figure 2. Diffuse hyperpigmentation particularly involving joints and hands shown with red arrows.\n\nFigure 3: Figure 3. (A) MRI brain T2 weighted axial sections showing bilateral parieto-occipital white matter abnormal signals in periventricular and subcortical planes marked with red arrows. (B) MRI brain (FLAIR) axial sections showing hyperintensities in bilateral parieto-occipital regions with white matter abnormal signals in periventricular and subcortical planes marked with red arrows. (C) MRI brain showing no significant enhancement on post contrast scan marked with red arrows."
      }
    ]
  },
  {
    "id": "PMC11552335_multi",
    "image": [
      "images/PMC11552335-f1.png",
      "images/PMC11552335-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"From gene to therapy: a review of deciphering the role of ABCD1 in combating X-Linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Distribution of Mutations of ABCD1 and Functional Domains of ABCD1. The top panel depicts the distribution of mutations in ABCD1 (excluding introns), categorized as pathogenic or likely pathogenic mutations (colored red), benign or likely benign mutations (colored green), or variants of uncertain significance (VUSs) (colored gray). The middle panel contains a variant density plot based on a 50-base-pair sliding window across ABCD1, with the x-axis representing the positions of amino acids. The bottom panel highlights the protein domains encoded by ABCD1. CDS = Coding Sequence, UTR = Untranslated Region. Mutation data was obtained from https://adrenoleukodystrophy.info/\n\nFigure 2: Figure 2. Therapeutic Targets in X-ALD Linked to ABCD1 Mutations. The mutation disrupts normal ABCD1 functioning, leading to decreased β-oxidation of very-long-chain fatty acids (VLCFAs). This reduction leads to the accumulation of VLCFA-CoAs and thus an increase in concentrations of free VLCFAs. The accumulation of VLCFAs triggers oxidative stress and cellular damage. The figure indicates intervention points that must be addressed when developing treatments to target the underlying biochemical abnormalities in X-ALD. ROS = reactive oxygen species. The figure is created with BioRender.com"
      }
    ]
  },
  {
    "id": "PMC11570732_multi",
    "image": [
      "images/PMC11570732-f1.png",
      "images/PMC11570732-f2.png",
      "images/PMC11570732-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Association between seizure reduction during ketogenic diet treatment of epilepsy and changes in circulatory metabolites and gut microbiota composition\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Serum metabolomic profiles of patients with epilepsy are influenced by treatment and response. (a) PERMANOVA analysis of covariates influencing the serum metabolomic profiles of the patients ranked by impact (R2 value). Significant influence is shown in orange (fdr<0.05), non-significant in yellow. Fdr values below 0.05 are shown inside the bars. (b) NMDS analysis of serum metabolomic profiles with samples from non-responders before KD in red (NR_Ep1), during KD in green (NR_Ep2), responders before KD in turquoise (R_Ep1), responders during KD in purple (R_Ep2).\n\nFigure 2: Figure 2. The ketogenic diet induces metabolomic changes in the serum of children with severe epilepsy. 345 out of 995 metabolites were significantly changed in a paired t-test (p<0.05) of which 185 remained after correcting for false discovery rate (fdr<0.05) (a) A volcano plot showing significant changes in metabolites due to starting KD treatment, with metabolites significantly changed (p<0.01 and fdr<0.05) above the dashed horizontal line in blue. Metabolites in red showed largest significant fold-changes (FC) with FC>2 beyond the dashed vertical lines and FC>5 beyond the straight vertical lines, labelled with metabolite names. Green indicates metabolite changes with FC>2 but p>0.01 or fdr>0.05. (b) Violin plots of normalised levels of glucose and the major ketone bodies 3-Hydroxybutyrate and Acetoacetate measured in the untargeted assay at both time points. A center line within each box represents the median; box limits are upper and lower quartiles; whiskers show 1.5 × interquartile range; and points depict outliers. (c) Pathway enrichment analysis of significantly changed metabolites with Enrichment scores on the x-axis and bars color-coded by coverage. (d) Multilevel PCA showing unsupervised clustering of serum metabolite profiles by time point. (e) Ranked loading plot of the five metabolites included in the final multilevel sPLS-DA model discriminating samples between time points with 100% accuracy as demonstrated in the confusion matrix in f.\n\nFigure 3: Figure 3. Heatmap of Spearman correlation coefficients of microbial taxa with the most significant metabolites correlating with seizure reduction. For clustering, Euclidean distances were used for rows and columns. Metabolite changes that positively correlated with seizure reduction are labelled in purple, while negative correlations are labelled in grey. Positive correlations are shown in red, negative correlations in blue. Taxa are only included in the heatmap if there was at least one correlation with a metabolite with p<0.01. ∗ indicates p<0.05, ∗∗ indicates p<0.01 and ∗∗∗ indicates p<0.001."
      }
    ]
  },
  {
    "id": "PMC11573904_multi",
    "image": [
      "images/PMC11573904-f1.png",
      "images/PMC11573904-f2.png",
      "images/PMC11573904-f3.png",
      "images/PMC11573904-f4.png",
      "images/PMC11573904-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"GhATL68b regulates cotton fiber cell development by ubiquitinating the enzyme required for β-oxidation of polyunsaturated fatty acids\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Analysis of SVs and characterization of DNA methylation patterns in promoter regions of ATL68b from different cotton species. (A) SVs in promoters of GarATL68b (G. arboretum), GheATL68b (G. herbaceum), and GhATL68b-A (G. hirsutum-A). Class I/LARD is a transposon. Numbers −189 to −467 are the bases upstream of GarATL68b. Dashed lines represent missing sequences in GhATL68b-A. (B) SVs in promoters of GraATL68b (G. raimondii) and GhATL68b-D (G. hirsutum-D). Numbers −315 to −499 are the bases upstream of GraATL68b. Dashed lines represent missing sequences in GhATL68b-D. (C) Class I/LARD sequence length differences in promoters of GarATL68b, GheATL68b, GhATL68b-A, GraATL68b, and GhATL68b-D. Primers are marked in (A) and (B), and their sequences are listed in Supplemental Table 3. (D) Sanger sequencing identification of an SV found in the promoter region of GhATL68b-A but not GarATL68b or GheATL68b. Underlined −363 to −438 are the numbers of bases upstream of the promoter from GarATL68b. (E) Sanger sequencing identification of an SV found in the promoter region of GhATL68b-D but not in that of GraATL68b. Underlined −389 to −442 are the numbers of bases upstream of the promoter from GraATL68b. (F) Differences in CHH-type DNA methylation in promoters of GarATL68b, GheATL68b, and GhATL68b-A observed after whole-genome bisulfite sequencing (WGBS) (left). CHH-type DNA methylation analysis of the GraATL68b and GhATL68b-D promoters using targeted bisulfite sequencing (Target-BS) (right). (G) Immunoblotting analysis of GhATL68b protein in ovules and fibers harvested at 10, 15, or 20 DPA or in young leaves from WT plants. Actin was used as the loading control. WT, wild-type upland cotton. (H)In situ hybridization analysis of GhATL68b expression. The right panel shows antisense hybridization of cross-sections from 2 DPA WT ovules. In the left panel, the sense strand was used as a negative control. The red arrows indicate the presence or absence of hybridization signals. Scale bar represents 200 μm.\n\nFigure 2: Figure 2. Evolution of the ATL68b gene family. (A) Evolution of ATL68b in animals, plants, and archaea. Among different plant species, ATL68b similarity was high, but the C. reinhardtii sequence showed only 6% identity. (B) Conserved amino acid residues for C3H2C3 in animals, plants, and archaea in the RING-H2 domains. (C) Phylogenetic analysis of major eudicot plants and their ancestors. (D) Evolution of GhATL68b, with collinearity between GhATL68b and its orthologous genes in ancestor plants highlighted (red lines). (E) Phylogenetic relationships of ATL68b with its orthologous genes in G. herbaceum, G. arboretum, G. raimondii, and G. hirsutum, with T. cacao and A. thaliana used as outgroups.\n\nFigure 3: Figure 3. Phenotypic analysis of knockout mutant cotton lines. (A) Sequence confirmation of ghatl68b knockout: genome editing at sgRNA1–2 sites for GhATL68b-A (upper panels) and -D (lower panels). Each sequence represents the same editing status of both sense and antisense strands in the genome, verified by three individual Sanger sequencing tests. The sgRNA target sites (red), nucleotide deletions (black dashes), and insertions (additional bases) are indicated. Dashed lines indicate deleted nucleotide sequences. (B) Plant growth phenotypes of three mutant lines compared with WT (unedited control plant) or WT1 (control plant carrying empty vectors). Plant height was measured from the soil to the growth tip. Empty vectors were not present in the mutant lines. Values are means ± SD (n = 3 independent samples), and ns corresponds to p > 0.05 in a Student’s t-test. (C) Analysis of upper-half mean fiber lengths. Values are means ± SD (n = 3 independent samples). Each biological replicate required 15 g of mature fibers as measured by the instrument. Because there were no significant differences between WT and WT1, we used WT as the control in subsequent experiments. ∗p < 0.05, ∗∗p < 0.01. Student’s t-test. (D)GhATL68b transcripts were not detected by qRT–PCR in knockout cotton plants. GhUBQ7 was used as a loading control. (E) No GhATL68b protein accumulated in the knockout lines, as shown by immunoblotting with anti-GhATL68b antibody. Anti-actin was used as a loading control. (F) Comparison of various fiber characteristics in knockout mutants and the control: panel 1, uniformity; panel 2, elongation at break; panel 3, total fiber weight from 100 seeds; panel 4, fiber-specific breaking strength (cN/tex, tensile force borne by 1 tex fiber); panel 5, micronaire (μg/in). Values are means ± SD (n = 3 independent samples). Each data point was obtained from 15 g of mature fiber. ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001 (Student’s t-test).\n\nFigure 4: Figure 4. GhATL68b interacts with and ubiquitinates GhDECR. (A) Interaction analysis of GhATL68b-A (bait) with a cotton ovule cDNA library using a yeast two-hybrid screening assay. Interaction partners (blue and black triangles) were identified by Sanger sequencing and are listed in Supplementary Table 2. (B) Split luciferase complementation (split-LUC) assay showing the interaction between GhATL68b-A and GhDECR (the major interaction partner reported in A) in N. benthamiana leaves. The constructs shown on the left were co-expressed in tobacco leaves by injection 3 days before images were taken. p1300-nLUC and p1300-cLUC vectors were used as negative controls. The pseudo-color bar shows the range of luminescence. (C) A GST-pull down assay shows the interaction between GST-GhATL68b-A and GhDECR in vitro. The GST tag was used as a negative control. Signs (+ and –) represent the presence or absence, respectively, of a specific component. (D) Conserved amino acid residues in GhATL68b-A and other known A. thaliana E3 ligases with RING-H2 domains. The upper drawing shows the full-length GhATL68b-A protein (199 aa), with the highly conserved RING-H2 domain indicated (residues 129–171, gray). Conserved Cys (red) and His (green) residues in the ubiquitination catalytic sites are also marked with # at the top of the panel. RHA3A, RHA3B, SDIR1, RHF1A, XERICO, and STRF1 are A. thaliana E3 ligases with RING-H2 finger domains (Ko et al., 2006; Zhang et al., 2007; Liu et al., 2008; Tian et al., 2015; Ma et al., 2020). (E)In vitro ubiquitination assay containing E1, E2, ubiquitin (Ub), and GhATL68b-A. Polyubiquitin chains were observed by immunoblotting with anti-MYC antibody, and signs (+ and –) represent the presence or absence of a specific component. (F) GhATL68b-A mediates GhDECR ubiquitination (detected by anti-Ub antibody in lane 7). Lane 8 (added only MYC-control), lane 9 (added BSA), and lane 6 (no GhDECR-FLAG added) were used as negative controls for non-ubiquitination (lane 8) or self-ubiquitination. The input proteins were quantified by immunoblots using MYC, FLAG, and Ub antibodies, as presented at the bottom of the panel. Signs (+ or –) represent the presence or absence, respectively, of a specific component. (G) Analysis of GhDECR ubiquitination intensity with increasing reaction time (min). (H) Analysis of GhDECR ubiquitination intensity with increasing GhDECR-FLAG protein content (2.5, 5, 10, or 20 μM GhDECR-FLAG was used in a total reaction volume of 25 μL). (I) GhATL68b mediates the degradation of GhDECR. Cellular proteins (100 ng) purified from 10 DPA fibers of WT or the ghatl68b mutant were incubated with GhDECR-FLAG at 23°C for the indicated times (min), then probed with anti-FLAG antibody. MG132 is a proteasome inhibitor, and actin and tubulin were used as internal controls. (J) Immunoblotting assay showing significant accumulation of GhDECR in ghatl68b knockout lines (upper left). When GhDECR content in the WT was set to 1 to quantify protein accumulation, each mutant line accumulated a significant amount of this protein (upper right). RT–qPCR experiments indicated no significant differences in GhDECR transcript level among various knockout mutant plants (lower panels). ImageJ was used for grayscale analysis. Three independent experiments were used for related calculations in (I) and (J). ∗∗∗p < 0.001 (Student’s t-test).\n\nFigure 5: Figure 5. Higher GhDECR protein content in the ghatl68b knockout mutant is associated with reduced PUFA levels. (A) Schematic representation of the linolenic acid (C18:3) β-oxidation pathway. In higher plants, C18:3 (shown here) and C18:2 are major PUFAs. In the β-oxidation pathway, GhDECR catalyzes the reduction of 2,4-dienoyl-CoA to enoyl-CoA, with NADPH serving as the hydrogen donor. (B) GhDECR enzyme activity in 10 DPA fibers of WT and knockout plants as determined by double antibody sandwich ELISA. Values are mean ± SD (n = 3 independent experiments). Asterisks mark significant changes compared with the WT based on Student’s t-test (∗∗p < 0.01). (C) Coenzyme II (NADP+/NADPH) reaction rate in WT and ghatl68b knockout mutants. ∗∗p < 0.01 (Student’s t-test). (D) Acetyl-CoA content in 10 DPA fibers of WT and ghatl68b knockout mutants. ∗∗∗p < 0.001 (Student’s t-test). (E) Quantitative analysis of long-chain fatty acids in 10 DPA fibers of WT and ghatl68b knockout mutant plants by GC–MS. Commercial fatty acids were used as external standards for quantification (see Supplemental Figure 8). CPS, counts per second. The experiments were repeated three times using independent cotton materials, with the identity of each peak individually labeled. (F) Fragment ions (Q1) of long-chain fatty acids used for quantitative analysis of chemicals in the chromatogram in (E). (G) Quantitative analysis of PUFAs, monounsaturated fatty acids (MUFAs), and saturated fatty acids (SFAs) in (E) on the basis of Q1 ions (see Methods). ∗∗p < 0.01, ∗∗∗p < 0.001 (Student’s t-test). (H) Cell membrane fluidity assay using fiber cell protoplasts prepared from 1 DPA fibers of WT and knockout mutants. Values are mean ± SD (n = 3 independent measurements). ∗∗∗p < 0.001 (Student’s t-test)."
      }
    ]
  },
  {
    "id": "PMC11576736_multi",
    "image": [
      "images/PMC11576736-f1.png",
      "images/PMC11576736-f2.png",
      "images/PMC11576736-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Evaluation of 100 Dutch cases with 16p11.2 deletion and duplication syndromes; from clinical manifestations towards personalized treatment options\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. This figure provides an overview of chromosome 16, including its short (p) and long (q) arms, as well as chromosomal bands and 16p11.2 breakpoints. A The recurrent typical ~600 kb 16p11.2 BP4-BP5 and distal ~220 kb 16p11.2 BP2-BP3 CNVs (deletions and duplications) are shown in more detail, including breakpoints (BPs) and genes in these regions. B The different 16p11.2 CNVs in our cohort, including the larger ‘other’ groups that are included in this study are shown, including the breakpoints.\n\nFigure 2: Figure 2. Depicted are the different 16p11.2 CNVs identified in our cases, mainly consisting of typical 16p11.2 BP4-BP5 and distal 16p11.2 BP2-BP3 deletions (del) and duplications (dup), but also other (larger) deletions and duplications.\n\nFigure 3: Figure 3. Comparative boxplots representing General IQ, BMI SDS, OFC SDS, and height SDS across 16p11.2 deletion (red) and –duplication (blue) subgroups. Mean values for the deletion and duplication groups are illustrated with blue and red horizontal lines, respectively. A t test was performed to identify statistically significant differences between the deletion and duplication groups, * (p < 0.05), ** (p < 0.01), and *** (p < 0.001)."
      }
    ]
  },
  {
    "id": "PMC11584599_multi",
    "image": [
      "images/PMC11584599-f1.png",
      "images/PMC11584599-f2.png",
      "images/PMC11584599-f3.png",
      "images/PMC11584599-f4.png",
      "images/PMC11584599-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Tandem mass spectrometry of serum cholestanoic (C27) acids – Typical concentration ranges and application to the study of peroxisomal biogenesis disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The chemical structures of the key intermediate cholestanoic acids in the pathway for primary bile acid synthesis from cholesterol.\n\nFigure 2: Figure 2. Negative ion MS/MS mass spectra of the racemic forms of [2H4]Tauro-DHCA, Tauro-DHCA, [2H4]Tauro-THCA and Tauro-THCA. The chemical structures and fragmentation pattern is indicated along with the position of the deuterium ([2H]) atoms, designated in the chemical structure with the letter ‘D’.\n\nFigure 3: Figure 3. Combined MRM mass chromatograms for the internal standards that were added to a sample of human serum to produce at concentration of 250 ng/mL and separated by HPLC. The following C27 bile acids are indicated numerically as: 1 and 2, (25S)- and (25R)-[2H4]Tauro-THCA, m/z 560.1 > 79.8; 3 and 4, (25S)- and (25R)-[2H4]Tauro-DHCA, m/z 544.1 > 79.8; 5 and 6, (25S)- and (25R)-[2H3]DHCA, m/z 436.2 > 436.2; 7 and 8, (25S)- and (25R)-[2H3]THCA m/z 452.2 > 452.2.\n\nFigure 4: Figure 4. Typical mass chromatograms for the MRM transitions of DHCA, THCA and their taurine conjugates and internal standards are shown for sera from a control subject with no evidence for liver disease, a patient with a confirmed peroxisomal disorder of Zellweger, and a patient with a confirmed 2-methylacyl-CoA racemase deficiency.\n\nFigure 5: Figure 5. The serum concentrations of (A) total C24 bile acids and (B) total C27 bile acids for the following groups; (1) normal adults n = 20, (2) non-cholestatic infants and children n = 8, (3) infants with moderate cholestasis n = 10, (4) severely cholestatic infants and children n = 9, (5) patients with genetically confirmed peroxisomal disorders n = 49, (6) patients with 2-methylacyl-CoA racemase deficiency n = 7, and (7) patients with confirmed heterozygous mutations in PEX genes n = 17. The serum total C27 bile acids concentrations are shown (C) for patients with mutations in the different PEX genes. Below are the correlations between C24 bile acids and C27 bile acids for patients with liver disease (D) and patients with Peroxisomal disorders (E)."
      }
    ]
  },
  {
    "id": "PMC11633702_multi",
    "image": [
      "images/PMC11633702-f1.png",
      "images/PMC11633702-f2.png",
      "images/PMC11633702-f3.png",
      "images/PMC11633702-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Bilateral pulvinar responsive neurostimulation for bilateral multifocal posteriorly dominant drug resistant epilepsy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (Top) Patient 1 postoperative electroencephalogram detection of seizure onset from the right pulvinar leads spreading to the left pulvinar. (Bottom) Spectrograph showing bursts at 25 Hz in the bilateral pulvinar leads with the right spreading to the left pulvinar.\n\nFigure 2: Figure 2. (Left) Patient 2 anterior–posterior radiograph showing depth electrode placement in bilateral pulvinar thalamic nuclei in the red circles. (Right) Postoperative magnetic resonance imaging with leads at overlaid targets showing placement in bilateral pulvinar thalamic nuclei.\n\nFigure 3: Figure 3. (Top Left) Electrocorticogram of patient 2 showing independent onset seizures in left pulvinar (Top Right) electrocorticogram of patient 2 showing independent onset seizures in right pulvinar. Both seizures had the same clinical semiology. (Bottom Left) Spectrograph showing bursts at 50 Hz in the left pulvinar leads. (Bottom Right) Spectrograph showing bursts at 25 Hz in the right pulvinar leads.\n\nFigure 4: Figure 4. Electrocorticograms and spectrographs of Patients 3 and 4 after responsive neurostimulation implantation showing accurate seizure detection bilaterally. (A) (Top) Electrocorticogram of Patient 3 showing simultaneous seizure onset in the left occipital and pulvinar. (Bottom) Spectrograph showing simultaneous bursts at 25 Hz in both pulvinar and occipital regions. (B) Electrocorticogram of Patient 4 showing right RNS seizure with near‐simultaneous onset in occipital and pulvinar leads. (Bottom) Spectrograph showing near‐simultaneous bursts at 50 Hz in the occipital region and 25 Hz in the pulvinar region."
      }
    ]
  },
  {
    "id": "PMC11651355_multi",
    "image": [
      "images/PMC11651355-f1.png",
      "images/PMC11651355-f2.png",
      "images/PMC11651355-f3.png",
      "images/PMC11651355-f4.png",
      "images/PMC11651355-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Long Noncoding RNA TRIBAL Links the 8q24.13 Locus to Hepatic Lipid Metabolism and Coronary Artery Disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Impact of top UK Biobank coronary artery disease (CAD) single-nucleotide polymorphism (SNP) on lipid traits and TRIBAL expression. A, rs6982502_ T allele (alternate/protective) linked to reduced CAD (odds ratio, <1), low-density lipoprotein (LDL-C), and triglyceride (TG; negative β-values). B, rs6982502_C allele (reference/risk) linked to increased TRIBAL expression. Stockholm-Tartu Atherosclerosis Reverse Network Engineering Task effect based on reference allele. C, Violin plot of liver TRIBAL expression as a function of rs6982502 genotype according to Genotype-Tissue Expression; P=0.008. adj. indicates adjusted; and LIV, liver.\n\nFigure 2: Figure 2. P-P plots of coronary artery disease (CAD) vs expression quantitative trait loci (eQTL) values for TRIBAL and TRIB1 in the liver and blood. ENSG00000253111 expression is not present in eQTLGen (whole blood), while a single significant eQTL within a 500-Kb window centered on TRIB1 was nominally (P<0.05) linked to TRIB1 expression in the liver. TRIBAL (liver), but not TRIB1 (whole blood), eQTLs are enriched in genome-wide association study (GWAS) significant CAD hits (P=5.27×10−60 vs P=0.299). Data were analyzed via eQTpLot. SNP indicates single-nucleotide polymorphism.\n\nFigure 3: Figure 3. Impact of TRIBAL suppression by antisense oligonucleotides (ASOs) on local gene expression. A, Schema of ASO cognate positions relative to the TRIBAL1 transcript drawn approximately to scale. B and C, RNA expression in TRIBAL ASO-treated hepatocytes. RNA expression was measured in primary hepatocytes from 3 distinct donors targeted for 72 hours with TRIBAL ASO1, ASO2, or ASO4, as indicated. B, Two distinct donors, each treated with either ASO1 or ASO2. C, Third donor, treated with 3 distinct ASOs. Values shown were normalized internally to PPIA (ΔCt method) and to the matching control (CTL) ASO values. Error bars represent the standard deviation (STD). P values (paired t test with matching NT values): *P<0.05, **P<0.01, ***P<0.001. NT indicates non-target.\n\nFigure 4: Figure 4. Suppression of major regulators of liver metabolism by TRIBAL antisense oligonucleotides (ASOs). Quantitative reverse transcription polymerase chain reaction (qRT-PCR) analysis of samples submitted to transcriptome array (A), or replication set (B), using a third donor and 3 TRIBAL cognate ASOs. Transcript abundance, expressed relative to the NT value as determined by qRT-PCR of hepatocytes treated with ASO1 or the NT ASO for 72 hours. Each point represents a biological replicate. Mean±SD is shown. Statistical significance was tested using 2-tailed Student t tests. *P<0.05, **P<0.01, ***P<0.001. NT indicates non-target.\n\nFigure 5: Figure 5. TRIBAL suppression reduces hepatocyte triglyceride (TG) secretion without affecting apoB secretion. Levels of TG (A) and apoB (B) in cell media of 72-hour antisense oligonucleotide (ASO)–treated hepatocytes (donor HU8412) were measured using a fluorescence-based lipase assay and ELISA, respectively. In C, the ratio of TG to APOB was calculated for each biological replicate and is expressed relative to the corresponding CTLASO value, indicating that TRIBAL suppression reduced lipidation of apoB lipoproteins. Each point represents a distinct biological replicate. Control apoB and TG values were 1.7 µg/mL (SD, ±0.34) and 224 ng/mL (SD, ±83), respectively. Statistical significance was tested using a 1-way Student t test (vs CTLASO), under the hypothesis that TG and apoB secretion would be inhibited. *P<0.05, **P<0.01, ***P<0.001. CTLASO indicates control antisense oligonucleotide."
      }
    ]
  },
  {
    "id": "PMC11656574_multi",
    "image": [
      "images/PMC11656574-f1.png",
      "images/PMC11656574-f2.png",
      "images/PMC11656574-f3.png",
      "images/PMC11656574-f4.png",
      "images/PMC11656574-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Protective effects of miR-24-2-5p in early stages of breast cancer bone metastasis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MiR-24-2-5p expression levels in the serum from BC patients, human BC cell lines, and small extracellular vesicles derived from BC cell lines. A Receiver operating characteristic (ROC) curves analysis for miR-24-2-5p to predict bone relapse, either alone (left panel) or in combination with patients’ tumour grade (TGRADE) (right panel). B Violin plot showing miR-24-3p, miR-24-1-5p and miR-24-2-5p expression levels in the serum from early-stage BC patients who did not relapse (NOMET, n = 16) versus BC patients who relapsed in bone (BONEMET, n = 16). C Comparison of the expression levels of miR-24-3p, miR-24-1-5p and miR-24-2-5p between NOMET and BONEMET groups. Only miR-24-2-5p expression levels showed a significant fold change (Log2FC≤-0.5, p = 0.02) between both groups. D Expression levels of miR-24-2-5p in different subtypes of human BC cell lines (luminal A, luminal B, HER+, TNBC). E Expression levels of miR-24-2-5p in the CCLE BC cell collection database (45 tumour cell lines sub-grouped into 4 BC subtypes). F Expression levels of miR-24-2-5p in small extracellular vesicles (sEVs) secreted from NW1 cells compared to the cells of origin. G Expression levels of miR-24-2-5p in sEVs secreted from SK-BR-3 cells compared to the cells of origin. Data are the mean ± SEM of three independent experiments, * p ≤ 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001\n\nFigure 2: Figure 2. Effects of miR-24-2-5p overexpression on migration, invasion, and proliferation of BC cells. A Migration assay at 24 h using transiently transfected NW1 cells overexpressing miR-24-5p (MIMIC-miR-24-2-5p) or the negative control mimic (MIMIC-negCTRL). B Same as in (A) for the migration of transiently transfected MCF7 cells (MIMIC-negCTRL, MIMIC-miR-24-2-5p). C Invasion assay at 24 h using transiently transfected NW1 cells (MIMIC-negCTRL, MIMIC-miR-24-2-5p). D Proliferation assay using transduced NW1 cells stably overexpressing miR-24-5p (MIMIC-miR-24-2-5p) or the negative control mimic (MIMIC-negCTRL). E Same as in (D) for the proliferation of transduced MCF7 cells (miR-negCTRL, miR-24-2-5p). Data are the mean ± SEM of 3 independent experiments. * p ≤ 0.05, ** p < 0.01, *** p < 0.001\n\nFigure 3: Figure 3. RNA-sequencing analyses on miR-24-2-5p-overexpressing BC cells. A Heatmap for transcripts modulated by miR-24-2-5p in NW1 cells. B Volcano plot with differentially expressed transcripts modulated by miR-24-2-5p in NW1 cells. C Heatmap for transcripts modulated by miR-24-2-5p in MCF7 cells. D Volcano plot with differentially expressed transcripts modulated by miR-24-2-5p in MCF7 cells. E Common transcripts modulated by miR-24-2-5p in both NW1 and MCF7 cells. In yellow, transcripts that were predicted direct targets of miR-24-2-5p. F GSEA on modulated transcripts in RNA-seq data from NW1 cells transiently transfected with MIMIC-miR-24-2-5p versus MIMIC-negCTRL. G GSEA on modulated transcripts in RNA-seq data from MCF7 cells transiently transfected with MIMIC-miR-24-2-5p versus MIMIC-negCTRL. Common gene sets between NW1 and MCF7, GSEA analyses are highlighted in red\n\nFigure 4: Figure 4. Real-time qPCR validation of transcripts downregulated by miR-24-2-5p overexpression. A Validated transcripts downregulated upon miR-24-2-5p overexpression at both early (day 1, D1) and late (day 4, D4) in NW1 cells transiently transfected with MIMIC-miR-24-2-5p versus MIMIC-negCTRL. B Validated transcripts downregulated only at D4 in NW1 cells transiently transfected with MIMIC-miR-24-2-5p versus MIMIC-negCTRL. C Validated transcripts downregulated only at D1 in NW1 cells transiently transfected with MIMIC-miR-24-2-5p versus MIMIC-negCTRL. D Correlations of miR-24-2-5p expression and the expression of each validated transcript in 736 primary BC tissues from the TGCA-BRCA database. Significant correlations are highlighted. Data are the mean ± SEM of 3 independent experiments. * p ≤ 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001\n\nFigure 5: Figure 5. Experimental model of bone metastasis to evaluate the effect of miR-24-2-5p on early BC dissemination in vivo. A Schematic representation of the protocol aimed to evaluate the impact of miR-24-2-5p overexpression on the early stages of (bone) metastasis formation in animals. The control group of mice that received an intracardiac injection of control NW1 cells (upper panel, gray) showed metastasis formation, mainly in bones (e.g., jaws, hind limbs, and shoulders), 7 days post tumour cell injection, as judged by BLI. Instead, the experimental group that received an intracardiac injection of miR-24-2-5p-overexpressing NW1 cells (lower panel, green) showed a drastic reduction or absence of metastases. B Total bioluminescence intensity of each mouse that belonged to the control (MIMIC-negCTRL) or experimental (MIMIC-miR-24-2-5p) group was quantified as a readout of tumour burden in animals at day 7 post injection. C Circulating CTX-I (bone resorption marker) and P1NP (bone formation marker) levels in control (MIMIC-negCTRL) and experimental (MIMIC-miR-24-2-5p) group at day 9 (sacrifice day). Data are shown as mean value ± SEM. * p ≤ 0.05"
      }
    ]
  },
  {
    "id": "PMC11656574_multi_2",
    "image": [
      "images/PMC11656574-f6.png",
      "images/PMC11656574-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Protective effects of miR-24-2-5p in early stages of breast cancer bone metastasis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Effect of the conditioned medium (CM) from miR-24-2-5p-overexpressing BC cells on osteoclast differentiation. A ClueGO-based analysis conducted on the top 250 predicted targets (TargetScan) for miR-24-2-5p. 18 GO biological process networks (groups) with the relative p-value are presented. Two groups of high relevance for osteoclastogenesis are highlighted. B Schematic representation of the experimental protocol with human blood-derived monocytes cultured in the presence of differentiating factors (RANKL, M-CSF) and the conditioned medium (CM) from BC cells overexpressing or not overexpressing miR-24-2-5p. C Representative figures of differentiated, TRAP-positive osteoclasts after 12 days in culture in the presence of CM from control (MIMIC-negCTRL) or miR-24-2-5p-overexpressing (MIMIC-miR-2-5p) NW1 or MCF7 cells (upper and lower panels, respectively). D Histograms showing the number of TRAP-positive osteoclasts in the presence of CM from control (MIMIC-negCTRL) or miR-24-2-5p-overexpressing (MIMIC-miR-2-5p) NW1 (upper panel) and MCF7 (lower panel) cells. Mature osteoclasts were classified into 3 groups: between 3 and 10 nuclei, from 11 to 30 nuclei, and more than 30 nuclei. E Effect of CM from NW1 cells overexpressing miR-24-2-5p (MIMIC-miR-24-2-5p) or a negative control mimic (MIMIC-negCTRL) on the differentiation of murine bone marrow-derived osteoclasts. Plot showed the number of multinucleated (> 3 nuclei) TRAP-positive osteoclasts for each group. F MiR-24-2-5p expression levels in osteoclasts cultured with CM from NW1 cells transfected with miR-24-2-5p mimics (MIMIC-miR-24-2-5p) or negative control miRNA mimics (MIMIC-negCtrl). Cell pellets were collected at day 7 of the osteoclastogenesis protocol. Relative expression levels of miR-24-2-5p compared to the housekeeping gene U6 were calculated by the 2−ΔΔCT method. G MiR-24-2-5p expression levels in immature and mature murine osteoclasts (the categorization was based on TRAP-positivity and gene expression analysis of markers related to osteoclastogenesis). Relative expression levels of miR-24-2-5p compared to the housekeeping gene U6 were calculated by the 2−ΔΔCT method. Data are the mean ± SEM of 3 independent experiments. * p ≤ 0.05, ** p < 0.01\n\nFigure 7: Figure 7. Schematic representation of the role of miR-24-2-5p during breast cancer progression and bone metastasis formation. In invasive human BC cells, forced miR-24-2-5p expression reduces cell malignant traits in vitro (upper panel). Low miR-24-2-5p expression levels in serum of early-stage BC patients are associated with a high risk to develop (bone) metastasis (middle panel). Forced expression of miR-24-2-5p in disseminated BC cells in bone has a protective effect in vivo by reducing the metastatic potential of circulating BC cells and decreasing bone turnover (lower panel). Overall, miR-24-2-5p has a protective role in the first events of BC bone metastasis formation, reducing malignant BC cell traits, tumour cell dissemination in bone, and the differentiation of monocytes into mature osteoclasts"
      }
    ]
  },
  {
    "id": "PMC11657003_multi",
    "image": [
      "images/PMC11657003-f1.png",
      "images/PMC11657003-f3.png",
      "images/PMC11657003-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The clinical and biochemical effectiveness and safety of cholic acid treatment for bile acid synthesis defects: a systematic review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PICOS chart detailing inclusion criteria for systematic review. Abbreviations RCT, randomized controlled trial; PICOS, ‘population, interventions, comparators, outcomes, and study designs’. Clinical outcomes: Liver disease, kidney dysfunction, neurological disease, hearing impairment, vision impairment, skeletal disease or growth retardation, psychiatric symptoms. Biochemical outcomes: Primary bile acids and bile acid intermediates (toxic metabolite) plasma levels, liver chemistries, fat-soluble vitamins, plasma cholestanol and cholesterol levels. Safety outcomes: Dose-response relationship, adverse effects and side effects\n\nFigure 3: Figure 3. Types of (serious) adverse events and number of times reported\n\nFigure 4: Figure 4. Risk of bias assessment of included studies using Murad tool. This represents the review authors judgements on each risk of bias item"
      }
    ]
  },
  {
    "id": "PMC11658218_multi",
    "image": [
      "images/PMC11658218-f1.png",
      "images/PMC11658218-f2.png",
      "images/PMC11658218-f3.png",
      "images/PMC11658218-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Novel pathogenic variant in a mild case of type B molybdenum cofactor deficiency: case report and literature review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Molybdenum cofactor biosynthesis pathway\n\nFigure 2: Figure 2. MRI at presentation age 12 months, T2 sequences demonstrating increased signal of the globus pallidus bilaterally. DWI and ADC demonstrating bilateral diffusion restriction in the globus pallidus\n\nFigure 3: Figure 3. Diagram of MOCS2 gene with all known pathogenic variants\n\nFigure 4: Figure 4. Summary of key clinical phenotypes of MoCD Type B caused by MOCS2 variants"
      }
    ]
  },
  {
    "id": "PMC11660744_multi",
    "image": [
      "images/PMC11660744-f1.png",
      "images/PMC11660744-f2.png",
      "images/PMC11660744-f3.png",
      "images/PMC11660744-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Altered lipid profile and reduced neuronal support in human induced pluripotent stem cell‐derived astrocytes from adrenoleukodystrophy patients\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Adrenoleukodystrophy (ALD) human‐induced pluripotent stem cells (hiPSC)‐derived astrocytes present deficits in very long‐chain fatty acid metabolism. (A) Immunofluorescence images of control and ALD hiPSC‐derived astrocytes positive for astrocyte‐associated markers GFAP, ID3, NESTIN, and S100β at Day ~60 (scale bar, 100 μm). (B) Confocal immunofluorescence image of control hiPSC‐derived astrocytes positive for CD44 and ABCD1 at Day ~60 (scale bar, 100 μm). (C) C26:0‐lysophosphatydylcholine (LPC(26:0)) levels in control (n = 3) and ALD (n = 4) hiPSC‐derived astrocytes at Day 70; three independent batches per line; mean ± SD. (D) Control (n = 3) and ALD (n = 4) hiPSC‐derived astrocytes were cultured with 30 μM D3‐C22:0 for 3 days. Peroxisomal VLCFA β‐oxidation is expressed as the ratio of D3‐C16:0 (product) to D3‐C22:0 (substrate); three independent batches per line; mean ± SD. In (C) and (D), the mean values of each donor are shown in color and individual data points of each differentiation batch (n = 3) are shown in gray in the background. p values were calculated by two‐tailed nested t‐test with all individual data points nested per group (control n = 3 and ALD n = 4) and are shown as numbers when significant. DAPI, diamidino‐2‐phenylindole.\n\nFigure 2: Figure 2. Differentially abundant lipids in adrenoleukodystrophy (ALD) human‐induced pluripotent stem cells (hiPSC)‐derived astrocytes. (A) Principal component analysis plot of lipid profile of control and ALD hiPSC‐derived astrocytes at Day 90. (B) Volcano plot comparing the lipid profiles of control and ALD hiPSC‐derived astrocytes at Day 90. The x‐axis shows the log fold change in ALD hiPSC‐derived astrocytes and the y‐axis shows the significance of this change expressed as –log (p value). Phospholipids are expressed as C(XX:Y), where XX is the total number of carbon atoms and Y is the total number of double bonds in the fatty acyl chains. This analysis, without fragmentation, does not allow specification of which fatty acid is at the sn‐1 or sn‐2 position. (C) Lipid chain trend plots of lysophosphatidylchloline (LPC) (left panel), phosphatidylcholine (PC) (middle panel), and triglycerides (TG) (right panel). The x‐axis represents the chain length of each lipid class, and the y‐axis represents the log2 fold change between CTRL and ALD hiPSC‐derived astrocytes. Note an increase in LPC, PC, and TG species containing fatty acids with a total number of more than 24, 44, and 64 carbon atoms, respectively, indicating an enrichment in very long‐chain fatty acid. (D) Saturation heat maps of LPC (left panel), PC (middle panel), and TG (right panel). The x‐axis represents chain unsaturation, and the y‐axis represents chain length. Plotted is the log2 fold change between CTRL and ALD hiPSC‐derived astrocytes. Group differences in the lipidomics data were tested with a linear mixed‐effects model (LMM), where subject (cell line)‐specific deviations from the group mean were modeled with random intercepts. Prior to analysis, the lipidomics data were normalized to the internal standards and then log transformed. (E) Heatmap of significantly differentially abundant lipids. Each row represents one hiPSC‐derived astrocyte cell line, and the x‐axis shows the different lipid classes. LPE, lysophosphatidylethanolamine; PE, phosphatidylethanolamine; PS, phosphatidylserine; SM, sphingomyelin.\n\nFigure 3: Figure 3. Response of human‐induced pluripotent stem cells (hiPSC)‐derived astrocytes to very long‐chain fatty acid. (A) Quantification of nuclei in control (n = 3) hiPSC‐derived astrocytes after 24 h treatment with 10 μM C26:0 or C26:1 at Day ~90; three independent batches per line; mean ± SD; (B) ABCD1 abundance in control (n = 3) hiPSC‐derived astrocytes after 24 h treatment with 10 μM C26:0 and C26:1 compared to vehicle condition at Day ~90; three independent batches per line; mean ± SD. (C) Quantification of %GFAP+ astrocytes in control (n = 3) hiPSC‐derived astrocytes after 24 h treatment with 10 μM C26:0 and C26:1 compared to vehicle condition (0.17% DMSO) at Day ~90; three independent batches per line; mean ± SD. In (A–C), the mean values of each donor are color coded (black, dark gray, and white) and the mean of 12 fields within three 96‐well plates of each differentiation batch (n = 3) is shown in gray in the background. p values were calculated by paired t‐test with the mean of 12 fields within three 96 well‐plate wells of each differentiation batch nested per group (control n = 3 and adrenoleukodystrophy [ALD] n = 4). (D) SERPINA3, VCAM1, and NFκB2 relative gene expression levels in control hiPSC‐derived astrocytes (n = 3) after 24 h treatment with 10 μM C26:0 or C26:1 compared to vehicle (0.17% DMSO) condition at Day ~90; mean ± SD. p values were calculated by paired t‐test with the mean of 2 − ∆∆Ct values of each differentiation batch, previously normalized against the housekeeping gene (control n = 3); three independent batches per line. (E) Heatmap of response‐associated genes in hiPSC‐derived astrocytes; mean fold changes of three independent batches per line against the control group mean for ALD lines and against the ALD group mean for control lines. p values were calculated by unpaired t‐test with Welch’ correction with the mean of 2 − ∆∆Ct values of each differentiation batch, previously normalized against the housekeeping gene (control n = 3 and ALD n = 4) and are shown as numbers when significant; three independent batches per line.\n\nFigure 4: Figure 4. Adrenoleukodystrophy (ALD) human‐induced pluripotent stem cells (hiPSC)‐derived astrocytes fail to support motor neurons in vitro. (A) Schematic illustrating the co‐culture approach of control hiPSC‐derived motor neurons co‐cultured with either control (gray) or ALD (red) hiPSC‐derived astrocytes. (B) Cropped live‐cell images of GFP+ motor neurons co‐cultured with control (upper panel) and ALD (lower panel) hiPSC‐derived astrocytes at 24 h, 72 h, and 2 weeks. (C) Sholl intersection profile of MAP2 dendritic arborization of control hiPSC‐derived motor neurons co‐cultured with control hiPSC‐derived astrocytes (gray line; n = 3) and ALD hiPSC‐derived astrocytes (red line; n = 4). Three independent batches per astrocyte line; two to three coverslips per line; 45 ± 23 neurons/coverslip; mean ± SD. (D, E) Stratified analyses were also performed on two radius ranges, 20–29 and 80–89 μm. (F) Cropped confocal images of control hiPSC‐derived motor neurons immunostained for MAP2 and SYNAPTOPHYSIN (SYN) co‐cultured with control hiPSC‐derived astrocytes (top panel) and ALD hiPSC‐derived astrocytes (bottom panel). (G) Quantification of SYN puncta (total number of vesicles divided by the dendrite length) within the dendritic mask defined by MAP2 positivity. Three independent batches per astrocyte line; two to three coverslips per line; mean ± SD. Mean values are shown in color and the mean of four fields from each differentiation batch is shown in gray in the background. p values were calculated by two‐tailed nested t‐test with the mean of four fields of each differentiation batch nested per group (control n = 3 and ALD n = 4) and are shown as numbers when significant."
      }
    ]
  },
  {
    "id": "PMC11670711_multi",
    "image": [
      "images/PMC11670711-f1.png",
      "images/PMC11670711-f2.png",
      "images/PMC11670711-f3.png",
      "images/PMC11670711-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome and pexophagy in neurological diseases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomes originate from ERs or mitochondria with the help of PEXs via class Ⅰ and class Ⅱ pathways. Moreover, the PEX11 and other fission related proteins (Mdv/Caf4, Fis1 and Dnm/Vps1) involved in the division of peroxisomes. Reproduced with permission [19].\n\nFigure 2: Figure 2. The different distributions and activities of peroxisomes (catalase) in human brain (referenced from the human protein atlas: https://www.proteinatlas.org/ENSG00000121691-CAT/brain).\n\nFigure 3: Figure 3. The specialized functions of peroxisomes and neurological disorders rising due to peroxisomal dysfunction in the brain. Reproduced with permission [68].\n\nFigure 4: Figure 4. The underlying mechanisms of pexophagy in mammals."
      }
    ]
  },
  {
    "id": "PMC11672891_multi",
    "image": [
      "images/PMC11672891-f1.png",
      "images/PMC11672891-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Diagnosis and Management of Mitochondrial Encephalopathy, Lactic Acidosis, and Stroke-like Episodes Syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pathophysiological mechanisms of stroke-like episodes in MELAS. ATP, adenosine triphosphate; CSF, cerebrospinal fluid; DNA, deoxyribonucleic acid; MELAS, mitochondrial encephalopathy lactic acidosis and stroke-like episodes; mtDNA, mitochondrial deoxyribonucleic acid; OXPHOS, oxidative phosphorylation; ROS, reactive oxygen species.\n\nFigure 2: Figure 2. Current therapeutic strategies for MELAS. KD, ketogenic diet; LGIT, low-glycemic index treatment; MAD, modified Atkins diet; MELAS, mitochondrial encephalopathy lactic acidosis and stroke-like episodes; NO, nitric oxide."
      }
    ]
  },
  {
    "id": "PMC11673738_multi",
    "image": [
      "images/PMC11673738-f1.png",
      "images/PMC11673738-f2.png",
      "images/PMC11673738-f3.png",
      "images/PMC11673738-f4.png",
      "images/PMC11673738-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome Proliferator Activator α Agonist Clofibrate Induces Pexophagy in Coconut Oil-Based High-Fat Diet-Fed Rats\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Organ weights and representative images and qualitative analyses of fatty liver of rats. (A) Absolute weight of intra-abdominal fat weight. (B) Relative intra-abdominal fat weight to body weight. (C) Absolute liver weight. (D) Relative liver weight to body weight. (E) Normal hepatocytes, slight fatty droplet deposition, and acidophilia and hypertrophy in hepatocytes in the CTL, CF, HFD, and HFD + CF groups, respectively. Bar = 50 μm. Hematoxylin and eosin. (F) NAFLD activity score (NAS). (G) Steatosis score. (H) Ballooning score. (I) Inflammation score. (J) ADRP-positive lipid droplets, evident in the HFD group. (K) Area of ADRP-positive lipid droplets. (L) Acidophilia score. Data represent a box-and-whisker plot (red cross, mean; blue dots, outliers). Group: CTL, rats received control diet (Blue); CF, rats received control diet mixed with clofibrate (Yellow); HFD, rats received high-fat diet (Light green); HFD + CF, rats received high-fat diet mixed with clofibrate (Light red). Different letters indicate significant differences between groups (p < 0.05, significantly different by Tukey’s or Steel–Dwass test).\n\nFigure 2: Figure 2. Representative images and qualitative analyses of autophagy-related markers in hepatocytes of rats. (A) Immunohistochemistry for NBR1-positive granules, counterstained with hematoxylin, in the CTL, CF, HFD, and HFD + CF groups. Bar = 50 μm. (B) Quantitative analysis of NBR1-positive granules. (C) Immunohistochemistry for p62-positive granules, counterstained with hematoxylin, in the CTL, CF, HFD, and HFD + CF groups. Bar = 50 μm. (D) Quantitative analysis of p62-positive granules. (E) Immunohistochemistry for LAMP2-positive granules, counterstained with hematoxylin, in the CTL, CF, HFD, and HFD + CF groups. Bar = 50 μm. (F) Quantitative analysis of LAMP2-positive granules. (G) Immunohistochemistry for Pex5-positive granules, counterstained with hematoxylin, in the CTL, CF, HFD, and HFD + CF groups. Bar = 50 μm. (H) Quantitative analysis of Pex5-positive granules. Insets: a higher magnification of positive granules in the HFD = CF group (A,C,E,G). Data represent a box-and-whisker plot (red cross, mean; blue dots, outliers). Group: CTL, rats received control diet (Blue); CF, rats received control diet mixed with clofibrate (Yellow); HFD, rats received high-fat diet (Light green); HFD + CF, rats received high-fat diet mixed with clofibrate (Light red). Different letters indicate significant differences between groups (p < 0.05, significantly different by Tukey’s or Steel–Dwass multiple comparison test).\n\nFigure 3: Figure 3. Representative TEM images of peroxisome and phagophores of hepatocytes. (A,B) Peroxisomes (P), mitochondria (M), and phagophore (Pha) in the CF group. An organelle, possibly peroxisome captured by phagophore (sequestered membranes), indicating phagophore expansion. (C,D) Peroxisomes, mitochondria, phagophore, and autolysosomes (L) in the HFD + CF group. Autolysosomes consist of organelles and lysosomes. TEM, transmission electron microscopy. Bar = 200 (B,D), 500 nm (A) and 1.0 μm (C).\n\nFigure 4: Figure 4. Representative images and qualitative analyses of GST-P-positive foci of rats. (A) GST-P-positive foci, counterstained with hematoxylin, in the CTL, CF, HFD, and HFD + CF groups. Bar = 100 μm. Box plot of number (B) and area (C) of GST-P-positive foci. (D) Distribution of GST-P-positive foci in each size and cumulative curve of GST-P-positive foci. Data represent a box-and-whisker plot (red cross, mean; yellow dots, outliers) (B,C). Group: CTL, rats received control diet (Blue); CF, rats received control diet mixed with clofibrate (Yellow); HFD, rats received high-fat diet (Light green); HFD + CF, rats received high-fat diet mixed with clofibrate (Light red). Different letters indicate significant differences between groups (p < 0.05, significantly different by Tukey’s or Steel–Dwass multiple comparison test). Kolmogorov–Smirnov test indicated that significant increases were detected between the CTL/CF/HFD and HFD + CF groups (p < 0.0083, modified with Bonferroni correction).\n\nFigure 5: Figure 5. Gene expression analysis on autophagy in the liver. Atg3, Atg5, and Atg7 are genes initiating phagophore formation, binding with the product of Lc3, a gene for autophagosome formation. P62 and Nbr1 are genes of receptors for cargos including damaged peroxisomes. Lamp1 and Lamp2 are genes of lysosome membrane proteins. Pex2, Pex5, and Pex4 are genes for damaged peroxisomes, leading to pexophagy. Data represent a box-and-whisker plot (red cross, mean; blue dots, outliers). Group: CTL, rats received control diet (Blue); CF, rats received control diet mixed with clofibrate (Yellow); HFD, rats received high-fat diet (Light green); HFD + CF, rats received high-fat diet mixed with clofibrate (Light red). Different letters indicate significant differences between groups (p < 0.05, significantly different by Tukey’s or Steel–Dwass multiple comparison test)."
      }
    ]
  },
  {
    "id": "PMC11673738_multi_2",
    "image": [
      "images/PMC11673738-f6.png",
      "images/PMC11673738-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Peroxisome Proliferator Activator α Agonist Clofibrate Induces Pexophagy in Coconut Oil-Based High-Fat Diet-Fed Rats\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Gene expression analysis on lipid metabolism in the liver. Fasn and Scd1 are genes regulating palmitate synthesis from malonyl CoA and palmitoleate and oleate synthesis from palmitate and stearate, respectively. Srebf1 is a transcription factor gene for Fasn and Scd1. Apob is a gene of a product that plays a role in fatty acid efflux. Acox1 and Acox2 are genes regulating β-oxidation. Ppara and Pparg are transcription factor genes regulating β-oxidation and lipid metabolism. Abca1 is a gene that plays a role in cholesterol efflux. Green arrows indicate lipid metabolic pathways, and dashed arrows indicate data associated with those pathways. Data represent a box-and-whisker plot (red cross, mean; blue dots, outliers). Group: CTL, rats received control diet (Blue); CF, rats received control diet mixed with clofibrate (Yellow); HFD, rats received high-fat diet (Light green); HFD + CF, rats received high-fat diet mixed with clofibrate (Light red). Different letters indicate significant differences between groups (p < 0.05, significantly different by Tukey’s or Steel–Dwass multiple comparison test).\n\nFigure 7: Figure 7. Gene expression analysis on antioxidant response in the liver. Sod1, Sod2, and Sod3 are genes of enzymes synthesizing hydrogen peroxide from superoxide. Gpx1 is a gene of an enzyme synthesizing hydrogen oxide from hydrogen peroxide. Catalase is a gene of an enzyme that synthesizes hydrogen oxide and oxygen from hydrogen peroxide. Green arrows indicate antioxidant responses and dashed arrows indicate data associated with those responses. Data represent a box-and-whisker plot (red cross, mean; blue dots, outliers). Group: CTL, rats received control diet (Blue); CF−, rats received control diet mixed with clofibrate (Yellow); HFD, rats received high-fat diet (Light green); HFD + CF, rats received high-fat diet mixed with clofibrate (Light red). Different letters indicate significant differences between groups (p < 0.05, significantly different by Tukey’s or Steel–Dwass multiple comparison test)."
      }
    ]
  },
  {
    "id": "PMC11702540_multi",
    "image": [
      "images/PMC11702540-f1.png",
      "images/PMC11702540-f2.png",
      "images/PMC11702540-f3.png",
      "images/PMC11702540-f4.png",
      "images/PMC11702540-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"FAF2 is a bifunctional regulator of peroxisomal homeostasis and saturated lipid responses\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Experimental design of the genome-wide CRISPR/Cas9 knockout viability screen. Cells were treated with BSA or 500 μM PA for 14 days to identify genetic knockouts that sensitize or protect cells from PA-induced toxicity (P<0.05). (B) Correlation plot showing reproducibility of screen hits among replicates 1 and 2 of the CRISPR knockout viability screen treated with BSA or 500 μM PA. (C) Volcano plot of screen hits in epithelial cells. All genes were plotted for their Log2-fold change (Log2FC) enrichment in PA versus BSA conditions and significance level (−Log10(P)). (D) Gene set enrichment analysis (GSEA) of PA screen hits showing select KEGG pathways that are most significantly enriched or depleted in epithelial cells. FDR<25%. (E) Enrichment analysis of GO terms comparing significant hits from PA screens in epithelial cells or K562 leukemia cells identifies unique lipotoxicity modulators between cell types. The clustered network plot was generated using clusterProfiler with p-adjusted value cutoff adjP<0.25. Correction for multiple testing was performed using the Benjamini-Hochberg method. The gene count of a node is the number of genes within each GO term.\n\nFigure 2: Figure 2. (A) GSEA analysis of gene knockouts that enrich or deplete in PA conditions shows high enrichment of peroxisomal processes. GSEA normalized enrichment scores (NES) are displayed for differentially enriched sets of guides; gene sets include KEGG, GOBP, and REACTOME pathway entries. The size of the data points corresponds to the NES. (B) Top-ranking enriched guides that contributed to the KEGG peroxisomal gene set are significantly KO-protective in epithelial cells (black) but not K562 leukemia cells (gray). (C) Peroxisomal genes are organized by their functional process with red indicating genes that are KO protective and blue indicating genes that are KO sensitizing. Genes with a black outline indicate P<0.05 in the PA screen. (D) FAF2 and ether lipid synthesis enzymes lie at the intersection of lipid and peroxisomal biology. Genes are plotted by coessentiality scores with peroxisomal biogenesis factors (x-axis) and enrichment in the PA screen (y-axis). Correlation with peroxisomal biogenesis factors was calculated as a peroxisomal score, the average Pearson correlation score of each gene vs PEX genes (DepMAP CRISPR, Chronos). (E) The Log2 enrichment (y-axis) of all genes that were significantly enriched in the PA screen plotted against enrichment in cellular peroxisomal IP fractions (x-axis). Multiple unpaired t-tests with two-stage step up (Benjamini correction FDR=1%) was calculated for peroxisomal enriched samples compared to control IP. Ether lipid synthesis genes and FAF2 are enriched in both datasets. (F) Loss of peroxisomal ether lipid synthesis enzymes or FAF2 protects cells from PA-induced toxicity over a five day growth period. Cells were treated with BSA or 125 uM PA for five days and measured for cell death using propidium iodide (PI) dye. ****p<0.0001. Ordinary two-way ANOVA with Tukey’s multiple comparisons test, with a single pooled variance.\n\nFigure 3: Figure 3. (A) Volcano plots of Log2 fold change (x-axis) plotted against −Log10(adjP) significance (y-axis) of normalized proteins in FAF2 KO, AGPS KO, and GNPAT KO cells compared to wildtype cells. (B) Hierarchical clustering of proteomics revealed 3 distinct clusters of proteins commonly changed between all KO cell lines. Log2 fold change (Log2FC) was calculated for normalized protein intensity values of knockout samples versus the average of wildtype cells, with proteins increased in KO samples (in red) or decreased (in blue). (C) 84 proteins with significantly altered abundance in all three KO cell lines were identified. (D) DAVID GO functional clustering highlights overrepresented processes that are commonly enriched or depleted across all three KO cell lines. We conducted functional enrichment of biological processes of proteins belonging to the clusters identified in Fig 3B. Adjusted Benjamini values (−Log10(adjP)) are reported for discovered processes. (E) Immunofluorescence imaging of peroxisomal proteins, AGPS, ABCD3, and catalase (CAT) in wildtype (WT) and FAF2 KO cells. ***p<0.001. Ordinary two-way ANOVA with Šídák’s multiple comparisons test. Scale bar = 50 μm. (F) The mean difference between experimental groups and wild-type was calculated to determine proteins that are changed in the KO cell lines. Genetic disruption resulted in decreased abundance of the proteins encoded by the corresponding targeted genes (FAF2, GNPAT, AGPS) as well as some commonly altered proteins (FAR1, S14L1, and ABCD3). (G) Commonly altered protein levels in KO cell lines. Significantly increased proteins are shown in red while significantly decreased proteins are shown in blue (size indicates −Log10(adjP)).\n\nFigure 4: Figure 4. (A) Schematic representing essential genes in the ether lipid synthesis pathway. (B) Volcano plots showing Log2 fold change of normalized lipid intensities in peroxisomal knockout cells show a decrease in plasmenyl lipid species compared to wildtype cells treated with PA. Dotted line shows cutoff for lipid fold changes that are significant at p<0.05. (PC=phosphatidylcholine; PS=phosphatidylserine; PA=phosphatidic acid; LPC=lysophosphatidylcholine; LPE=lysophosphatidylethanolamine; PE=phosphatidylethanolamine; TG=triacylglycerol; DG=diacylglycerol; Plasmenyl-PC=plasmenyl-phosphatidylcholine; Plasmenyl-PE=plasmenyl-phosphatidylethanolamine). (C) Plasmenyl-PEs and PCs are globally downregulated in PA-treated FAF2 and peroxisomal knockout cells compared to wildtype cells. (D) Heatmap of various lipid species’ Log2 fold changes (Log2FC) across genotypes showing a decrease in ether lipid species in peroxisomal knockout cells, which is reversible with ether lipid treatment, but not ester lipid. Cells were treated with PA+DMSO, PA+ether lipid (EL) intermediate (1-O-hexadecyl-sn-glycerol), or PA+ester lipid (ES) (dl-a-palmitin) as a control.\n\nFigure 5: Figure 5. (A) Schematic of the FAF2/UBXD8 hairpin-anchored protein and FAF2 domain deletion constructs. (B) Western blot of FAF2 in WT or FAF2 KO cells transduced with full or domain-deleted (ΔUBX, ΔUAS, or ΔUBA domain) myc-tagged FAF2 constructs. (C) Western blots of peroxisomal proteins AGPS, GNPAT, and PEX10 in WT, KO, and KO-cells with re-expressed full or domain-deleted FAF2 constructs (ΔUBX, ΔUAS, or ΔUBA domain) show that UBX and UAS domains are necessary to restore peroxisomal protein abundance. (D) (Left) CAT localization was quantified by training the dataset with Harmony high-content imaging software on WT and FAF2 KO phenotypes. Cells in each sample were then assigned to either a WT or FAF2 KO phenotype and percentage of results are displayed. N=3 biological replicates per genotype, quantification is of one representative experiment. (Right) Immunofluorescence images (60X) show that CAT punctae and AGPS protein abundance are dependent on the FAF2 UBX and UAS domains. Scale bar = 50 μm. (E) PA-induced toxicity is dependent on the UBX and UAS domains of FAF2. Cell death was quantified by percentage of propidium iodide (PI) positive cells. ****p<0.0001. Ordinary two-way ANOVA with Tukey’s multiple comparisons test."
      }
    ]
  },
  {
    "id": "PMC11708211_multi",
    "image": [
      "images/PMC11708211-f1.png",
      "images/PMC11708211-f2.png",
      "images/PMC11708211-f3.png",
      "images/PMC11708211-f4.png",
      "images/PMC11708211-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Glial peroxisome dysfunction induces axonal swelling and neuroinflammation in Drosophila\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomes are enriched in the glial and neuronal tissues of the abdominal VLM in adult Drosophila. a) Schematic diagram showing adult Drosophila abdominal muscles and axon innervation of motor neurons. b) Representative image showing neuronal tissues of the A3 abdominal VLM that are labeled with anti-horseradish peroxidase (HRP) antibodies. The dashed box indicates the area of interest used for axonal area and volume quantifications. c) Representative image showing the presence of peroxisomes in the axon of motor neurons. Peroxisomes are labeled with anti-Pmp70 antibodies (white arrow). Glia are labeled with anti-repo antibodies, while neuronal tissues are labeled with anti-HRP antibodies.\n\nFigure 2: Figure 2. Glia-specific KD of Pex5 causes axonal swelling of peripheral motor neurons and impairs locomotion activities. a) Representative images showing axon morphology in 2 wild-type flies (the left and middle panels) and glia-specific Pex5 RNAi flies (the right panel). Two control crosses are shown, repo-GAL4 > ywR and repo-GAL4 > P(CaryP)attp40. Axons are labeled with anti-HRP antibodies. b, c) Quantification of axonal area and volume in flies with glia-specific Pex5 KD. N = 20, 1-way ANOVA. d) Climbing activity of glia-specific Pex5 KD flies at 2 different ages. About 5–10 vials (10 females per vial) were tested per group. N = 5–10, 1-way ANOVA. *P < 0.05, **P < 0.01, **P < 0.001, and ****P < 0.0001.\n\nFigure 3: Figure 3. Adult-onset glia-specific KD of Pex5 induces axonal swelling. a) Representative images showing axon morphology in wild-type (−RU, the left panel) and adult-onset glia-specific Pex5 KD flies (+RU, the right panel). Axons are labeled with anti-HRP antibodies. The repo-GS-GAL4 driver is used to knock down Pex5 in adult glial cells. Mifepristone (RU486) is used as the chemical inducer. Scale bar: 1 μm. b, c) Quantification of axonal area and volume in flies with adult-onset glia-specific Pex5 KD. N = 20, Student's t-test. *P < 0.05, **P < 0.01, **P < 0.001, and ****P < 0.0001.\n\nFigure 4: Figure 4. KD of Pex5 in specific glial subtypes induces axonal swelling. a) Representative images showing axon morphology in wild-type (the left panel) and wrapping glia-specific Pex5 KD (the right panel). Axons are labeled with anti-HRP antibodies. b) Representative images showing axon morphology in subperineurial/perineurial glia-specific KD of Pex5. Scale bar: 1 μm. c, d) Quantification of axonal area and volume in flies with wrapping glia- or subperineurial/perineurial glia-specific Pex5 KD. N = 5–20, 1-way ANOVA. *P < 0.05, **P < 0.01, **P < 0.001, and ****P < 0.0001.\n\nFigure 5: Figure 5. Impairment of VLCFA beta-oxidation and ether lipid biosynthesis in glial cells induces axonal swelling. a) Representative images showing axon morphology in attp40 control (the left panel) and glia-specific KD of peroxisome matrix enzymes, Acox1, Gnpat, and Cat. Axons are labeled with anti-HRP antibodies. Scale bar: 1 μm. b, c) Quantification of axonal area and volume in flies with glia-specific KD of Acox1, Gnpat, and Cat. N = 15–20, 1-way ANOVA. *P < 0.05, **P < 0.01, **P < 0.001, and ****P < 0.0001."
      }
    ]
  },
  {
    "id": "PMC11708211_multi_2",
    "image": [
      "images/PMC11708211-f6.png",
      "images/PMC11708211-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Glial peroxisome dysfunction induces axonal swelling and neuroinflammation in Drosophila\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Defective peroxisomal import upregulates pro-inflammatory cytokine upd3 in glia, and motor neuron-specific activation JAK-STAT signaling increases axonal swelling. a) Representative images showing upd3-LacZ activity in wild-type (the top row) and glia-specific KD of Pex5 (the bottom row). Axons are labeled with anti-HRP antibodies. Scale bar: 1 μm. b) Quantification of LacZ intensity between control and glial Pex5 KD. N = 10–15, unpaired 2-tailed Student's t-test. c) Representative images showing axon morphology in wild-type (the left panel) and glia-specific overexpression of upd3 (the right panel). Axons are labeled with anti-HRP antibodies. Scale bar: 1 μm. d, e) Quantification of axonal area and volume in flies with glia-specific upd3 overexpression. N = 6–9, Student's t-test. f) Representative images showing axon morphology in wild-type (the left panel) and motor neuron-specific expression of hopTuml (the right panel). Axons are labeled with anti-HRP antibodies. Scale bar: 1 μm. g, h) Quantification of axonal area and volume in flies with motor neuron-specific hopTuml expression. N = 20–30, Student's t-test. *P < 0.05, **P < 0.01, **P < 0.001, and ****P < 0.0001.\n\nFigure 7: Figure 7. The proposed model shows that impaired glial peroxisomal import function induces the production of pro-inflammatory cytokine upd3, which nonautonomously activates JAK-STAT in motor neurons and causes axonal swollen and locomotion defects."
      }
    ]
  },
  {
    "id": "PMC11711287_multi",
    "image": [
      "images/PMC11711287-f1.png",
      "images/PMC11711287-f2.png",
      "images/PMC11711287-f3.png",
      "images/PMC11711287-f4.png",
      "images/PMC11711287-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Consuming a modified Mediterranean ketogenic diet reverses the peripheral lipid signature of Alzheimer’s disease in humans\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Forest plot highlighting significant lipid classes associated with the 6-week MMKD (n = 20) from a linear mixed model. Units are in fold change of lipid concentration from baseline with 95% confidence intervals. Light grey, uncorrected p value > 0.05, dark grey, uncorrected p value < 0.05, blue, Benjamini-Hochberg corrected p value < 0.05. b–e Relative concentration of each lipid class for each participant at baseline (grey) and follow-up (red). Horizontal bars represent mean concentration for baseline and follow up with 95% confidence intervals. Exact p-values and coefficients are in Supplementary Data 1.\n\nFigure 2: Figure 2. a Associations of lipid species with 6-week MMKD (n = 20) obtained from a linear mixed model. Units are in fold change of lipid concentration from baseline with 95% confidence intervals. Light grey, corrected p value > 0.05, dark grey, Benjamini-Hochberg corrected p value < 0.05, blue, top 10 species ranked by p-value. b–d Volcano plot highlighting specific lipid classes associated with MMKD intervention, light grey circles, Benjamini-Hochberg corrected p value > 0.05, bolded grey circles, Benjamini-Hochberg corrected p value < 0.05, blue highlighted circles, class specific species that are Benjamini-Hochberg corrected p value < 0.05. FA: Fatty Acid, NL: Neutral Loss, Ox: Oxidized. For the spelling of lipid species abbreviations, see Fig. 1. Exact p values and coefficients are in Supplementary Data 2.\n\nFigure 3: Figure 3. A heatmap highlighting lipid associations with MMKD intervention (n = 20) stratified using an interaction term for cognitive group (a), APOE genotype (b) and sex (c). Reference denotes the unadjusted linear mixed model on lipid associations with MMKD intervention. Black diamonds, nominal p value < 0.05, black block, nominal interaction p value < 0.05. Both nominal and corrected p-values are in Supplementary Datas 3–5. APOE: Apolipoprotein E, CN: Cognitively Normal, MCI: Mild Cognitive Impairment, MMKD: Modified Mediterranean-Ketogenic Diet.\n\nFigure 4: Figure 4. A scatter plot correlating lipid class associations with MMKD intervention and Alzheimer’s disease (data previously reported Huynh et al. 2020). a Lipid classes nominally associated with both MMKD and prevalent/existing AD (highlighted in blue, class totals, meta-analysis of both AIBL and ADNI) and b Lipid classes nominally associated with both MMKD and incident/future risk of AD (highlighted in red). Exact p-values and coefficients are in Supplementary Data 6. AD: Alzheimer’s Disease, Hex2Cer: Dihexosylceramide, Hex3Cer: Trihexosylceramide, LPE: Lysophosphatidylethanolamine, MMKD: Modified Mediterranean-Ketogenic Diet, NL: Neutral Loss, PC: Phosphatidylcholine, PE: Phosphatidylethanolamine, SHexCer: Sulfatide, TG: Triglyceride.\n\nFigure 5: Figure 5. A Pearson correlation between changes in the total of each lipid class with changes in different biochemical, cognition and CSF markers. Black diamond, p < 0.05. n = 20 for all correlations except for weight (n = 17), fasting glucose (n = 17), fasting ketones (n = 16), I&D Story recall (n = 19), phosphorylated tau (n = 19), total tau (n = 19), amyloid ratio (n = 19), neurofilament light (n = 13), neurogranin (n = 9), ache (n = 13), bche (n = 13) and their ratio (n = 13). ADAS-COG12: Alzheimer’s Disease Assessment Scale-Cognitive, Cog: Cognition, CSF: Cerebrospinal Fluid, FCSRT: Free and Cued Selective Reminding Test, HbA1C: Hemoglobin A1c, HDL: High-Density Lipoprotein, I&D Story Recall: Immediate and Delayed Story Recall composite, LDL: Low-Density Lipoprotein, MMKD: Modified Mediterranean-Ketogenic Diet, VLDL: Very-Low-Density Lipoprotein. Exact coefficients are in Supplementary Data 7."
      }
    ]
  },
  {
    "id": "PMC11725563_multi",
    "image": [
      "images/PMC11725563-f1.png",
      "images/PMC11725563-f2.png",
      "images/PMC11725563-f3.png",
      "images/PMC11725563-f4.png",
      "images/PMC11725563-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The interconnective role of the UPS and autophagy in the quality control of cancer mitochondria\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Protein and organellar quality control mechanisms of mitochondria. a The UPS: E3 ubiquitin ligases, such as MARCH5, facilitate the ubiquitination of mitochondrial OMM proteins, thereby tagging them for proteasomal degradation. b Mitochondrial chaperones and proteases: These proteins play a crucial role in maintaining the quality and functionality of mitochondrial proteins. c Mitochondrial morphology: This is dynamically regulated through the processes of fission and fusion. d Mitophagy: This process selectively eliminates dysfunctional, excess, or aged mitochondria to maintain cellular health. e Mitochondrial biogenesis: This process regulates the number and functionality of mitochondria to fulfill the energy and metabolic requirements of the cell\n\nFigure 2: Figure 2. Orchestration of protein homeostasis in inner mitochondrial compartments by mitochondrial chaperones and mitoproteases. Precursor proteins, synthesized in the cytosol, enter mitochondria via the translocase of the outer membrane (TOM) complex and the presequence translocase (TIM23) complex. The membrane potential (Δψm) drives protein translocation through TIM23 into the matrix and inner membrane. Mitochondrial HSP70 (mtHSP70), part of the presequence translocase-associated motor (PAM), completes ATP-dependent import into the matrix. The mitochondrial processing peptidase (MPP) removes the presequence, followed by protein folding mediated by chaperones mtHSP70 and HSP60-HSP10. Misfolded proteins resulting from impaired chaperone function are degraded by matrix proteases CLPXP and LON. The inner mitochondrial membrane (IMM) houses two AAA proteases: the i-AAA protease degrades proteins in the intermembrane space (IMS) and outer mitochondrial membrane (OMM), while the m-AAA protease targets inner membrane and matrix proteins. This quality control system, encompassing import, folding, and degradation mechanisms, is crucial for maintaining mitochondrial function and cellular health\n\nFigure 3: Figure 3. The damaged mitochondria turnover. a Mitochondrial dynamics: fusion and fission dilute damaged parts and remove dysfunctional mitochondria. b Mitophagy: a dedicated mechanism to eliminate damaged mitochondria. c Mitocytosis: a novel quality control pathway in migrating cells where damaged mitochondria are encapsulated into “migrasomes” budding from elastic fibers and exported from the cell. d Mitochondrial-derived vesicles (MDVs): oxidative stress stimulates special vesicles to remove damaged materials from stressed mitochondria. e Mitochondrial biogenesis: generating new mitochondria to replace lost ones\n\nFigure 4: Figure 4. Crosstalk between UPS and mitophagy promotes mitochondria homeostasis. Left: The UPS and mitoproteases coordinated with mitochondrial fusion promotes the efficient and rapid resolution of mild mitochondrial damage. As the mitochondrial membrane potential gradually decreases, the emphasis on quality control mechanisms shifts towards fission and mitophagy. Right top: The UPS primarily degrades soluble OMM proteins and regulates proteins involved in mitochondrial dynamics such as MFN1/2, thereby modulating mitochondrial fusion and fission. Under normal conditions, PARL stimulates retro-translocation and degradation of the PINK1 kinase, which is associated with mitophagy. On import into mitochondria, OPA1 can be cleaved by the YME1L and metalloproteinase OMA1, which results in the formation of short and long OPA1 forms. Right middle: The higher membrane potential (higher △Ψm) tends to fuse, mediated by MFN1/2 and L-OPA1. In contrast, mitochondria with a lower membrane potential (lower △Ψm) tend to undergo fission and mitophagy. DRP1, binding to receptors on OMM, executes fission. S-OPA1 generated by OMA1 further promotes this process. Moreover, Parkin plays a dual role—regulating mitochondrial dynamics proteins as E3 ligases while mediating mitophagy. Right below: The PINK1/Parkin-dependent mitophagy is the main surveillance mechanism for damaged mitochondria, and PINK1 recruits Parkin to ubiquitinate OMM proteins in response to impaired membrane potential. These proteins are recognized by selective autophagy receptors like OPTN and NDP52, which damage mitochondria to autophagosomes. In PINK1/Parkin-independent mitophagy, BNIP3L/FUNDC1/PHB2/CL can directly interact with LC3 to induce the removal of dysfunctional mitochondria\n\nFigure 5: Figure 5. Mitochondrial quality control (MQC) research over the past decade. Over the past decade, MQC research has made significant progress, with many important discoveries that have significantly advanced our understanding of this critical cellular process. However, owing to space constraints, this review could not cover all the key milestones [31–33, 38, 93, 108, 120, 194–218]"
      }
    ]
  },
  {
    "id": "PMC11727801_multi",
    "image": [
      "images/PMC11727801-f1.png",
      "images/PMC11727801-f2.png",
      "images/PMC11727801-f4.png",
      "images/PMC11727801-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Optical coherence tomography angiography reveals abnormal retinal vascular density and perfusion in patients with X-linked adrenoleukodystrophy: a cross-sectional study\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Macular and peripapillary partitioning and stratification methods. a The right eye macular is segmented for the ETDRS segmentation network. The peripheral ring and pericentral ring are divided into four quadrants: S, I, N and T. The red and green lines are reference auxiliary lines. b Segmenting the left eye macular for the ETDRS segmentation network. c The right eye peripapillary region is segmented for the ONH segmentation network, and the surrounding area of the peripapillary region is divided into eight sectors: NS, NI, IN, IT, TI, TS, ST and SN. d Segmenting the left eye optic disc for the ONH segmentation network. e The macular is divided into superficial and deep layers: SVC: superficial vascular complex; DVC: deep vascular complex. f The peripapillary layer is divided into superficial and deep layers\n\nFigure 2: Figure 2. Fundus photography and retinal vascular density maps of both eyes of patients and healthy controls. a Fundus photography of both eyes of a patient. b Fundus photograph of a healthy control. c Vascular density map of the macular SVC of a patient. d Vascular density map of the macular SVC of a healthy control\n\nFigure 4: Figure 4. Comparative map and p value map of vascular density. The values in the sector are the differences in the means or medians between the symptomatic group and the other two groups. S symptomatic group, C healthy control group, L less symptomatic group\n\nFigure 5: Figure 5. Comparative map and p value map of the perfusion area. The values in the sector are the differences in the means or medians between the symptomatic group and the other two groups. S symptomatic group, C healthy control group, L less symptomatic group"
      }
    ]
  },
  {
    "id": "PMC11742001_multi",
    "image": [
      "images/PMC11742001-f1.png",
      "images/PMC11742001-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"AP4B1 hypomorphic variants cause autosomal recessive adult-onset ataxia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Molecular spectrum associated with AP4B1-related adult-onset ataxia in this series. A Family pedigrees are depicted for each affected individual, in addition with the confirmation of AP4B1 compound heterozygous variants in probands using Sanger sequencing. B Linear representation of AP4B1 (NM_001253852.3), featuring the localization of reported variants. Loss-of-function and novel hypomorphic missense variants are highlighted in red and orange, respectively. Variant annotation was conducted using GRCh37/hg19 genome assembly\n\nFigure 2: Figure 2. Brain MRI of affected individuals. Sagittal T1-weighted images show mild cerebellar atrophy in all three affected individuals. No morphological abnormality of corpus callosum, ventriculomegaly nor white matter loss, ordinarily associated with SPG47, were detected in this series"
      }
    ]
  },
  {
    "id": "PMC11764017_multi",
    "image": [
      "images/PMC11764017-f2.png",
      "images/PMC11764017-f1.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Modelling Peroxisomal Disorders in Zebrafish\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. Schematic overview of predicted functions of Pex proteins and peroxisomal membrane proteins in zebrafish. Matrix protein import: Following translation on free ribosomes, cargo proteins that contain the peroxisomal targeting signals (PTS1 or PTS2) bind their respective cytosolic receptors, Pex5 or Pex7 (Pex proteins are labelled as numbers in the figure). For PTS2 import, accessory factors like the long isoform of Pex5 (Pex5L) are required. The receptor-cargo complexes dock at the peroxisomal membrane via Pex13 and Pex14, followed by translocation into the matrix through a dynamic translocon, Pex2, Pex10, and Pex12. Here, a pore-like structure of Pex13/Pex14 is suggested, which allows the import of completely folded, co-factor bound proteins. Export of the receptor back to the cytosol involves ubiquitination (Ub) and extraction by an AAA–ATPase complex, Pex1, and Pex6, with Pex6 interacting with Pex26. Membrane assembly and PMP insertion: The integration of peroxisomal membrane proteins (PMPs) with targeting signals (mPTS) is mediated by Pex19, Pex3, and Pex16. Pex19 acts as a cycling receptor/chaperone, binding PMPs in the cytosol and interacting with Pex3 at the peroxisomal membrane. Growth and division, proliferation: Pex11α, Pex11β, and Pex11γ regulate peroxisome size and number. Pex11β remodels the peroxisomal membrane and recruits the fission machinery, including the membrane adaptors Mff and Fis1, which engage with the dynamin-like GTPase Dnm1l to drive fission. Motility and inheritance: In mammals, peroxisomes move along microtubules via Rhot/Miro proteins, which serve as membrane adaptors for microtubule-dependent motor proteins. Inter-organelle contacts: Peroxisome-ER membrane contact sites are mediated by Acbd5 and Acbd4, which bind ER-resident Vap proteins. Fatty acid transport: Fatty acids enter peroxisomes through ABC transporters (Abcd 1-3), and ACBD5 captures VLCFAs for transport in mammals. Other peroxisomal membrane proteins: Zebrafish peroxisomal membrane proteins include Far1 (fatty acyl-CoA reductase 1, involved in ether lipid biosynthesis), Mavs (mitochondrial antiviral signalling protein, involved in innate immune response), Usp30 (ubiquitin-specific protease 30, a deubiquitinase involved in the turnover/pexophagy of peroxisomes), and Trim37 (tripartite motif-containing protein 37, an E3 ubiquitin-protein ligase that aids in Pex5-mediated protein import). Some proteins may localise to both peroxisomes and mitochondria (marked with asterisks). Abbreviations: Pex, peroxin; PMP, peroxisomal membrane protein; mPTS, membrane protein targeting signal (adapted from [21]).\n\nFigure 1: Figure 1. Schematic overview of the peroxisomal fatty acid beta-oxidation pathway in D. rerio. Peroxisomes metabolise fatty acids (FA) through a four-step beta-oxidation process; 1. Dehydrogenation: Catalysed by multiple acyl-CoA oxidases with different substrate specificities. In humans, ACOX2 specifically oxidises C27 bile acid intermediates (D/THCA), but this enzyme is absent in zebrafish (see also Table 1). 2. Hydration: Enzymatic activity is mediated by two bifunctional proteins (L-BP, D-BP) with enoyl-CoA hydratase and 3-hydroxy-acyl-CoA dehydrogenase functions. 3. Second dehydrogenation: Also mediated by the bifunctional proteins. 4. Thiolytic cleavage: Carried out by various thiolases, including Acca1 and Scpx. Additionally, peroxisomes utilise accessory enzymes, such as those involved in fatty acid alpha-oxidation, to modify the acyl-CoA esters of those fatty acids that cannot directly enter the beta-oxidation pathway (e.g., phytanic acid) (see text for details) (adapted from [18]). These enzymes ensure the effective metabolism of diverse fatty acids. Acaa1, acetyl-Coenzyme A acyltransferase 1; DCA, dicarboxylic acid; D/THCA, di-/tri-hydroxycholestanoic acid; Scpx, sterol carrier protein x."
      }
    ]
  },
  {
    "id": "PMC11791027_multi",
    "image": [
      "images/PMC11791027-f1.png",
      "images/PMC11791027-f2.png",
      "images/PMC11791027-f3.png",
      "images/PMC11791027-f2-2.png",
      "images/PMC11791027-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cholesterol ensures ciliary polycystin-2 localization to prevent polycystic kidney disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A, B) Ciliary localization of PC1 (A) and PC2 (B) in quiescent G0-phase WT and Pex14−/− mIMCD3 cells. (A, B) WT cells were treated with methyl-β-cyclodextrin, and the Pex14−/− cells were incubated with cholesterol (cholesterol/methyl-β-cyclodextrin complex), and then, the cells were immunostained with anti-PC1 (green), anti-acetylated tubulin (magenta), and FGFR1OP (cyan) antibodies (A), or with anti-PC2 (green), anti-ARL13B (magenta), and anti-γ-tubulin (cyan) antibodies (B). Scale bars, 1 μm. (C) Quantification of the PC1 (left) and PC2 (right) intensities at primary cilia in WT cells with or without MβCD treatment and Pex14−/− cells with or without cholesterol treatment (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 50–54 cells per experiment). Graphs show the median and quartiles. (D) Localization of cholesterol in primary cilia. The WT and Pex14−/− cells were stained with a cholesterol probe, filipin III (green), anti-acetylated tubulin (magenta), and FGFR1OP (cyan) antibodies. Scale bars, 1 μm. (E) Filipin III ciliary intensity in WT cells with or without MβCD treatment and Pex14−/− cells with or without cholesterol treatment (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 50–53 cells per experiment). The graph shows the median and quartiles. (F) Spheroid formation in the WT and Pex14−/− mIMCD3 cells grown in three-dimensional culture. After the formation of spheroids, Pex14−/− cells were treated with cholesterol or left untreated. Then, the cells were stained for β-catenin (green), ZO-1 (magenta), acetylated tubulin (white), and DAPI (cyan). Scale bars, 10 μm. (G) Ratio of lumen area to spheroid area in WT cells and Pex14−/− cells with or without cholesterol treatment (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 45–61 spheroids per experiment). The graph shows the median and quartiles.\n\nFigure 2: Figure 2. (A, B) Quiescent G0-phase Pkd2−/− mIMCD3 cells cotransfected with PC2-AcGFP (white) and DsRed2-PACT (green) and treated with (B) or without methyl-β-cyclodextrin (A) were imaged live for 20 min by confocal microscopy. Sum intensity projections of z-stack images are shown. Scale bars, 2 μm.\n\nFigure 3: Figure 3. (A) Western blot analysis showing depletion of Pex 14 in the Pex14−/− mIMCD3 cell clones. α-Tubulin served as a loading control. (B) Quantification of ciliogenesis in Pex14−/− cells. The percentage of ciliated cells is presented as the mean ± SD (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 50 cells per experiment). (C) Schematic overview of the spheroid formation protocol. (D) Spheroid formation in the WT cells grown in three-dimensional culture. After the formation of spheroids, cells were treated with MβCD or cholesterol. Then, cells were stained for β-catenin (green), ZO-1 (magenta), acetylated tubulin (white), and DAPI (cyan). Scale bars, 10 μm. (E) Quantification of spheroidgenesis in Pex14−/− cells. The percentage of spheroids with a single lumen is presented as the mean ± SD (n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 52–73 spheroids per experiment). (F) Schematic illustration showing the measurement of spheroid and lumen size. Serial z-stack confocal images obtained were first analyzed in the number of lumens to evaluate the spheroidgenesis. Next, in spheroids with a single lumen, the xy-plane, which had the largest cross-sectional area of the spheroid, was determined by analyzing the series of the z-stack images of β-catenin. Finally, the spheroid area (β-catenin) and lumen area (ZO-1) were measured at the same plane. (G, H) Quantification of the spheroid size. (G, H) Lumen area (G) and spheroid area (H) were measured (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 45–61 spheroids with a single lumen per experiment). The graphs show the median and quartiles. (I) Ratio of lumen area to spheroid area in WT treated with MβCD or cholesterol (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 45–61 spheroids with a single lumen per experiment). The graph shows the median and quartiles.\n\nFigure 2: Figure 2. (A) Western blot analysis for pull-down assay. The lysates of HEK293T cells transiently expressing either Myc-tagged PC2 WT, PC2 W414G, or PC2 L517R mutant protein were precipitated with cholesterol-conjugated magnetic beads and analyzed by Western blotting using anti-Myc antibody. (B) Average current density changes in response to a voltage ramp from −100 to 100 mV in AcGFP-tagged PC2 variants. Current densities are calculated by dividing the individual current by membrane capacitance of the HEK293 cell. Current densities at −100 mV and 100 mV are shown on the right. Untransfected parent cells and PC2 R325Q–expressing cells were used as a negative control (Vien et al, 2020). Error bars represent the mean ± SEM (n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 22 [WT], 21 [L517R], 14 [W414G], 14 [R325Q], and 21 [untransfected parent] cells). (C) Ciliary localization of PC2 variants in quiescent G0-phase mIMCD3 cells. Cells were stained with anti-PC2 (green), anti-ARL13B (magenta), and anti-γ-tubulin (cyan) antibodies. Line-scan PC2 intensity of each primary cilium is shown in Fig S5D. Scale bars, 1 μm. (D) Quantification of the PC2 intensity at primary cilia in Pkd2-mutated cells (*P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 50–55 cells per experiment). The graph shows the median and quartiles.\n\nFigure 5: Figure 5. (A) Western blot analysis for pull-down assay. The lysates of HEK293T cells transiently expressing either Myc-tagged PC2 WT, PC2 W414G, or PC2 L517R mutant protein were precipitated with cholesterol-conjugated magnetic beads and detected by Western blot analysis using anti-Myc antibody, indicating that PC2 W414G possesses cholesterol-binding ability. (B) Confocal imaging of HEK293 stable cell lines expressing AcGFP-tagged PC2 WT, PC2 R325Q, PC2 W414G, or PC2 L517R mutant protein. A single slice from the confocal z-stack shows the localization of PC2-AcGFP to the plasma membrane (inset). Scale bars, 5 μm, 1 μm (inset). (C) Western blot analysis showing HEK293 stable cell lines expressing AcGFP-tagged PC2 WT, PC2 R325Q, PC2 W414G, or PC2 L517R mutant protein. α-Tubulin served as a loading control."
      }
    ]
  },
  {
    "id": "PMC11791027_multi_2",
    "image": [
      "images/PMC11791027-f6.png",
      "images/PMC11791027-f7.png",
      "images/PMC11791027-f3-2.png",
      "images/PMC11791027-f4.png",
      "images/PMC11791027-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cholesterol ensures ciliary polycystin-2 localization to prevent polycystic kidney disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Schematic diagram of the human PC2 structure. Pkd2 L517R is located in the S3 helix, and W414G in the TOP domain. (B) Targeting strategy for mouse Pkd2 L515R (L517R mutation of human PC2) knock-in using the CRISPR/Cas9 system. Silent mutations are indicated with lower-case letters. (C) Sanger sequencing of Pkd2WT/L515R-edited mIMCD3 cell clone, Pkd2L515R/L515R-edited mIMCD3 cell clone, Pkd2W412G/W412G-edited mIMCD3 cell clone, and Pkd2WT/WT cell. (D) RT–PCR confirmed correct splicing in Pkd2L515R/L515R-edited mIMCD3 cell clones. β-Actin served as a loading control. (E) Western blot analysis showing PC2 L515R expression in Pkd2L515R/L515R-edited mIMCD3 cell clones. α-Tubulin served as a loading control. (F) Western blot analysis showing PC2 W412G expression in Pkd2W412G/W412G-edited mIMCD3 cell clones. α-Tubulin served as a loading control. (G) Quantification of ciliogenesis in Pkd2-mutated cells. The percentage of ciliated cells are presented as the mean ± SD (n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 50 cells per experiment). (H) Total cellular cholesterol levels in the quiescent G0-phase Pkd2-mutated cells. The total cholesterol level was not altered in Pkd2L515R/L515R, Pkd2W412G/W412G, and Pkd2−/−edited cells. Results are presented as the mean ± SD (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments).\n\nFigure 7: Figure 7. (A, B) Aggregation of intracellular cholesterol outside primary cilia in PC2 mutant cells. (B) Cholesterol level is presented as the heat map of filipin III images (B). Scale bars, 10 μm. (C) Disruption of ciliary localization of the polycystin complex in Pkd1-knockout and Pkd2-knockout cells. Scale bars, 1 μm. (D) Line-scan measurements of ciliary PC2 fluorescence intensity from images shown in Fig 2C. PC2 signal is shown in green, and ARL13B signal is shown in magenta. (E) Ciliary localization of PC1 in Pkd2 L515R cells and Pkd2 W412G cells. The cells were immunostained with anti-PC1 (green), anti-acetylated tubulin (magenta), and FGFR1OP (cyan) antibodies. Scale bars, 1 μm. (F) Quantification of the PC1 intensities at primary cilia in Pkd2 mutated cells (****P < 0.0001; n.s., not significant: one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 50 cells per experiment). Graphs show the median and quartiles. (G) Line-scan measurements of ciliary PC2 and filipin III fluorescence intensity from images shown in Fig 3A. PC2, ARL13B, and filipin III signals are shown in green, magenta, and cyan, respectively.\n\nFigure 3: Figure 3. (A) Ciliary localization of PC2 variants in quiescent G0-phase mIMCD3 cells in a manner dependent on cholesterol. Cells were stained with filipin III (cyan), anti-PC2 (magenta), anti-acetylated tubulin (green), and anti-FGFR1OP (yellow) antibodies. Line-scan measurements of PC2 and filipin III intensity of each primary cilium are shown in Fig S5G. Scale bars, 1 μm. (B, C) Quantification of the filipin III intensity (B) and the PC2 intensity (C) at primary cilia in Pkd2-mutated cells. WT cells were treated with or without MβCD. Pkd2 L515R cells, Pkd2 W412G cells, and Pex14−/− cells were treated with water-soluble cholesterol (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 49–51 cells per experiment). The graph shows the median and quartiles. (D, E) Relationship between the ciliary PC2 and filipin III intensity. (D) r indicates the correlation coefficient (D). (E) Plots represent mean values (error bars, ± SD) (E).\n\nFigure 4: Figure 4. (A) Western blot analysis for the immunoprecipitation assay. The lysates of HEK293T cells transiently expressing either Myc-tagged PC2 W414G mutant or Halo-tagged Tulp3 protein or both proteins were precipitated with anti-Myc antibody–conjugated beads and analyzed by Western blotting using anti-Halo antibody. (B) Ciliary localization of PC2 variants in quiescent G0-phase mIMCD3 cells in a manner dependent on cholesterol. Cells were stained with filipin III (cyan), anti-PC2 (magenta), anti-acetylated tubulin (green), and anti-FGFR1OP (white) antibodies. Scale bars, 1 μm. (C, D) Quantification of the filipin III intensity (C) and the PC2 intensity (D) at primary cilia in Tulp3-mutated cells. WT cells were treated with or without MβCD. Pkd2 W412G cells, Tulp3−/− cells, and Pkd2 W412G/Tulp3−/− cells were treated with water-soluble cholesterol (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 48–52 cells per experiment). The graph shows the median and quartiles.\n\nFigure 10: Figure 10. (A) Western blot analysis for the immunoprecipitation assay. The lysates of HEK293T cells transiently expressing either the Myc-tagged PC2 W414G mutant or Halo-tagged Tulp3 protein or both proteins were precipitated with anti-Myc antibody–conjugated beads and analyzed by Western blotting using anti-Halo antibody. (B) Sanger sequencing of the Tulp3−/−-edited mIMCD3 cell clone and Pkd2W412G/W412G/Tulp3−/−-edited mIMCD3 clone. (C) Western blot analysis showing Tulp3 expression in Pkd2W412G/W412G-, Tulp3−/−-, and Pkd2W412G/W412G/Tulp3−/−-edited mIMCD3 clones. PC2 and α-tubulin served as a loading control. (D, E) Relationship between the ciliary PC2 and filipin III intensity. (E) r indicates the correlation coefficient (E). The plots represent mean values (error bars, ± SD). n = 3 independent experiments: 48–52 cells per experiment."
      }
    ]
  },
  {
    "id": "PMC11791027_multi_3",
    "image": [
      "images/PMC11791027-f5-2.png",
      "images/PMC11791027-f12.png",
      "images/PMC11791027-f6-2.png",
      "images/PMC11791027-f14.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cholesterol ensures ciliary polycystin-2 localization to prevent polycystic kidney disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 5: Figure 5. (A) Spheroid formation in Pkd2-mutated mIMCD3 cells grown in three-dimensional culture. After the formation of spheroids, cells were treated with or without cholesterol and then stained for β-catenin (green), ZO-1 (magenta), acetylated tubulin (white), and DAPI (cyan). Scale bars, 10 μm. (B) Lumen size in Pkd2-mutated cells with or without the cholesterol treatment (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 52–140 spheroids with a single lumen per experiment). The graph shows the median and quartiles. (C) Spheroid size in Pkd2-mutated cells with or without the cholesterol treatment (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 52–140 spheroids with a single lumen per experiment). The graph shows the median and quartiles. (D) Ratio of lumen area to spheroid area in Pkd2-mutated cells with or without the cholesterol treatment (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 52–140 spheroids with a single lumen per experiment). The graph shows the median and quartiles.\n\nFigure 12: Figure 12. (A) Quantification of spheroidgenesis in Pkd2 mutant cells. The percentage of spheroids with a single lumen is presented as the mean ± SD (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 150–152 spheroids per experiment). (B) Number of nuclei in the largest cross-sectional plane of spheroids of Pkd2-mutated cells with or without the cholesterol treatment (****P < 0.0001; n.s., not significant, one-way ANOVA with Tukey’s multiple comparison tests, n = 3 independent experiments: 52–140 spheroids with a single lumen per experiment). The graph shows the median and quartiles.\n\nFigure 6: Figure 6. (A, B, C, D, E, F) HE staining showed mouse fetus kidneys from Pkd2+/+ (A), Pkd2L515R/+ (B), and Pkd2L515R/L515R (C). Scale bars represent 500 μm. (A, B, C, D, E, F) Boxed areas in (A, B, C) are presented in (D, E, F). (F) Bowman’s lumen (asterisk) was notably enlarged in Pkd2L515R/L515R (F). Scale bars represent 100 μm. (G, H, I) Stereomicroscopic images show mouse fetus hearts from Pkd2+/+ (G), Pkd2L515R/+ (H), and Pkd2L515R/L515R (I). (I) Dextrocardia was observed in Pkd2L515R/L515R (I). The arrow and arrowhead indicate the apex of the heart and the outflow tract, respectively. (J) Model for the organization of the ciliary cholesterol–polycystin complex. Cartoon summarizing the implications of the current results and previous studies associated with the ciliary cholesterol and polycystin complex. Peroxisomes supply cholesterol into the ciliary membrane via the peroxisomal Rab10/Rabin8/KIFC3 complex and ORP3 at the ciliary pocket. Pex14 knockout or MβCD-mediated cholesterol depletion impairs ciliary localization. Cholesterol rescues the ciliary PC2 in the Pex14 mutant cells, but not the ciliary localization of PKD2 L517R exhibiting deficiency of cholesterol binding. Cholesterol enables PKD2 W414G, which is defective in ciliary localization but exhibits normal cholesterol binding, to exert its function in the ciliary membrane. Overall, the defective interaction between PC2 and cholesterol causes polycystic kidney in humans and mice.\n\nFigure 14: Figure 14. (A) Rate of phenotypic occurrence found in Pkd2 L515R/L515R mice. Heterotaxy was observed only in a Pkd2 L515R/L515R mouse, and its rate was about 31%. Either edema or hemorrhage was observed in a Pkd2 L515R/L515R mouse. (B) Stereomicroscopic image represented typical hemorrhage in Pkd2 L515R/L515R mice (left), whereas the appearance of Pkd2 L515R/+ mice was normal (right)."
      }
    ]
  },
  {
    "id": "PMC11794251_multi",
    "image": [
      "images/PMC11794251-f1.png",
      "images/PMC11794251-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Case Report: The first Korean familial case of BCAP31-related deafness, dystonia, and cerebral hypomyelination\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Axial T2-weighted image of the proband at 10 months shows marked brain atrophy, particularly in the white matter. (B) Axial T1-weighted image of the proband at 10 months displays delayed myelination. (C) Sagittal T1-weighted image of the proband at 10 months demonstrates thinning of the corpus callosum. (D) At the follow-up examination at two years of age, the proband exhibited mild facial dysmorphism characterized by downward slanting palpebral fissures, hypertelorism, esotropia, and a tented upper lip vermilion.\n\nFigure 2: Figure 2. Sanger sequencing identified the hemizygous pathogenic variant (c.247C>T, p.Gln83Ter) in BCAP31 in the male proband (arrow), and the variant was also found heterozygously in the mother and twin sister, who had a milder phenotype."
      }
    ]
  },
  {
    "id": "PMC11811033_multi",
    "image": [
      "images/PMC11811033-f1.png",
      "images/PMC11811033-f2.png",
      "images/PMC11811033-f3.png",
      "images/PMC11811033-f4.png",
      "images/PMC11811033-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"TRIM32 regulates insulin sensitivity by controlling insulin receptor degradation in the liver\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Representation of dietary regimen plan of RCD and HFD group (n = 10). (B) Graphical representation of ipGTT (n = 10 mice each). Mice were fasted for 6 h after 2 h of the dark cycle, and 2 g/kg body weight Glucose was injected intraperitoneally. Glucose levels were measured before Glucose administration and at 15, 30, 60, 90, and 120 min post-injection (left). AUC for the ipGTT curve (right). (C) Graphical representation of ipITT data (n = 10 mice each). Mice were fasted for 6 h after 2 h of the dark cycle, and 0.5 I.U/kg of body weight of insulin was injected intraperitoneally. Glucose levels were measured before and at 15, 30, 60, 90, and 120 min post-injection. AUC for the ipITT curve. (D) Graphical representation of ipPST (n = 10 mice each). Mice fasted for 12 h before 2 h of the dark cycle, and 100 mg/kg of body weight pyruvate was administrated intraperitoneally. Glucose levels were measured before Glucose administration and at 15, 30, 60, 90, and 120 min post-injection. AUC for the ipPST curve. (E) Graphical representation of Fasting blood glucose measured after overnight fasting (n = 10). (F) Fasting systemic Insulin levels measured after overnight fasting (n = 3), biological replicates. (G) Representation of H&E staining, Oil red O, and Sirius Red of RCD and HFD mice liver. All images were taken at 40x. Scale bar (50 µm). (H) Qualitative and quantitative representation of AMPKα and ACC phosphorylation at Thr172 and S79 residue of mice liver (n = 4), biological replicates. (I) Qualitative and quantitative representation of INSR levels from whole liver lysate of RCD and HFD mice (n = 4), biological replicates. (J) Qualitative and quantitative representation of INSR levels from Muscle of RCD, HFD, group (n = 4), biological replicates. (K) Qualitative and quantitative representation of INSR levels from eWAT of RCD, HFD, group (n = 4), biological replicates. Graphs were plotted in Graph pad prism8. The statistical significance was assessed by unpaired two-tailed t-test, and data has been expressed as Mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001 and ****p < 0.0001. Data information: In (B), unpaired two-tailed t-test, p = 0.0001 (AUC of ipGTT of RCD vs. HFD), (C) AUC of ipITT of RCD vs. HFD (p = 0.0021), (D) AUC of ipPST of RCD vs. HFD (p = 0.0001), (E) fasting blood RCD vs. HFD (p = 0.0001), (F) Fasting insulin RCD vs. HFD (p = 0.0009), (H) RCD vs. HFD (p = 0.0003), pACC RCD vs. HFD (p = 0.0003), (I) RCD vs. HFD (p = 0.0001), (J) RCD vs. HFD (p = 0.6206), (K) RCD vs. HFD (p = 0.1801). Source data are available online for this figure.\n\nFigure 2: Figure 2. (A) Western blot showing insulin receptor degradation in the presence of insulin (100 nM) and proteasomal inhibitor MG-132 (10 µM) treatment for 24 h. (B) Insulin receptor degradation was assessed after cells were treated with 100 nM insulin for 24 h. CHX (100 µg /ml) treatment was given after 18 h of insulin treatment, i.e., for 6 h, 4 h, 2 h, and 0 h before the completion of 24 h, and INSR expression was analyzed using WB. (C) INSR was pulled down after 24 h of insulin (100 nM) and MG132 (10 µM) treatment in mouse primary hepatocytes and analyzed for ubiquitination using WB. (D) PLS-DA plot of RNA-seq from mice’s liver shows both groups are well segregated, and the expression of a differentially expressed set of genes from the HFD and RCD groups of mice. (E) Clustered Heat map showing differentially expressed ubiquitin ligases of RCD and HFD mice liver (n = 3), biological replicates. (F) Graphical representation of RT-PCR data of TRIM32 gene from the liver of RCD and HFD mice (n = 3), biological replicates. (G) Relative expression of TRIM32 protein in whole liver lysate of RCD and HFD mice (n = 5), biological replicates. (H) HepG2 cells were transfected with the TRIM32 plasmid. After 48 h, the cells were incubated with Biotin (2 mM), and surface INSR expression was analyzed using WB (n = 3, biological replicates). (I) Clustered Heat map showing differentially expressed ubiquitin ligases from the liver of healthy, early, and moderate human NAFLD patients (n = 216). (J) In these plots, we have shown individual transcripts per million (TPM) values as black dots across three independent groups of healthy, early, and moderate human NAFLD patients (n = 216). The minima in this plot is the lowest TPM value in the individual groups and maxima as the highest TPM value in the individual groups. The rectangle box represents the interquartile range (IQR), with quartile 1 (Q1) at the lower end of box and quartile 3 (Q3) at the upper end of the box. The black line inside the box (in between Q1 and Q3) represents the median value. The red colored dot in the center of each box represents mean (average) of all TPM values in the individual groups. Graphs were plotted in Graph pad prism8. The statistical significance was assessed by unpaired two-tailed t-test, and data has been expressed as Mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001 and ****p < 0.0001. Data information: in (F), Relative mRNA expression of TRIM32 RCD vs. HFD (p = 0.0250), (G) Relative TRIM32/GAPDH (A.U) of RCD vs. HFD (p = 0.0079), (H) control vs. GFP-TRIM32(A.U) (p = 0.0143), (J) TRIM32 gene expression in Control vs. NAFLD mild (p < 0.0001), control vs NAFLD moderate (p < 0.0001), SREBF1gene expression Control vs NAFLD mild (p < 0.0001), control vs NAFLD moderate (p < 0.0001). Source data are available online for this figure.\n\nFigure 3: Figure 3. (A) TRIM32 was overexpressed in mouse primary hepatocytes and, after 48 h, treated with 100 nM insulin for the last 15 min to activate insulin signaling and accessed for pINSR(Y1150)/ tINSR and pAkt(S473)/tAkt using WB. (B) TRIM32 was knocked down in mouse primary hepatocytes. After 24 h of transfection, hepatocytes were treated with 100 nM insulin for the next 24 h. Hepatocytes were stimulated for 15 min with 100 nM insulin to access INSR and Akt phosphorylation using WB. (C) TRIM32 was overexpressed in HepG2 cells, and after 48 h of transfection, endogenous INSR was pooled down. The interaction of INSR and TRIM32, along with INSR ubiquitination, was assessed using WB. (D) TRIM32 and Ubiquitin-WT plasmids were overexpressed in HepG2 cells. After 24 h of transfection, 24 h of MG132 (10 μM) treatment were given, pooled down with INSR, and ubiquitination was accessed by WB. (E) TRIM32 was overexpressed in HepG2 cells and was treated with MG132(10 μM) for 24 h. Cells were incubated on ice with Biotin (2 mM) for the last 30 min, and surface INSR levels were analyzed using WB. (F) The plausible mode of interaction of INSR with TRIM32 as depicted by ClusPro and HADDOCK. Upper Panel Left: The top 1 ranked cluster with least energy having maximum number of structures obtained ClusPro. Upper Panel Right: Superimposed view of the top 1 ranked cluster snapshots obtained from HADDOCK. Lower Panel Left: The top 2 ranked cluster with least energy having maximum number of structures obtained ClusPro. Lower Panel Right: Superimposed view of the top 2 ranked cluster snapshots obtained from HADDOCK. (G) Intrinsic dynamics stability, inter-molecular hydrogen bonds and residual flexibility in INSR with TRIM32 complex systems over the time period of 100 ns. (G.i) Backbone RMSD of the two systems over the time period of 100 ns. (G.ii) The dynamics of inter-molecular hydrogen bonds in each frame of both the systems. (G.iii) The Cα-RMSF profile of the INSR protein with system 1 and 2 of INSR with TRIM32 complexes (G.iv) The Cα-RMSF profile of the TRIM32 protein with system 1 and 2 of INSR with TRIM32 complexes. (H) Global motions and the electrostatic surface potential maps of INSR with TRIM32 complex systems. (H.i) Porcupine plots of system 1 displaying the global movements of INSR-TRIM32 (INSR: Green; TRIM32: Cyan). (H.ii) The global movements of INSR-TRIM32 complex in system 2, displayed in porcupine plots (INSR: Green; TRIM32: Cyan). (H.iii) Distribution of surface charge of INSR-TRIM32 complex in system 1 and its intermolecular contact analysis. (H.iv) Electrostatic surface potential map of INSR-TRIM32 complex in system 2 and its subsequent intermolecular contacts. (I) Mouse primary hepatocytes were transfected with INSR-WT, INSRK1085R, and the TRIM32 plasmid. After 48 h, they were immunoprecipitated with the INSR antibody and accessed for TRIM32 using WB to check the interaction between INSR and TRIM32. Source data are available online for this figure.\n\nFigure 4: Figure 4. (A) Schematic representation of SRE site on TRIM32 promoter. (B) SREBP-1c occupancy on TRIM32 promoter in HepG2 cells after high glucose stimulation (30 mM), (n = 3), biological replicates. (C) Qualitative representation of levels of SREBP-1c in the cytosolic and nuclear extract of RCD and HFD mice liver. (D) SREBP-1c WT, SREBP-1c S372A, and SREBP-1c S372D were overexpressed in mouse primary hepatocytes, and expression of TRIM32 was analyzed using WB. (E) Mouse hepatocytes were co-treated with Insulin (100 nM) and SREBP-1c inhibitor Atorvastatin (100 µM) for 24 h, and expression of TRIM32 and FASN was analyzed with WB. (F) Mouse hepatocytes were co-treated with Insulin (100 nM) and AMPK activator AICAR (100 µM) for 24 h, and expression of TRIM32 and FASN was analyzed with WB. Blots were quantified using ImageJ software, and values were plotted in GraphPad Prism 8. The statistical significance was assessed by one-way analysis of variance (ANOVA) post-Bonferroni. Data were expressed as Mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001. Data Information: In (B), 5 mM vs 30 mM glucose (p < 0.0001). Source data are available online for this figure.\n\nFigure 5: Figure 5. (A) Schematic regimen of C57BL/6 male mice (n = 7 for each group). (B) Qualitative and quantitative representation of TRIM32 levels in RCD, HFD, and HFD+shTRIM32 group (n = 3), biological replicates. (C) Graphical representation of absolute change in body weight (n = 7). (D) The bar graph shows the relative change of liver to Body weight ratio (n = 7). (E) Qualitative representation of Western blot shows phosphorylation of INSR(Y1150) & Akt(S473 &Thr308), tAkt, respectively (n = 4), biological replicates. (F) Graphical representation of ipGTT data (n = 7). Mice were fasted for 6 h, 2 g/kg of B.W. glucose was injected intraperitoneally, and glucose level was measured at 0, 15, 30, 60, 90, and 120 min. AUC of ipGTT (n = 7). (G) Graphical representation of ipITT data (n = 7). Mice fasted for 6 h, 0.5 I.U/kg B.W. insulin was injected intraperitoneally, and blood glucose was measured at 0, 15, 30, 60, 90, and 120 min. AUC of ipITT (n = 7). (H) The bar graph shows relative fasting blood glucose levels (n = 7). (I) Relative Fasting insulin levels from mice serum after overnight fasting (n = 4), biological replicates. (J) The bar graph shows the relative HOMA-IR index (n = 4), biological replicates. (K, L) The bar graph shows triglyceride and cholesterol levels in the liver of mice (n = 4), biological replicates. (M) ORO images from RCD, HFD, and HFD+shTRIM32 mice liver sections. Images were taken at 40x. Blots were quantified using ImageJ software, and values were plotted in GraphPad Prism 8. The statistical significance was assessed by one-way analysis of variance (ANOVA) with Bonferroni. Data were expressed as Mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001. Data information: In (B), RCD vs HFD (p = 0.0013) and HFD vs HFD+shTRIM32 (p = 0.0036), (D) RCD vs HFD (p = 0.0149) and HFD vs HFD+shTRIM32 (p = 0.0008), (F) AUC of ipGTT RCD vs HFD (p = 0.0001) and HFD vs HFD+shTRIM32 (P = 0.0179), (G) AUC ipITT RCD vs HFD (p = 0.020) and HFD vs HFD+shTRIM32 (p = 0.0009), (H) Insulin RCD vs HFD (p = 0.0001) and HFD vs HFD+shTRIM32 (p = 0.0048), (I) Insulin RCD vs HFD (p = 0.0001) and HFD vs HFD+shTRIM32 (p = 0.0030), (J) HOMA-IR of RCD vs HFD (p < 0.0001) and HFD vs HFD+shTRIM32 (p = 0.0004), (K) Liver TG of RCD vs HFD (p = 0.0005) and HFD vs HFD+shTRIM32 (p = 0.0039), (L) Liver Cholesterol of RCD vs HFD (p = 0.0001) and HFD vs HFD+shTRIM32 (p = 0.0001). Source data are available online for this figure."
      }
    ]
  },
  {
    "id": "PMC11811033_multi_2",
    "image": [
      "images/PMC11811033-f6.png",
      "images/PMC11811033-f7.png",
      "images/PMC11811033-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"TRIM32 regulates insulin sensitivity by controlling insulin receptor degradation in the liver\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Graphical representation of normalized Liver to body weight ratio (n = 10). (B–E) Graphical representation of serum cholesterol, triglyceride, AST, and ALT levels, respectively (n = 3), biological replicates. (F, G) Graphical representation of Liver Triglyceride and Cholesterol data, respectively (n = 3), biological replicates. (H–K) Graphical representation of hepatic ballooning, macrovesicular & microvesicular steatosis, and NAFLD score (n = 3), biological replicates. Graphs were plotted in Graph pad prism8. The statistical significance was assessed by unpaired two-tailed t-test, and data has been expressed as Mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001. Data information: In (1A) unpaired two-tailed t-test, p = 0.0252 (RCD vs. HFD), (B) RCD vs. HFD (p = 0.034), (C) RCD vs. HFD (p = 0.0414), (D) AST ratio of RCD vs. HFD (p = 0.0420), (E) ALT ratio of RCD vs. HFD (p = 0.0009), (F) Liver Cholesterol RCD vs. HFD (p = 0.0019), (G) Liver TG of RCD vs. HFD (p = 0.0125), (H) RCD vs. HFD (p < 0.0001), (I) RCD vs HFD (p < 0.0001), (J) RCD vs HFD (p < 0.0001), (K) RCD vs HFD (p < 0.0001). Source data are available online for this figure.\n\nFigure 7: Figure 7. (A–E) Quantitative representation of RT-PCR data for MRKN1, HUWE1, TRIM32, MARCH 1, and TRIM72 E3 ubiquitin ligases from RCD and HFD liver (n = 3), biological replicates. Graphs were plotted in Graph pad prism8. The statistical significance was assessed by unpaired two-tailed t-test, and the data has been expressed as Mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001. Data information: (A) RCD vs HFD (p = 0.1718), (B) RCD vs HFD (p = 0.3962), (C) RCD vs HFD (p = 0.0250), (D) RCD vs HFD (p = 0.4998), (E) RCD vs HFD (p = 0.0601). Source data are available online for this figure.\n\nFigure 8: Figure 8. (A–C) The bar graph shows the relative change of iWAT, eWAT, and BAT to body weight ratio (n = 7). (D) Quantitative representation of Western blots showing phosphorylation of INSR(Y1150) (left), Akt(S473) (middle), and Akt(Thr308) (right) (n = 3), biological replicates. (E) Mouse primary hepatocytes were transfected with the shTRIM32 plasmid and, after 24 h, co-treated with Insulin (100 nM) and MG132 (10 µM) for the next 24 h. Immunoprecipitation was performed using the INSR antibody and checked for INSR ubiquitination using WB. Blots were quantified using ImageJ software, and values were plotted in GraphPad Prism 8. The statistical significance was assessed by one-way analysis of variance (ANOVA) with Bonferroni. Data were expressed as Mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001 and ****p < 0.0001 Data information in (A) iWAT by B.W. ratio of RCD vs. HFD (p < 0.0001) and HFD vs. HFDshTRIM32 (p = 0.0025), (B) eWAT by B.W. ratio of RCD vs. HFD (p < 0.0001) and HFD vs. HFDshTRIM32 (p = 0.0287), (C) BAT by B.W. ratio of RCD vs HFD (p = 0.099) and HFD vs HFDshTRIM32 (p = 0.0999). Source data are available online for this figure."
      }
    ]
  },
  {
    "id": "PMC11833080_multi",
    "image": [
      "images/PMC11833080-f1.png",
      "images/PMC11833080-f2.png",
      "images/PMC11833080-f3.png",
      "images/PMC11833080-f4.png",
      "images/PMC11833080-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"E3 ubiquitin ligase CHIP facilitates cAMP and cGMP signalling cross-talk by polyubiquitinating PDE9A\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic representation of PDE9A and CHIP structures; ∆TPR signifies the TPR domain of CHIP deletion, and ∆U-box indicates the U-box domain of CHIP deletion. The T246M mutation at the p.T246M locus results in inactivation of the U-box domain of CHIP, whereas the K30A mutation at the p.K30A locus leads to inactivation of the TPR domain. (B) Upper: In a set of experiments involving four 10 cm diameter Petri dishes for plasmid transfection, each dish was transfected with a total of 12 µg of plasmid DNA, followed by cotransfection of 4 µg of Flag-CHIP plasmid with increasing contents of V5-His-PDE9A (0, 2, 4, and 8 µg) and decreasing contents of blank-vector plasmid (8, 6, 4, and 0 µg) into HEK293T cells. This was followed by western blot analysis to examine the CHIP-mediated regulation of PDE9A levels. Lower: summary data, n = 3 biological replicates/group, two-way ANOVA (2WANOVA) for each condition, 0 vs. 2, 2 vs. 4, 4 vs. 8, Tukey’s multiple comparisons test (mct), V5: ****P < 0.0001 for all comparisons, **P = 0.0025; Flag: ****P < 0.0001 for all comparisons, ***P = 0.0005, P > 0.05 no marks. (C) Similar methodology. Upper: HEK293T cells were cotransfected with 4 µg of V5-His-PDE9A plasmid with increasing concentrations (0, 2, 4, and 8 µg) of Flag-CHIP and decreasing concentrations of blank-vector plasmid (8, 6, 4, and 0 µg), followed by western blot analysis to elucidate PDE9A-mediated alterations in CHIP. Lower: summary data, n = 3 biological replicates/group. 2WANOVA, Tukey mct, V5: ****P < 0.0001 for all comparisons, **P = 0.0095; Flag: **P = 0.0069, ****P < 0.0001, P > 0.05 no marks. (D) Changes in PDE9A mRNA levels following transfection with various CHIP mutant plasmids involved transfecting each well of a six-well plate with 2 µg of blank-vector plasmid, along with 2 µg of each mutant CHIP variant, into HEK293T cells; NC consisted of 2 µg of blank-vector plasmid, T246M represents homozygous mutations at the p.T246M site, K30A represents homozygous mutations at the p.K30A site, and CHIP+Bay indicates cells overexpressing CHIP treated with 200 µg/mL Bay 73-6691 (PDE9A inhibitor, dissolved in cell culture medium using a sonicator); sh-CHIP represents shRNAs targeting CHIP mRNA expression, summary data, n = 6 biological replicates/group, 1WANOVA, Tukey mct, nsP > 0.05 for all comparisons. (E) Changes in PDE9A protein levels following transfection with various CHIP mutant plasmids involved transfecting each well of a six-well plate with 2 µg of PDE9A plasmid, along with 2 µg of each CHIP variant, into HEK293T cells. Upper: Blots showing the CHIP mRNA variation affecting subsequent PDE9A protein levels. Lower: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, CHIP: ****P < 0.001 for all comparisons, **P = 0.0051; PDE9A: *P = 0.0274, ****P < 0.0001 for all comparisons, ***P = 0.0010, ***P = 0.0007. (F) Changes in CHIP mRNA levels following transfection with PDE9A mutant plasmids, cotransfection of 2 µg of various PDE9A mutant plasmids and 2 µg of blank-vector plasmid, PDE9A+Bay represents HEK293T cells overexpressing PDE9A treated with 200 µg/mL Bay 73-6691; sh-PDE9A indicates RNAi-mediated PDE9A knockdown. Summary data: n = 6 biological replicates/group, 1WANOVA, Tukey mct, nsP > 0.05 for all comparisons. (G) Changes in CHIP protein levels following transfection with PDE9A mutant plasmids, cotransfection of 2 µg of various PDE9A mutant plasmids and 2 µg of CHIP plasmid into HEK293T cells. Upper: Blots showing the CHIP mRNA variation affecting subsequent PDE9A protein levels. Lower: summary data, n = 3 biological replicates/group. 2WANOVA, Tukey mct, PDE9A: ****P < 0.0001, **P = 0.0017, **P = 0.0021; CHIP: ****P < 0.0001, nsP = 0.0681, nsP = 0.1775. (H) After HEK293T cells were cotransfected with 2 µg of CHIP-HA and 2 µg of PDE9A–Flag plasmids, immunofluorescence staining was used to observe the colocalization of PDE9A and CHIP within the cytoplasm. Imaging was performed through multiphoto laser scanning microscopy. Experiment replicated × 3. CHIP (red), PDE9A (green), and DPAI (blue). (I) Cotransfections were performed in each well of a six-well plate by introducing 2 µg of CHIP-HA and 2 µg of empty vector plasmid or 2 µg of PDE9A–Flag and 2 µg of empty vector plasmid into HEK293T cells, followed by treatment with 50 nM bafilomycin A1 (autophagy inhibitor) or 100 nM bortezomib (proteasome inhibitor, PS-341) with cycloheximide (CHX, which inhibits protein synthesis) added at six time points (0, 2, 4, 6, 8, and 10 h). Upper: Blot assessment of the half-lives and degradation pathways of CHIP and PDE9A. Lower: summary data, n = 3 biological replicates/group, comparing slope differences by analysis of covariance (ANCOVA), ****P < 0.0001 for all comparisons. (J) A similar methodology was used, followed by treatment with 200 µg/mL Bay 73-6691 and cotransfection of 2 µg CHIP plasmid and 2 µg PDE9A plasmid into HEK293T cells. Upper: Blotting was used to assess the impact of PDE9A and Bay 73-6691 on the degradation of CHIP and the impact of CHIP and Bay 73-6691 on the degradation of PDE9A. The blot and statistical values for the Control (Con) group are identical to those for the Control (Con) group in (I). Lower: summary data, ANCOVA for each condition, n = 3 biological replicates/group, ANCOVA, ****P < 0.0001 for all comparisons, **P = 0.0038. Each summary panel shows the means ± SDs, summary plot (D–G) and regressions (B, C, I, J). The P-value are shown from left to right. Source data are available online for this figure.\n\nFigure 2: Figure 2. (A) Coimmunoprecipitation assays to identify interacting domains between PDE9A and CHIP. Antibodies: V5-rabbit and Flag-mouse. Experiment replicated × 3. (B) Schematic of ubiquitin variants. (C, D) In vivo ubiquitination assays validating the role of different ubiquitin chain mutants in the CHIP-mediated ubiquitination of PDE9A. HEK293T cells were cotransfected with 6 µg of V5-His-PDE9A plasmid, 6 µg of Flag-CHIP plasmid, and 6 µg of ubiquitin variants in 10 cm diameter Petri dishes. Polyubiquitin chains are generated with K48, K63, K11, K27 and K29 linkages, whereas synthesis is impaired for the K63R and K27R chains. Experiment replicated × 3. Antibodies: V5-rabbit, HA-mouse, and Flag-mouse. (E) LS/MS detection of ubiquitination at position K186 in the PDE9A sequence AEVANHLAVLEKR (indicated within the red box). Experiment replicated × 2. (F) Similar to in vivo ubiquitination assays, HEK293T cells were cotransfected with 6 µg of V5-His-PDE9A plasmid or 6 µg of V5-His-PDE9A-K186R plasmid, 6 µg of Flag-CHIP plasmid, and 6 µg of ubiquitin mutant variant plasmid. Experiment replicated × 3. Antibodies: V5-rabbit, HA-mouse, and Flag-mouse. Paired t test, ****P < 0.0001 for all comparisons, **P = 0.0098. (G) Similar to the methodology used for in vivo ubiquitination assays, HEK293T cells were cotransfected with 6 µg of the V5-His-PDE9A plasmid, 6 µg of the site-specific CHIP mutation plasmid, and 6 µg of the HA-Ub plasmid. Site-specific mutations p.T246M and p.K30A in CHIP result in impaired PDE9A ubiquitination in vivo. Experiment replicated × 3. Each summary panel shows the means ± SDs and summary plot (G). The P-value are shown from left to right. Source data are available online for this figure.\n\nFigure 3: Figure 3. (A) Timeline for behavioural assessments in the Bay 73-6691 treatment and AAV-CHIP injection cohorts. The Bay 73-6691 treatment cohort included Hom(6M+) (6.25-month-old homozygous rats harbouring the p.T246M mutation), Hom(6M+)+Bay(+) (Bay 73-6691 solubilized in corn oil administered intraperitoneally at 2 mg/kg to homozygous rats), Hom(6M-) (presymptomatic 4-month-old homozygous rats with the p.T246M mutation), and WT (wild-type littermates). The AAV-CHIP injection cohort included Hom(7M+) (n = 8, homozygous rats with the p.T246M mutation), Hom(7M+) + AAV-CHIP (n = 8, tail vein injection of 1.2 × 1011 vg/mL HBAAV2/BBB-CHIP virus to increase CHIP protein levels in the brains of homozygous rats), Hom(7M+) + AAV-NC (n = 8, homozygous rats injected with an equivalent dose of control empty HBAAV2/BBB-blank virus) and WT (n = 8, wild-type littermates). (B) Tolerance to maximal velocity in the rodent rotarod test. Summary data: The Bay 73-6691 treatment cohort included WT (n = 16), Hom(6M-) (n = 17), Hom(6M+) (n = 12), and Hom(6M+)+Bay(+) (n = 9) individuals. Each rat was tested in triplicate. 1WANOVA, Tukey mct, nsP > 0.9999, ***P = 0.0009, nsP = 0.9631. (C) Time required for the rats to traverse the balance beam in its entirety during the balance beam. Summary data: The Bay 73-6691 treatment cohort included WT (n = 15), Hom(6M+) (n = 11), Hom(6M-) (n = 14), and Hom(6M+)+Bay(+) (n = 9) individuals. Each rat was tested in triplicate. 1WANOVA, Tukey mct, nsP = 0.9922, ****P < 0.0001, nsP > 0.4606. (D) Gait analysis illustrating rodent footprints, where red represents the forelimbs and blue represents the hindlimbs. The parameters measured included LFSL (left front stride length), RFSL (right front stride length), LRSL (left rear stride length), RRSL (right rear stride length), LFRO (left front rear overlap), RFRO (right front rear overlap), FBW (front-base width), and RBW (rear-base width). The Bay 73-6691 treatment cohort included WT (n = 15), Hom(6M+) (n = 11), Hom(6M-) (n = 14), and Hom(6M+)+Bay(+) (n = 9) individuals. (E) Summary of gait analysis data. Each rat was tested in triplicate. 1WANOVA, Tukey mct, LFSL: *P = 0.0185, ****P < 0.0001; RFSL: ****P < 0.0001; LRSL: ****P < 0.0001; RRSL: ****P < 0.0001; RBW: ***P = 0.0003; RFRO: *P = 0.0336. nsP > 0.05 for all comparisons. (F) Morris water maze trajectory depicting the exploration patterns of the rats in Bay 73-6691 treatment cohort after the introduction of the platform in the third quadrant. The Bay 73-6691 treatment cohort included WT (n = 15), Hom(6M+) (n = 11), Hom(6M-) (n = 11), and Hom(6M+)+Bay(+) (n = 9) individuals. (G) Latency period for rats to locate the hidden platform in the third quadrant, monitored over a consecutive 5-day period. WT (n = 15), Hom(6M+) (n = 11), Hom(6M-) (n = 11), and Hom(6M+)+Bay(+) (n = 9). Summary data: 2WANOVA. (H) On the sixth day after platform removal, the proportion of time the rats spent in the NE quadrant after water entry was determined. WT (n = 15), Hom(6M+) (n = 11), Hom(6M-) (n = 11), and Hom(6M+)+Bay(+) (n = 9). Summary data: 1WANOVA, Tukey mct, nsP = 0.9882, ****P < 0.0001, ***P = 0.0009. (I) Number of platform crossings within 60 s and 5 min after water entered the NE quadrant after platform removal. WT (n = 15), Hom(6M+) (n = 11), Hom(6M-) (n = 11), and Hom(6M+)+Bay(+) (n = 9). Summary data: 1WANOVA, Tukey mct, nsP = 0.7787, ***P = 0.0008, nsP = 0.2410. (J) Tolerance to maximal velocity in the rodent rotarod test in AAV-CHIP injection cohort. Each rat was tested in triplicate. 1WANOVA, Tukey mct, ***P = 0.0001, ****P < 0.0001, nsP = 0.4259. (K) Time required for the rats to traverse the balance beam in its entirety during the balance beam in AAV-CHIP injection cohort. Each rat was tested in triplicate. 1WANOVA, Tukey mct, ***P = 0.0010, **P = 0.0028, nsP = 0.8879. (L) Gait analysis illustrating rodent footprints in AAV-CHIP injection cohort. (M) Summary of gait analysis data. Each rat was tested in triplicate. 1WANOVA, Tukey mct, LFSL: ****P < 0.0001 for all comparisons; RFSL: ****P < 0.0001 for all comparisons; LRSL: ****P < 0.0001 for all comparisons; RRSL: ****P < 0.0001 for all comparisons; FBW: **P = 0.0083, *P = 0.0237; RBW: ***P = 0.0003, **P = 0.0039. nsP > 0.05 for all comparisons. (N) Morris water maze trajectory depicting the exploration patterns of the rats in the AAV-CHIP injection cohort after the introduction of the platform in the third quadrant. Hom(7M+) (n = 8), Hom(7M+) + AAV-CHIP (n = 8), Hom(7M+) + AAV-NC (n = 8), and WT (n = 8). (O) Latency period for rats to locate the hidden platform in the third quadrant, monitored over a consecutive 5-day period. Hom(7M+) (n = 8), Hom(7M+) + AAV-CHIP (n = 8), Hom(7M+) + AAV-NC (n = 8), and WT (n = 8). Summary data: 2WANOVA. (P) On the sixth day after platform removal, the proportion of time the rats spent in the NE quadrant after water entry was determined. Hom(7M+) (n = 8), Hom(7M+) + AAV-CHIP (n = 8), Hom(7M+) + AAV-NC (n = 8), and WT (n = 8). Summary data: 1WANOVA, Tukey mct, ***P = 0.0002, ***P = 0.0001, **P = 0.0094. (Q) Number of platform crossings within 60 s and 5 min after water entered the NE quadrant after platform removal. Hom(7M+) (n = 8), Hom(7M+) + AAV-CHIP (n = 8), Hom(7M+) + AAV-NC (n = 8), and WT (n = 8). Summary data: 1WANOVA, Tukey mct, ****P < 0.0001, ***P = 0.0001, nsP = 0.2134. Each summary panel shows the means ± SDs, summary plot (B, C, E, H–K, M, P, Q) and regressions (F, O). The P-value are shown from left to right. Source data are available online for this figure.\n\nFigure 4: Figure 4. (A) The phosphorylation state of CHIP at serine 20 in cerebellar and hippocampal tissues across the Bay 73-6691 treatment cohort was assessed via a phospho-specific S20 antibody. Upper: Blots showing the CHIP and p-CHIP (phosphorylated CHIP) levels in Hom(6M+) (6.25-month-old homozygous rats harbouring the p.T246M mutation), Hom(6M+)+Bay(+) (Bay 73-6691-treated homozygous rats), and WT (wild-type littermates), with each lane containing a mixed-tissue protein sample from three rats. Lower: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: ****P < 0.0001 for all comparisons; Hippocampus: ****P < 0.0001, ***P = 0.0002. (B) CHIP phosphorylation levels in the cerebellum and hippocampus were quantified for the AAV-CHIP injection cohorts. Upper: Blots showing the CHIP and p-CHIP levels among Hom(7M+) (7-month-old homozygous rats harbouring the p.T246M mutation), Hom(7M+) + AAV-CHIP (AAV-CHIP-injected homozygous rats), Hom(7M+) + AAV-NC (AAV-NC-injected homozygous rats), and WT (wild-type littermates), with each lane containing a mixed tissue protein sample from three rats. Lower: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: ****P < 0.0001 for all comparisons, nsP = 0.2375; Hippocampus: ****P < 0.0001 for all comparisons, nsP = 0.9858. Each summary panel shows the means ± SDs and summary plot (A, B). The P-value are shown from left to right. Source data are available online for this figure.\n\nFigure 5: Figure 5. (A, B) Left: Quantitative immunofluorescence of the cerebellar Purkinje cell marker protein calbindin-D28K to determine alterations in the number of cerebellar Purkinje neurons in the Bay 73-6691-treated and AAV-CHIP-injected cohorts. The Bay 73-6691 treatment cohort included Hom(6M+) (6.25-month-old homozygous rats harbouring the p.T246M mutation), Hom(6M+)+Bay(+) (Bay 73-6691 solubilized in corn oil administered intraperitoneally at 2 mg/kg to homozygous rats), and WT (wild-type littermates). The AAV-CHIP injection cohort included Hom(7M+) (homozygous rats with the p.T246M mutation), Hom(7M+) + AAV-CHIP (tail vein injection of 1.2 × 1011 vg/mL HBAAV2/BBB-CHIP virus to increase CHIP protein levels in the brains of homozygous rats) and WT (wild-type littermates). Calbindin-D28k (red), DAPI (blue). Right: summary data, n = 6 biological replicates/group, 1WANOVA, Tukey mct, Bay 73-6691 treatment cohort: ****P < 0.0001 for all comparisons; AAV-CHIP injection cohort: ****P < 0.0001, nsP = 0.3712. (C) Left: Automated capillary western blot assays for the expression of autophagic proteins in cerebellar and hippocampal tissues across the Bay 73-6691 treatment cohort. Tissue protein samples from three rats were mixed for each lane. Right: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, P62: **P = 0.0076, nsP = 0.5963, ***P = 0.0004, nsP = 0.6285; LC3B: ****P < 0.0001, nsP = 0.9998, ****P < 0.0001, nsP = 0.0766. (D) Left: Similar methodology in AAV-CHIP injection cohort. Tissue protein samples from three rats were mixed for each lane. Right: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, P62: ****P < 0.0001 for all comparisons, nsP = 0.8687, *P = 0.0315; LC3B: ****P < 0.0001 for all comparisons, nsP = 0.9886, *P = 0.0106. (E) Left: Automated capillary western blot assays for the expression of autophagic proteins in cerebellar and hippocampal tissues from the Bay 73-6691 treatment cohort. Tissue protein samples from three rats were mixed for each lane. Right: summary data, cerebellar tissue followed by the hippocampus. n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: FIS1: ****P < 0.0001, nsP = 0.1018; OPA1: ****P < 0.0001, nsP = 0.4467; BNIP3: ****P < 0.0001 for all comparisons. Hippocampus: FIS1: ***P = 0.0003, nsP = 0.5225; OPA1: **P = 0.0012, nsP = 0.2388; BNIP3: ****P < 0.0001. nsP = 0.9928. (F) Left: Similar methodology in AAV-CHIP injection cohort. Right: summary data, cerebellar tissue followed by the hippocampus. n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: FIS1: ****P < 0.0001 for all comparisons, nsP = 0.9207; OPA1: ***P = 0.0003, **P = 0.0022, nsP = 0.9778; BNIP3: ****P < 0.0001 for all comparisons, ***P = 0.0003. Hippocampus: FIS1: **P = 0.0026, **P = 0.0016, nsP = 0.8312; OPA1: nsP = 0.0774, **P = 0.0027, nsP = 0.8654; BNIP3: ****P < 0.0001 for all comparisons, **P = 0.0054. (G) TEM observations of mitochondrial alterations in rat cerebellar tissue. Left: Ultrastructure of the cerebellum under TEM, Hom (CHIP p.T246M homozygous mutant rats), Hom+Bay(+) (Bay 73-6691 treated the homozygous mutant rats), Hom+AAV-CHIP (AAV-CHIP injected the homozygous mutant rats), and WT (wild-type littermates). In the Hom group, mitochondria (M, indicated by the red dashed circle) are less common and exhibit localized membrane blurriness and rupture, abundant crista disintegration and dissolution and matrix vacuolisation. Autophagolysosomes (ASSs, red arrows) are also visible. N: Nucleus, Go: Golgi apparatus, Lip: lipofuscin, RER: rough endoplasmic reticulum, Mi: microbody, AP: autophagosomes. Right: Mitochondrial injury Flameng score; five different microscopic fields were selected for each sample, and 20 mitochondria were randomly selected for each field of view. Summary data: n = 6 rat samples/group, 1WANOVA, Tukey mct, ****P < 0.0001, nsP = 0.4370, nsP = 0.5253. Each summary panel shows the means ± SDs and summary plot (A–G). The P-value are shown from left to right. Source data are available online for this figure."
      }
    ]
  },
  {
    "id": "PMC11833080_multi_2",
    "image": [
      "images/PMC11833080-f6.png",
      "images/PMC11833080-f7.png",
      "images/PMC11833080-f8.png",
      "images/PMC11833080-f9.png",
      "images/PMC11833080-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"E3 ubiquitin ligase CHIP facilitates cAMP and cGMP signalling cross-talk by polyubiquitinating PDE9A\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Schematic of the experimental strategy applied for single-cell transcriptome analysis. Four experimental groups were assessed: Hom (n = 3, CHIP p.T246M homozygous mutant rats), Hom+Bay(+) (n = 3, Bay 73-6691-treated homozygous mutant rats), Hom+AAV-CHIP (n = 3, AAV–CHIP-injected homozygous mutant rats), and WT (n = 3, wild-type littermates). Hippocampal and cerebellum tissues were mixed 1:1 for each rat, with three rats per group. (B, C) Cell clustering diagram: Cells from the rat hippocampus and cerebellum were classified into 12 distinct clusters on the basis of the following marker genes: granule cells (Reln, Rbfox3, Neurod1), oligodendrocytes (Mbp), glutamatergic neurons (Aldoc), GABAergic neurons (Gad2, Pnoc, Tcf7l2, Lhx9), GABAergic interneurons (Pax2, Lbx1), pyramidal cells (Nell1, Npy2r, Slc4a8, B3gat2), oligodendrocyte precursor cells (Pdgfra, Olig1, Olig2), endothelial cells (C1qa, C1qb, C1qc), Bergmann glia cells (Gdf10, S100b), microglial cells (Tmem119), Purkinje cells (Gad1, Car8, Calb1, Pcp2, Necab2, Pcp4) and astrocytes (Clu, Apoe). (D) Volcano plot illustrating the expression of cluster-specific marker genes across the 12 identified cell clusters. granule cells (58,325 cells), oligodendrocytes (6395 cells), glutamatergic neurons (4576 cells), GABAergic neurons (2982 cells), GABAergic interneurons (840 cells), pyramidal cells (1765 cells), oligodendrocyte precursor cells (1107 cells), endothelial cells (613 cells), Bergmann glia cells (2498 cells), microglial cells (383 cells), Purkinje cells (1492 cells) and astrocytes (183 cells). Wilcoxon rank sum test.\n\nFigure 7: Figure 7. (A) KEGG enrichment analysis of differentially expressed genes in whole cells comparing Wt vs. Hom. Hom (CHIP p.T246M homozygous mutant rats) and Wt (wild-type littermates). The most relevant signalling pathways are highlighted in red boxes. Hypergeometric test. (B) AUCell pathway activity analysis showing the expression of the cGMP‒PKG signalling pathway in whole cells across the four groups. Hom (n = 3, CHIP p.T246M homozygous mutant rats. 19,279 cells), Wt (n = 3, wild-type littermates. 13,473 cells), Hom+Bay(+) (n = 3, Bay 73-6691-treated homozygous mutant rats. 23,177 cells), and Hom+AAV-CHIP (n = 3, AAV–CHIP-injected homozygous mutant rats. 25,238 cells). T test, ***P < 2.22E−16, ***P < 2.22E−16, ***P < 2.22E−16. (C) AUCell pathway activity analysis showing the expression of the cAMP signalling pathway in whole cells across the four groups. Hom (n = 3. 19,279 cells), Wt (n = 3. 13,473 cells), Hom+Bay(+) (n = 3. 23,177 cells), and Hom+AAV-CHIP (n = 3. 25,238 cells). T test, ***P < 2.22E−16, **P = 0.0018, ***P < 2.22E−16. (D, E) GSEA pathway activity analysis indicating alterations in the cGMP-PKG signalling pathway and cAMP signalling pathway in total cells when comparing Wt vs. Hom. (F) KEGG enrichment analysis of differentially expressed genes in whole cells comparing Hom+AAV-CHIP vs. Hom. Hypergeometric test. (G, H) GSEA pathway activity analysis indicating alterations in the cGMP-PKG signalling pathway and cAMP signalling pathway in total cells when comparing Hom+AAV-CHIP vs. Hom. (I) KEGG enrichment analysis of differentially expressed genes in whole cells comparing Hom+Bay(+) vs. Hom. Hypergeometric test. (J, K) GSEA pathway activity analysis indicating alterations in the cGMP-PKG signalling pathway and cAMP signalling pathway in total cells when comparing Hom+Bay(+) vs. Hom. Each summary panel shows the means ± SDs and summary plot (B, C). The P-value are shown from left to right.\n\nFigure 8: Figure 8. (A) Upper: Blotting was used to evaluate cAMP‒PKA signalling protein expression in the cerebellum and hippocampus tissues of Bay 73-6691 treatment cohorts. Bay 73-6691 treatment cohorts: Hom(6M+) (6.25-month-old homozygous rats harbouring the p.T246M mutation), Hom(6M+)+Bay(+) (Bay 73-6691 solubilized in corn oil administered intraperitoneally at 2 mg/kg to homozygous rats), and WT (wild-type littermates). The protein samples from three rats were mixed for each lane. The GAPDH blots selected for the repeated experiments were consistent, and statistical analysis was performed by calculating the ratio of each target protein to its corresponding GAPDH. Lower: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: cAMP: ****P < 0.0001 for all comparisons, PRCAKA: ****P < 0.0001 for all comparisons; Hippocampus: cAMP: ****P < 0.0001 for all comparisons, PRCAKA: ****P < 0.0001, nsP = 0.2607. (B) Upper: Blotting was used to evaluate cAMP‒PKA signalling protein expression in the cerebellum and hippocampus tissues of AAV-CHIP injection cohort. The AAV-CHIP injection cohort included Hom(7M+) (homozygous rats with the p.T246M mutation), Hom(7M+) + AAV-CHIP (tail vein injection of 1.2 × 1011 vg/mL HBAAV2/BBB-CHIP virus to increase CHIP protein levels in the brains of homozygous rats) and WT (wild-type littermates). The protein samples from three rats were mixed for each lane. The GAPDH blots selected for the repeated experiments were consistent, and statistical analysis was performed by calculating the ratio of each target protein to its corresponding GAPDH. Lower: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: cAMP: ****P < 0.0001 for all comparisons, ***P = 0.0004, PRCAKA: ****P < 0.0001 for all comparisons, nsP = 0.4916; Hippocampus: cAMP: ***P = 0.0002, ****P < 0.0001, nsP = 0.0783, PRCAKA: ***P = 0.0006, ****P < 0.0001, nsP = 0.0867. (C) The impact of the cAMP agonist forskolin (50 µM) on CHIP-mediated PDE9A ubiquitination with K63 and K27 linkages. In vivo ubiquitination assays revealed changes in CHIP-mediated ubiquitination of PDE9A upon cAMP suppression. Experiment replicated × 3. Antibodies: V5-rabbit, HA-mouse, and Flag-mouse. Paired t test, ****P < 0.0001, ***P = 0.0006, *P = 0.0496. (D) ELISA assays were used to measure cGMP concentrations in the cerebellum and hippocampus in the Bay 73-6691 treatment cohort. Tissue protein samples from three rats from each group were mixed. Summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: ****P < 0.0001, nsP = 0.6151; Hippocampus: ****P < 0.0001, nsP = 0.5007. (E) ELISA assays were used to measure cGMP concentrations in the cerebellum and hippocampus in the AAV-CHIP injection cohort. Tissue protein samples from three rats from each group were mixed. Summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: ****P < 0.0001 for all comparisons, *P = 0.0233; Hippocampus: ****P < 0.0001 for all comparisons, *P = 0.0314. (F) Upper: Automated capillary western blot assays were used to assess PKG signalling protein expression in cerebellar and hippocampal tissues across the Bay 73-6691 treatment cohort. Tissue protein samples from three rats were mixed for each lane. Lower: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: CHIP: ****P < 0.0001 for all comparisons, PDE9A: ****P < 0.0001, nsP = 0.9301, PRKG1: ***P = 0.0005, nsP = 0.4655, PRKG2: **P = 0.0030, nsP = 0.8901; Hippocampus: CHIP: ****P < 0.0001 for all comparisons, PDE9A: ****P < 0.0001, nsP = 0.5242, PRKG1: ****P < 0.0001, nsP = 0.0856, PRKG2: ****P < 0.0001, nsP = 0.9677. (G) Upper: Automated capillary western blot assays were used to assess PKG signalling protein expression in cerebellar and hippocampal tissues across the AAV-CHIP injection cohort. Tissue protein samples from three rats were mixed for each lane. Lower: summary data, n = 3 biological replicates/group, 2WANOVA, Tukey mct, Cerebellum: CHIP: ****P < 0.0001 for all comparisons, ***P = 0.0003, PDE9A: ****P < 0.0001, ***P = 0.0002, nsP = 0.9801, PRKG1: ***P = 0.0003, ****P < 0.0001, nsP = 0.9045, PRKG2: ****P < 0.0001 for all comparisons, nsP = 0.5738; Hippocampus: CHIP: ****P < 0.0001 for all comparisons, nsP = 0.1177, PDE9A: ****P < 0.0001 for all comparisons, nsP = 9289, PRKG1: ****P < 0.0001 for all comparisons, nsP = 0.5815, PRKG2: ****P < 0.0001 for all comparisons, nsP = 0.1878. Each summary panel shows the means ± SDs and summary plot (A–G). The P-value are shown from left to right. Source data are available online for this figure.\n\nFigure 9: Figure 9. (A–C) Differential gene KEGG enrichment analysis in Purkinje cells for the following comparisons: Wt vs. Hom, Hom+AAV-CHIP vs. Hom, and Hom+Bay(+) vs. Hom, Hom (CHIP p.T246M homozygous mutant rats), Wt (wild-type littermates), Hom+AAV-CHIP (AAV-CHIP-injected homozygous mutant rats), and Hom+Bay(+) (Bay 73-6691-treated homozygous mutant rats). The most relevant signalling pathways are highlighted in red boxes. Hypergeometric test. (D–I) AUCell pathway activity analysis revealed alterations in Purkinje cells across the four groups in multiple signalling pathways. Hom (n = 3. 47 cells), Wt (n = 3. 117 cells), Hom+AAV-CHIP (n = 3. 1148 cells), and Hom+Bay(+) (n = 3. 180 cells). T test, cGMP-PKG signalling pathway: ***P < 2.22E−16, ***P < 2.22E−16, ***P = 1.8E−07; cAMP signalling pathway: NSP = 0.5500, ***P = 3E−07, **P = 0.0066; Mitophagy: ***P < 2.22E−16, ***P < 2.22E−16, ***P = 2E−09; Autophagy: ***P < 2.22E−16, ***P < 2.22E−16, *P = 0.0257; Ubiquitin-mediated proteolysis: ***P < 2.22E−16, ***P < 2.22E−16, ***P = 8E−06; Oxidative phosphorylation: ***P < 2.22E−16, ***P < 2.22E−16, *P = 0.0190. Each summary panel shows the means ± SDs and summary plot (D–I). The P-value are shown from left to right.\n\nFigure 10: Figure 10. The diagram fully illustrates the regulatory network of CHIP and PDE9A within Purkinje cells, demonstrating the involvement of cGMP and cAMP signaling pathways and their implications for mitophagy and proteostasis in neuronal apoptosis. Arrows indicate activation or progression of processes, while red crosses denote inhibition."
      }
    ]
  },
  {
    "id": "PMC11872110_multi",
    "image": [
      "images/PMC11872110-f1.png",
      "images/PMC11872110-f2.png",
      "images/PMC11872110-f3.png",
      "images/PMC11872110-f4.png",
      "images/PMC11872110-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Development of a rabbit model for adrenoleukodystrophy: A pilot study on gene therapy using rAAV9\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Mutation detection sequence and predicted protein structure of mutated ABCD1 (A) Sequencing information of ABCD1-mutated rabbits with two sgRNA targets highlighted in blue, and PAM sites underlined. (B) Predicted structure of WT ABCD1 and mutant truncated ABCD1. (C) Editing efficiency of sgRNA1 and sgRNA2.\n\nFigure 2: Figure 2. Serum VLCFA levels in WT and ABCD1-mutated rabbits (A) Table of the VLCFAs content in serum. Values are presented as mean (SD). (B) Bar graph illustration of the VLCFA levels in serum. ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001, ∗∗∗∗p < 0.0001, by one-way ANOVA, followed by Dunnett’s multiple comparisons test.\n\nFigure 3: Figure 3. T2-weighted MRI of WT and ABCD1−/− rabbit brains and spinal cords\n\nFigure 4: Figure 4. Ultrastructure morphology of WT and ABCD1−/− rabbit brains and spinal cords Normal myelin structure is seen in the white matter of the brain (A and B) and spinal cord (E and F) of WT rabbits, while obvious demyelination is observed in the white matter of the brain (C and D) and spinal cord (G and H) of ABCD1−/− rabbits. Yellow arrowheads indicate demyelination. Scale bar, 1 μm for (A) and (C); 2 μm for (E) and (G); 0.5 μm for (B), (D), (F), and (H).\n\nFigure 5: Figure 5. Effect of rAAV9-hABCD1 treatment on mutant rabbits (A) Monitoring VLCFA (C26:0/C22:0 ratio) levels post rAAV9-hABCD1 gene therapy. Two-way ANOVA followed by Bonferroni’s multiple comparisons test. Values presented as means (SD), ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001, ∗∗∗∗p < 0.0001. (B) Expression of hABCD1 in different tissues among different groups determined by qPCR. ∗p < 0.05, by one-way ANOVA followed by Dunnett’s multiple comparisons test. (C) Blood biochemical levels before and after treatment in the rAAV9-hABCD1 group compared with the WT group. AST, aspartate aminotransferase; GGT, gamma-glutamyl transferase; TP, total protein; CR, creatinine; TG, triacylglycerol; TCHO, total cholesterol; HDL-C, high-density lipoprotein cholesterol; LDL-C, low-density lipoprotein cholesterol; ALT, alanine transaminase; ALB, albumin; LDH, lactate dehydrogenase. (D) Liver and kidney pathologies in rAAV9-hABCD1-treated ABCD1−/− rabbits, untreated ABCD1−/− mutants, and the WT group. The black arrow indicates the lipid droplet vacuole. Scale bar, 250 μm."
      }
    ]
  },
  {
    "id": "PMC11920078_multi",
    "image": [
      "images/PMC11920078-f1.png",
      "images/PMC11920078-f2.png",
      "images/PMC11920078-f3.png",
      "images/PMC11920078-f4.png",
      "images/PMC11920078-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"HSD17B4 deficiency causes dysregulation of primary cilia and is alleviated by acetyl-CoA\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a, b Primary cilia were visualized in fibroblasts derived from healthy controls (Cont #1, #2) and HSD17B4-deficient patients (c.422_423DelAG; Patient #1, #2) by immunostaining with an anti-ARL13B (green) antibody. Nuclei were counterstained with Hoechst 33342 dye (blue). Data are presented as the mean ± SEM (n = 3, independent biological replicates). P-value vs. healthy controls determined by one-way ANOVA followed by Tukey’s multiple comparisons test [Ciliated cells: Cont #1 vs. Patient #1 p = 0.0008, vs. Patient #2 p = 0.0002; Cont #2 vs. Patient #1 p = 0.0005, vs. Patient #2 p = 0.0001; Cilium length: Cont #1, 2 vs. Patient #1, 2 p < 0.0001]. c HSD17B4 expression was abrogated in HSD17B4 patient-derived fibroblasts. Western blot analysis was performed using the indicated antibodies. Representative blot from three independent experiments is presented d, e RPE cells were transfected with either scrambled (Sc) siRNA or siRNA targeting HSD17B4 (siHSD17B4) for 72 h. Primary cilia were immunostained with an anti-acetylated-α-tubulin antibody (red), and nuclei were counterstained with Hoechst 33342 dye (blue). f, g HSD17B4-knockout (KO) and wild-type (WT) SH-SY5Y/Cas9 cells were immunostained with an anti-ARL13B (green) antibody and Hoechst 33342 (blue) dye. The number of ciliated cells and the ciliary length of the cells were quantified using a fluorescence microscope. Scale bar, 5 μm. Data are presented as the mean ± SEM (n = 3, independent biological replicates). P-value vs. Sc non-targeting siRNA treatment or WT cells determined by two-tailed unpaired t-test [Ciliated cells: Sc vs. siHSD17B4 p = 0.0032 (e), WT vs. KO p = 0.0160 (g); Cilium length: Sc vs. siHSD17B4, WT vs. KO p < 0.001 (e, g)]. h Primary cilia-mediated signaling was assessed by western blotting using the indicated antibodies. Experiments were repeated three times. Source data are provided as a Source Data file.\n\nFigure 2: Figure 2. a, b The RPE cells were transfected with a Sc or an HSD17B4 siRNA (siHSD17B4). After incubation for 48 h, the cells were treated with serum-free (SF) medium, SAG (1 μM), or GSK503 (10 μM) for 24 h. Primary cilia were immunostained with an anti-ARL13B antibody (green) and the nuclei were counterstained with Hoechst 33342 dye (blue). Data are presented as the mean ± SEM (n = 3, independent biological replicates). P-value vs. between the indicated groups determined by one-way ANOVA followed by Tukey’s multiple comparisons test [Ciliated cells: Sc vs. siHSD17B4; Cont p = 0.0172, SF p < 0.0001, SAG p < 0.0001, GSK503 p < 0.0001; Cilium length: Sc vs. siHSD17B4; Cont p = 0.0264, SF, SAG, and GSK503 p < 0.001]. c, d The RPE cells transfected with the indicated siRNA for the dysregulation of peroxisomal β-oxidation pathway were further incubated with or w/o SF medium. The primary cilia were immunostained with anti-ARL13B (green) antibody, and the nuclei were counterstained with Hoechst 33342 dye (blue). Data are presented as the mean ± SEM (n = 3, independent biological replicates). P-value vs. between the indicated groups determined by one-way ANOVA followed by Tukey’s multiple comparisons test [Ciliated cells: Cont Sc vs. siABCD1 p = 0.0126, siACOX1 p = 0.0093, siHSD17B4 p = 0.0051, siTYSND1 p = 0.0037; SF Sc vs. siABCD1, siACOX1, siHSD17B4, siTYSND1 p = 0.0051; Cilium length: Cont Sc vs. siABCD1 p < 0.0001, siACOX1 p = 0.0005, siHSD17B4 p < 0.0001, siTYSND1 p < 0.0001; SF Sc vs. siABCD1, siACOX1, siHSD17B4, siTYSND1 p < 0.001]. Scale bar, 5 μm. Source data are provided as a Source Data file.\n\nFigure 3: Figure 3. a–c Fibroblasts derived from healthy controls (Cont #1, Cont #2) and HSD17B4-deficient patients (422_423DelAG; Patient #1, #2) were treated with sodium acetate (10 mM) for 24 h. a Intracellular acetyl-CoA levels were assessed using an acetyl-CoA ELISA kit from whole-cell lysates. Representative data from three independent experiments (n = 3) are presented as the mean ± SEM. [Patient #1, #2: Cont vs. Acetate p < 0.001]. b, c Primary cilia were immunostained with an anti-ARL13B (green) antibody, and the nuclei were counterstained with Hoechst 33342 (blue) dye. Data are presented as the mean ± SEM (n = 3, independent biological replicates). [Ciliated cells: Cont vs. Acetate; Cont #1 p = 0.0016, Cont #2 p = 0.0006, Patient #1 p = 0.0018, Patient #2 p = 0.0011; Cilium length: Cont vs. Acetate; Cont #1, 2, Patient #1, 2 p < 0.001]. d Schematic representation of HSD17B4 domains: dehydrogenase (pink), hydratase (blue), and SCP2 (yellow). The patient-derived mutations (G16S and N457Y) are indicated. e–g SY5Y/Cas9 HSD17B4-KO cells were transfected with hemagglutinin (HA)-tagged WT or mutant (G16S or N457Y) HSD17B4 constructs. e The expression of HSD17B4 was examined by western blotting. Representative blot from three independent experiments is shown. f, g HSD17B4 WT or mutant-overexpressing SY5Y/Cas9 HSD17B4-KO cells were co-stained with an anti-HA (red), anti-ARL13B (green) for primary cilia, and Hoechst 33342 (blue) for nuclei. Data are presented as the mean ± SEM (n = 3, independent biological replicates). [Ciliated cells: Cont vs. Acetate; Cont p = 0.0013, WT p = 0.0004, G16S p < 0.0001, N457Y p < 0.0001; Cilium length: Cont vs. Acetate; Cont p < 0.0001, WT p = 0.0016, G16S p < 0.0001, N457Y p < 0.0001]. P-value vs. between the indicated groups determined by one-way ANOVA followed by Tukey’s multiple comparisons test. Scale bar, 5 μm. Source data are provided as a Source Data file.\n\nFigure 4: Figure 4. a Schematic diagram of HDAC inhibitors. HDAC inhibitors were categorized into classes I, IIa, IIb, and IV, with each HDAC inhibitor targeting a different class of HDAC. b–d HSD17B4-KO SY5Y/Cas9 cells were separately treated with the indicated HDAC inhibitors for 24 h. The cells were immunostained with an anti-ARL13B (green) antibody and Hoechst 33342 (blue) dye. Data are presented as the mean ± SEM (n = 3, independent biological replicates). P-value vs. treatment determined by one-way ANOVA followed by Tukey’s multiple comparisons test [Ciliated cells: Cont vs. Acetate p = 0.0128, PIC34051 p = 0.0202, Tubastatin A (Tuba A) p = 0.0002, TSA p < 0.0001, VPA p = 0.0001, SAHA p = 0.0002; Cilium length: Cont vs. Acetate, RGF966, TSA, SAHA p < 0.0001, Tuba A p = 0.0185, VPA p = 0.0145]. e–g The HDAC6-WT or -KO MEFs were transiently transfected with a Sc or siHSD17B4 (#1, #2) for 72 h. e, f The primary cilia were immunostained with an anti-ARL13B (green) antibody and the nuclei were counterstained with Hoechst 33342 (blue) dye. Data are presented as the mean ± SEM (n = 3, independent biological replicates). P-value vs. indicated groups determined by one-way ANOVA followed by Tukey’s multiple comparisons test [Ciliated cells: WT vs. HDAC6-KO; siHSD17B4 #1 p = 0.0016, siHSD17B4 #2 p = 0.0023; Cilium length: WT vs. HDAC6-KO; siHSD17B4 #1 p < 0.0001, siHSD17B4 #2 p < 0.0002]. Scale bar, 5 μm. g The upregulation of acetylated α-tubulin (Ac-α-tubulin) was assessed by western blotting analysis using the indicated antibody. Representative blot from three independent experiments is presented. Source data are provided as a Source Data file.\n\nFigure 5: Figure 5. a Western blot analysis confirmed the downregulation of Hsd17B4 in Hsd17B4−/− mice (n = 3). b Growth retardation was assessed by imaging 11-week-old mice and measuring body weight from 3-week-old mice (Hsd17B4+/+ n = 9; Hsd17B4−/− n = 7). Data are presented as the mean ± SEM. Statistical analysis was performed using two-way ANOVA with multiple comparisons. Scale bars, 1 cm. c Kaplan-Meier survival curves comparing Hsd17B4+/+ (n = 25) and Hsd17B4−/− mice (n = 30) were analyzed using the Log-rank (Mantel-Cox) tests (p < 0.0001). d Representative images (n = 3) of H&E staining revealed reduced cerebellar volume, malformed lobules, and thinner molecular layers in Hsd17B4−/− mice. Scale bars, 500, 50, and 20 μm. e Molecular layer thickness was quantified in Hsd17B4+/+ (n = 7) and Hsd17B4−/− (n = 6) mice (p < 0.0001). Data are presented as the mean ± SEM. f Motor function was evaluated using the rota-rod test in 9- and 11-week-old mice. Box plots represent the interquartile range (25th–75th percentile), median (central line), and minimum/maximum values (whiskers) [9-week-old Hsd17B4+/+ (n = 6) Min = 59, Max = 300, Median = 280.5; Hsd17B4−/− (n = 5) Min = 18, Max = 190, Median = 105; 11-week-old Hsd17B4+/+(n = 6) Min = 24, Max = 300, Median = 196; Hsd17B4−/− (n = 3) Min = 1, Max = 131, Median = 1]. [Hsd17B4+/+ vs. Hsd17B4−/−; 9 weeks p = 0.0006, 11 weeks p = 0.0014]. g–j. Immunofluorescence staining for primary cilia (ARL13B, green, white arrow; DAPI, blue) was performed in granular (Scale bar, 2 μm) and Purkinje (Scale bar, 20 μm) layers. Purkinje cells were counterstained with anti-calbindin (red). Data are presented as mean ± SEM (n = 3, independent biological replicates). [Hsd17B4+/+ vs. Hsd17B4−/− Ciliated cells: p = 0.0078 (h), p = 0.0010 (j); Cilium length: p < 0.0001 (h, j)]. Statistical analysis was performed using a two-tailed unpaired t-test (e–j). k Western blot confirmed HSD17B4 expression in the cerebellum from three independent experiments. Source data are provided in the Source Data file."
      }
    ]
  },
  {
    "id": "PMC11924726_multi",
    "image": [
      "images/PMC11924726-f1.png",
      "images/PMC11924726-f2.png",
      "images/PMC11924726-f3.png",
      "images/PMC11924726-f4.png",
      "images/PMC11924726-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Genome-wide analysis of CHYR gene family and BnA03.CHYR.1 functional verification under salt stress in Brassica napus L.\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Phylogenetic tree of CHYR proteins from four species in Brassicaceae. Overall, 24 BnCHYRs (Green circle), 9 BoCHYRs (Perple star), 9 BaCHYRs (Blue triangle), and 7 AtCHYRs (Red box) were classified into three groups (Group I-III), and different groups of CHYR proteins were distinguished by different colored backgrounds. The neighbor-joining tree was generated through the MEGA11 program using the amino acid sequences of the CHYRs by the neighbor-joining (NJ) method, with 1000 bootstrap replicates\n\nFigure 2: Figure 2. Characterization of CHYR genes in B. napus. A The conserved motif location of BnCHYRs proteins in B. napus. and motif1-motif10 were showed by different colors. B The domain location of BnCHYR proteins, CHY-zinc finger, C3H2C3-type RING finger, zinc ribbon and hemerythrin domains (C) Distribution of cis-acting elements in the promoters of BnCHYRs. Different cis-acting elements are annotated by boxes of different colors. D Exon–intron structure features of BnCHYRs. Green boxes indicate exons, yellow boxes indicate UTR regions, Blackish-grey lines indicate introns. The bottom scale shows the protein length\n\nFigure 3: Figure 3. Distribution of BnCHYRs on chromosomes of B. napus. The name of each chromosome is presented at the top of the corresponding bar, and the gene names are given on the right side. The results on the left indicate the physical position in megabases (Mb)\n\nFigure 4: Figure 4. Collinearityy analyses of CHYRs among B. napus, B. rapa, B. oleacea, and A. thaniana. The species names with the prefixes “Bn”, “Br”, “Bo”, and “At” indicate B. napus, B. rapa, B. oleracea and A. thaliana, respectively. The grey lines represent the collinear blocks between different species, while the red lines and blue lines indicates the syntenic CHYR gene pairs. The chromosome number is labelled above or behind the each chromosome. The chromosomes of B. napus are shown in the form that symbol starting with A represents the chromosome originating from B. rapa, and symbol starting with C denotes the chromosome from B. oleracea\n\nFigure 5: Figure 5. Expression patterns of BnCHYR genes in response to cold (A), heat (B), salt (C) and PEG (polyethylene glycol) (D) treatments determined by real-time PCR. Rapeseed seedlings were sampled after 3, 6, 12 and 24 h under stress conditions. The expression level of the rapeseed Bnactin7 gene was used as the internal control to standardize the RNA samples for each reaction. The values were the mean ± SE from three samples"
      }
    ]
  },
  {
    "id": "PMC11955060_multi",
    "image": [
      "images/PMC11955060-f1.png",
      "images/PMC11955060-f2.png",
      "images/PMC11955060-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Current AAV-mediated gene therapy in sensorineural hearing loss\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic representation of the inner ear. The inner ear consists of the acoustical cochlea and the balance-related vestibular organs. The cochlear duct has a special structure with three separate fluid-filled spiral-shaped cavities inside the bone labyrinth called the scala vestibuli (SV), scala media (SM), and scala tympani (ST). The double-layered sensory epithelium is located on the surface of the organ of Corti, including OHCs, IHCs, and several types of SCs. TM: tectorial membrane; OHCs: outer hair cells; IHCs: inner hair cells; GER: great epithelia region; PCs: pillar cells; DCs: Deiter's cells; HeCs: Hensen's cells; AN: auditory nerve; SGN: spiral ganglion neuron.\n\nFigure 2: Figure 2. AAV structure and production. (a) Structural comparisons between natural AAV and rAAV. The transgene is substituted for the rep and cap genes from the genome of natural AAV and is limited to 4.7 kb without the ITR sequences. (b) The AAV-helper-free packaging system that is commonly used includes a transgene plasmid (vector plasmid), a Rep/Cap plasmid (packaging plasmid), and a helper plasmid. Host cells like HEK293 cells are co-transfected with the three plasmids that mediate replication of AAVs containing the transgene of interest.\n\nFigure 3: Figure 3. AAV delivery routes in the inner ear. Schematic diagram of the murine inner ear illustrating the approaches used to deliver therapeutic AAVs. AAVs can be delivered to the cochlea by cochleostomy and to the vestibular organs by RWM injection, utricle injection, or canalostomy. AAV particles are transported to the target cells by the lymphatic fluid in the spiral cavities."
      }
    ]
  },
  {
    "id": "PMC11970524_multi",
    "image": [
      "images/PMC11970524-f1.png",
      "images/PMC11970524-f2.png",
      "images/PMC11970524-f3.png",
      "images/PMC11970524-f4.png",
      "images/PMC11970524-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Evolution of diapause in the African turquoise killifish by remodeling the ancient gene regulatory landscape\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic of paralog specialization after gene duplication. After duplication from the same ancestral gene, genes from a paralog gene pair can specialize for different functions or states (e.g., diapause vs. development). (B) Examples of a paralog gene pair, with specialized expression of gene 1 in diapause (blue, EZH1) and gene 2 in development (orange, EZH2) in the African turquoise killifish. Bars represent mean expression level (normalized DESeq2 count) across replicates in diapause or development state. Dots show normalized DESeq2 counts in each replicate. Error bar is standard error of mean. Corrected p values (median from pairwise comparisons) from DESeq2 Wald test. (C) Boxplots showing expression levels (normalized DESeq2 counts) of all the specialized paralog pairs in diapause and development in the African turquoise killifish genome. Gene 1 of the paralog pair has a higher expression on average in diapause (blue) compared with development (orange), whereas gene 2 hasa higher expression on average in development (orange) compared with diapause (blue). p values from Kolmogorov-Smirnov test. (D) Schematic for binning paralog duplication time into 3 categories based on OrthoFinder pipeline with 71 species (see STAR Methods). Divergence time estimates are from Ensembl species tree. Binned categories include genes that were duplicated in the common ancestor of (1) all vertebrates or earlier (very ancient, >473 million years ago [mya]), (2) all fish (ancient, 111–473 mya), and (3) all killifish or the African turquoise killifish exclusively (recent or very recent, 0–111 mya). (E) Fraction of total paralog pairs within each of the very ancient (left), ancient (middle), and recent/very recent (right) binned categories. Violin plots represent the distribution of observed vs. expected specialized paralog fractions generated through 10,000 bootstrapped random sampling. Median and quartiles are indicated by dashed lines. The enrichment of diapause-specialized paralog pairs within each bin is compared with genome-wide expectation. p values from chi-square test. See also Figure S1.\n\nFigure 2: Figure 2. (A) Experimental design for analysis of RNA-seq datasets either publicly available (hollow circles) or de novo generated for this study (filled circles) (see also Table S1B). Killifish species are from Africa (with and without diapause) and South America (with diapause). Medaka and zebrafish are other teleost fish without diapause. The development stage (orange hollow circle) in the South American killifish corresponds to post-diapause development. Pre-Dia, pre-diapause; Dia, diapause; Dev, development; 6 days, 6 days in diapause; 1 month, 1 month in diapause. (B) Examples of paralog gene pair, with specialized expression of gene 1 in diapause (blue, EZH1) and gene 2 in development (orange, EZH2) in the South American killifish. Gene names displayed are the names assigned to the ortholog in the African turquoise killifish. Bars represent the mean expression level (normalized DESeq2 count) across replicates in diapause or post-diapause development state. Error bar is standard error of mean. Each dot represents the normalized expression level for all sample replicates in diapause or post-diapause development. p values from DESeq2 Wald test. (C) Boxplots showing the expression levels (normalized DESeq2 counts) of all the specialized paralog pairs in diapause and development in the South American killifish. Gene 1 of the paralog pair has a higher expression on average in diapause (blue) compared with development (orange), whereas gene 2 has a higher expression on average in development (orange) compared with diapause (blue). p values from Kolmogorov-Smirnov test. (D) Spearman’s rank correlation between ortholog genes that change with diapause in African turquoise killifish and South American killifish. Dots represent the fold change values of ortholog genes in diapause compared with development in the two species. Spearman’s correlation coefficient (r) and p values are indicated. Selected Gene Ontology (GO) terms shared between both species are listed on the right (see also Figure S2I and Table S2A). (E) Fraction of the total paralog pairs within each of the very ancient (left), ancient (middle), and recent/very recent (right) binned categories as described in Figure 1D. Violin plots represent the distribution of observed vs. expected specialized paralog fractions generated through 10,000 bootstrapped random sampling. Median and quartiles are indicated by dashed lines. The enrichment of diapause-specialized paralog pairs within each bin is compared with genome-wide expectation (reference). p values are from chi-square test. See also Figure S2.\n\nFigure 3: Figure 3. (A) Experimental design for the ATAC-seq datasets either publicly available (hollow circles) or de novo generated in this study (filled circles) (see also Table S1B). Pre-Dia, pre-diapause; Dia, diapause; Dev, development; 6 days, 6 days in diapause; 1 month, 1 month in diapause. (B) Principal-component analysis (PCA) on all chromatin accessibility regions in each species group: African turquoise killifish only (upper left), South American killifish only (upper right), all killifish species (lower left), and diapause-capable killifish (lower right). Each point represents the consensus ATAC-seq peaks (chromatin accessibility) from an individual replicate of a given species at a given developmental or diapause state. Percentage of the variance explained by each principal component (PC) is shown in parentheses. (C) Conservation analysis of genomic sequence and chromatin accessibility at very ancient paralogs with specialization in diapause vs. development. Left: schematic of the analysis. Right: percentage (e.g., conservation) of alignable regions containing diapause-specific chromatin accessibility (upper) and the conservation of diapause-specific chromatin accessibility (lower) near specialized ancient paralogs (see also Figures S3C–S3E). Although the majority of genomic sequences are ancient, the chromatin accessibility at those peaks evolved recently in the African turquoise killifish. p values from chi-square test. (D) Example of a chromatin accessibility regions (ATAC-seq peaks) at the promoter of genes from a very ancient paralog pair, with one gene specialized for expression in diapause (DNAJA4) and the other in development (DNAJA2). Replicates within each condition were aggregated by summation for visualization. Blue boxes and lines represent genomic features (exons and introns, respectively). (E) Examples of diapause-specific chromatin accessibility regions that are: ancient/very ancient (conserved across killifish and medaka or zebrafish; left), recent (conserved in at least 2 killifish species; middle), or very recent (specific to African turquoise killifish; right). Blue boxes and lines at the bottom represent genomic features for the closest gene (exons and introns, respectively). To generate tracks, reads per kilobase per million mapped reads (RPKM)-normalized reads were summed across replicates and biological time points (e.g., diapause and development separately) to obtain single tracks for each species. See also Figure S3.\n\nFigure 4: Figure 4. (A) Left: word cloud for transcription factors whose binding sites are enriched in the diapause-specific chromatin-accessible regions (ATAC-seq peaks) at specialized paralogs using hypergeometric optimization of motif enrichment (HOMER). Right: consensus binding sites for selected transcription factors. y axis represents informational content (i.e., bits), which scales based on single-base overrepresentation in the binding sequence (0: bases are represented equally at 25% each in reference sequences; 2: a single base dominates the entirety of reference sequences at 100%). (B) Conservation in other fish species of the transcription-factor binding sites enriched in the diapause-specific chromatin-accessible regions in the African turquoise killifish. The majority of diapause-specific sites are very recent (i.e., specific to the African turquoise killifish) and not enriched in killifish species without diapause. Selected representative motifs are highlighted. See also Figure S4.\n\nFigure 5: Figure 5. (A) Schematic of two possible mechanisms for the evolution of the diapause-specific transcription factor binding sites in the African turquoise killifish genome. Upper: gradual mutations paired with selective pressure lead to the formation of binding sites for specific transcription factors and accompanying chromatin accessibility. Lower: a site experiences a transposable element (TE) insertion event, providing a novel sequence that contains a binding site for a specific transcription factor and accompanying chromatin accessibility. (B) Percentage contribution of the two possible evolutionary mechanisms (mutation and TE insertion) for motif evolution in diapause-specific chromatin at specialized paralogs. Mutation-derived or TE-derived motifs are subdivided for their conservation either only in the African turquoise killifish (dark colors) or in at least one other species (light colors). Binding expectations are based on the HOMER log odds ratio binding criteria (see STAR Methods). The largest fraction of diapause-specific binding sites likely evolved through mutations exclusively in the African turquoise killifish. (C) Example of a transcription factor binding site that likely evolved via mutation: FOXO3 binding site in a diapause-specific chromatin-accessible region of the African turquoise killifish genome near GPC3 (LOC107379575) and aligned regions in other fish species. Aligned sequences are colored based on the similarity to the canonical FOXO3 binding site from HOMER (top track). (D) Aggregated informational content across all FOXO3 transcription factor binding sites in diapause-specific accessible chromatin regions and aligned regions in other species. y axis is formatted using informational content (i.e., bits). The African turquoise killifish motif exhibits highest similarity to the canonical FOXO3 binding site. (E) Fraction of diapause-specific chromatin-accessible regions under positive selection in the African turquoise killifish (see STAR Methods) at false discovery rate (FDR) < 0.1. These regions are enriched for many TF binding sites (e.g., REST, FOXO3, and PPARA). (F) Enrichment or depletion of specific transposable elements (TEs) in the diapause-specific chromatin-accessible regions (ATAC-seq peaks) in the African turquoise killifish genome as compared with three sets of reference regions: the overall genomic abundance of the given TE (“Genome”), the abundance of the given TE in all chromatin-accessible regions (“Chromatin”), and the abundance of the given TE in size-matched control regions 10 kb away from ATAC-seq peak of interest (“Control loci”). (G) Example of a diapause-specific chromatin accessibility region containing a PPARA binding site overlapping with a TE. Almost all TE-derived motifs are specific to the African turquoise killifish. See also Figure S5."
      }
    ]
  },
  {
    "id": "PMC11970524_multi_2",
    "image": [
      "images/PMC11970524-f6.png",
      "images/PMC11970524-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Evolution of diapause in the African turquoise killifish by remodeling the ancient gene regulatory landscape\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) CRISPR-Cas9-based platform to assess the effect of transcription factor knockout on diapause and development gene expression programs in injected (F0) embryos in the African turquoise killifish (upper). Scheme of the stages for RNA-seq analysis (lower). Six transcription factors (TFs) were selected: REST, FOXO3a, FOXO3b, PPARAa, PPARAb, and PPARG. CRISPR-Cas9-mediated knockouts were conducted by injecting 3 single guide (sgRNAs) per gene in single-cell embryos. Non-injected embryos (wild type) and embryos injected with scrambled sgRNAs (scramble) were used as controls. Genotyping and RNA-seq on individual embryos were performed at two stages: diapause (Dia, blue, 6 days) or development (Dev, orange). A total of 130 single-embryo RNA-seq libraries were generated and analyzed. (B) Principal-component analysis (PCA) of transcription factor knockouts and control RNA-seq samples in the African turquoise killifish. Each shape represents transcriptome of a single embryo. Knockouts and wild-type/scramble controls are denoted by different shapes. PPARAa knockout was lethal, and no viable embryos were recovered. Color denotes diapause (blue) or development (orange) for each embryo. Percentage of variance explained by each principal component (PC) is shown in parentheses. (C) Fold changes of differentially expressed genes (DEGs) between diapause and development for each transcription factor knockout compared with scrambled sgRNAs-injected embryos (scramble). Each dot represents a single gene. Significantly differentially expressed genes (DEseq2, FDR < 0.1) are in color: diapause (dark blue) or development (dark orange). Genes not significantly changed are in gray. PPARAa knockout was embryonic lethal, and no viable embryos were recovered. (D) Schematic of possible results for the RNA-seq data analysis. Correlation plot where the x axis represents the fold change of DEGs in diapause vs. development control (wild type and scramble), and the y axis represents the fold change of DEGs in diapause embryos of transcription factor knockout (KO) vs. scramble. No correlation would indicate that the TF knockout has no effect on the diapause program (upper right). A positive correlation would indicate that the diapause program is enhanced upon TF knockout (middle right). A negative correlation would indicate that the diapause program is decreased by TF knockout and switches to a development-like state (bottom right). (E) Correlation plot between the fold change of DEGs in diapause vs. development control (wild type and scramble) (x axis) and the fold change of DEGs in TF knockout (KO) vs. scramble (in diapause) (y axis). Similar results were observed with either type of control (wild type or scramble). Dots represent individual DEGs with FDR < 0.1. Spearman’s correlation ρ and p values are displayed for each transcription factor knockout plot. (F) GO enrichment analysis of the diapause-specific changes observed for the three TF knockouts. Enriched GO terms from gene set enrichment analysis (GSEA) were compared for diapause embryos in non-injected samples (wild type), scrambled-sgRNA-injected samples (scramble), and knockout samples (KO), respectively. Representative GO functions are listed on the right, and functions related to lipid metabolism are highlighted in boxes (see also Tables S6A–S6C). (G) Paralog specialization in diapause and development upon REST knockout. Paralog specialization for diapause and development (light blue/light orange) is reduced in the context of REST knockout (dark blue/dark orange) compared with control (median expression in both wild-type and scramble samples). p value is from two-way ANOVA. See also Figures S5 and S6.\n\nFigure 7: Figure 7. (A) Experimental design for untargeted lipidomics in the African turquoise killifish (with diapause) and the red-striped killifish (without diapause). (B) Principal-component analysis (PCA) on the estimated concentrations for all detected lipids for the African turquoise killifish only (left) and for both killifishes (right). Each point represents an individual replicate from a given species at a given developmental or diapause stage. Variance explained by each principal component (PC) is shown in parentheses. (C) Heatmaps representing the fold change of significantly different triglycerides between diapause vs. development in the African turquoise killifish (upper) and between the African turquoise killifish vs. red-striped killifish (development only, lower). Fold change values are plotted between each pairwise comparison between diapause and development time points, or the two development or diapause time points. For most triglycerides, levels are higher at both 1-month and 6-day diapause relative to development. The bottom panel shows the fold change values of the same lipids in the African turquoise killifish compared with the red-striped killifish; levels of most triglycerides are higher in the African turquoise killifish. Very-long-chain fatty acids among displayed triglycerides species are highlighted in green. (D) Lipid abundance counts for very-long-chain triglycerides (TGs) in the African turquoise killifish during development (orange) and diapause (blue) time points. Bars represent mean ± SEM. Dots represent individual replicates. p values from Welch’s t test. (E) Representative images of BODIPY 493/503 staining in the African turquoise killifish embryos in diapause and development (63× objective). Diapause embryos (left) were either 6 days or 1 month in diapause (Dia). Development embryos (right) were either pre-diapause (pre-Dia) or in 1 day of development (Dev). Scale bars, 5 μm. White arrows highlight lipid droplets stained by BODIPY. (F) Quantification of lipid droplet number (normalized to the 1-month diapause time point) in African turquoise killifish embryos stained with BODIPY 493/503. Bars represent mean ± SEM. Each dot represents an individual embryo. Graph represents five experiments merged. p values from Welch’s t test (see Table S7D). See also Figure S7."
      }
    ]
  },
  {
    "id": "PMC11994451_multi",
    "image": [
      "images/PMC11994451-f1.png",
      "images/PMC11994451-f2.png",
      "images/PMC11994451-f3.png",
      "images/PMC11994451-f4.png",
      "images/PMC11994451-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Precise in vivo RNA base editing with a wobble-enhanced circular CLUSTER guide RNA\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a, Design of the cis-acting editing reporter and illustration of the applied triplet base-pairing motifs. The orientation of wobble base pairs at nearest neighbor positions or the presence of G or C counter bases modulate Δ-editing at the central A of a triplet in comparison to its fully Watson–Crick base-paired counterpart. All triplet base-pairing motifs with ocher background color were installed at the empty dotted outline within the cis-acting editing construct to generate the results in b,c. b, Suppression of RNA editing in different target triplets using G•U wobble base pairs or G•A mismatches. c, Enhancing RNA editing in different target triplets using U•G wobble base pairs. The Sanger sequence analysis in b and c was performed after transfection of editing reporter plasmids into ADAR1 p110 Flp-In T-REx cells. Data in b and c are shown as the mean ± s.d. of n = 3 biological replicates. For statistical analysis, a Student’s t-test (two-tailed, parametric) was applied.\n\nFigure 2: Figure 2. a, Schematic of 111-nt-long unstructured linear LEAPER guide RNA. b–d, Editing heat maps of the LEAPER guide RNA-binding sites within the indicated transcripts: AHI1 (b), COL3A1 (c) and BMPR2 (d). The basic design column, LEAPER, lacks G•A mismatches and wobble base pairs. The other guide RNAs contain either G•A mismatches or G•U wobbles at G•U-amenable sites or a combination of both solutions at all bystander sites. In the latter case, G•A mismatches are placed at sites not amenable to G•U wobbles. The triplet context for each listed editing event is given with the target A highlighted in green and all off-target A bases in blue. The position of each site is given relative to the transcript and the target A (±0 position). Editing was performed with plasmid-borne guide RNA and target in HeLa cells (endogenous ADAR). Data are shown as the mean editing percentage ± s.d. of n = 3 (AHI1 and COL3A1) or n = 5 (BMPR2) biological replicates.\n\nFigure 3: Figure 3. a, Schematic of the λN-ADAR editing system. The 2× boxB motif-containing guide RNA (84 nt) binds its target mRNA (through 49 bp) to recruit the engineered hyperactive λN-ADAR2Q editase. b, Editing heat map of exogenous AHI1 W725>amber mRNA targeted by the λN-ADAR system. c, Schematic of the Cas13b-ADAR system. The DR motif-containing guide RNA (87 nt) binds its target mRNA (through 51 bp) to recruit the engineered PspCas13b-ADAR editase carrying a hyperactive ADAR2 E488Q deaminase domain. d, Editing heat map of exogenous AHI1 W725>amber mRNA targeted by the Cas13b-ADAR system. e, Schematic of a symmetric ASO bound to its target mRNA (through 58 nt). The ASO is end-blocked by 2′-OMe, contains phosphorothioate linkages and recruits endogenous ADARs. f, Editing heat map of the ASO binding site within exogenous PEX1G843D transcript. In b,d,f, the basic designs (columns 2× boxB, DR guide RNA and ASO) do not contain G•A mismatches, wobble base pairs or 2′-OMe modifications beyond the end-blocks. The other guide RNAs contain additional 2′-OMe modifications, G•A mismatches, G•U wobbles at G•U-amenable sites or a combination of these solutions at all bystander sites. In the case of a combined solution, G•A mismatches or 2′-OMe modifications are placed at sites not amenable to G•U wobbles. The triplet context for each listed editing event is given with the target A highlighted in green and all off-target A bases in blue. The position of each site is given relative to the transcript and the target A (±0 position). Editing was performed in HeLa cells using plasmid-borne guide RNAs (2× boxB and DR guide RNA) and editase (λN-ADAR2Q and Cas13b-ADAR2Q) or ASOs recruiting endogenous ADAR. Data are shown as the mean editing percentage ± s.d. of n = 3 biological replicates.\n\nFigure 4: Figure 4. a, Results from an in silico search for RS-binding sites within the murine Mecp2 W104>amber ORF when applying the previous filter settings to the GuideRNA-Forge tool. The binding site for the SD is displayed in turquoise and outlined in black. It contains the target A in green and underlined. All potential RS-binding regions ≥ 20 nt length, in which binding sites for RSs can be selected, are displayed in light blue. The previous filter excludes all A bases except for those within a 5′-GAB (B = U, C or G) triplet context. b, Results for the same in silico search with the latest filter that included A bases in a 5′-GAB, 5′-UAB, 5′-BAU, 5′-KAAU and 5′-CAC triplet context, in addition to allowing A bases independent of their sequence context at the edges of a detected binding region. c, Illustration of binding regions in which specific binding sites of RSs of three circular CLUSTER guide RNAs are located within the Mecp2 ORF, generated using the previous filter (V1 and V2) or the latest filter (V3). d, Editing was performed with plasmid-borne guide RNA and murine Mecp2 transcript in HeLa cells (endogenous ADAR). e, Secondary structure prediction of guide RNA V1–V3 generated using the ViennaRNA Package 2.0 (ref. 54). The mean free energy (MFE) of the antisense part (SD and CLUSTER of RS) is given in kcal per mol. The dot–bracket ratio (DBR) indicates the number of dots (unpaired bases) per bracket (paired bases) within the dot–bracket annotation of the antisense part. Data are shown as the mean editing percentage ± s.d. of n = 3 biological replicates. For statistical analysis, a Student’s t-test (two-tailed, parametric) was applied.\n\nFigure 5: Figure 5. Editing heat map of guide RNA-binding sites within the murine Mecp2 W104>amber transcript. The triplet context for each listed editing event is given with the target A highlighted in green and all off-target A bases in blue. The position of each site is given relative to the transcript and the target A (±0 position). Editing was performed with plasmid-borne guide RNA and murine Mecp2 transcript in HeLa cells (endogenous ADAR). a, Circular CLUSTER guide RNA design. b, Circular LEAPER guide RNA design. c, Yields achieved using circular unstructured LEAPER guide RNAs containing a 111-nt-long antisense part. The basic design (column circular LEAPER) does not contain bystander solutions. The other guide RNAs either contain G•A mismatches or apply U depletion at all bystander sites, G•U wobbles at G•U-amenable sites or a combination of G•A mismatching or U depletion with G•U wobbles at amenable sites. d, Yields achieved using circular CLUSTER guide RNAs containing a 100-nt-long antisense part split into a targeting sequence (20 nt) and four RSs (each 20 nt). The basic design (column circular CLUSTER) does not contain bystander solutions. The other guide RNAs contain G•U wobbles at positions −49, −27 and +48, as well as no bystander solution, G•A mismatch or depleted U at position −5. Data in a,b are shown as the mean editing percentage ± s.d. of n = 3 biological replicates."
      }
    ]
  },
  {
    "id": "PMC11994451_multi_2",
    "image": [
      "images/PMC11994451-f6.png",
      "images/PMC11994451-f1-2.png",
      "images/PMC11994451-f2-2.png",
      "images/PMC11994451-f3-2.png",
      "images/PMC11994451-f4-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Precise in vivo RNA base editing with a wobble-enhanced circular CLUSTER guide RNA\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a, Editing yields in different brain regions, after delivery of the AAV-PHP.eB-encoded guide RNA through retro-orbital injection into Rett mice carrying the Mecp2 W104>amber mutation and quantification by Sanger sequencing 4 weeks later. b, Correlation between the median editing in a and the geometric mean of the RT–qPCR targets in c,g,i,k. Olfactory bulb, Ob; cerebellum, Cb; hippocampus, Hi; cortex, Cx; midbrain, Mb; thalamus, Th; brainstem, Bs. c, Guide RNA expression quantified by RT–qPCR (normalized to the geometric mean of Actb, Rps29 and Rnu6. d, As in b but correlating a,c. e, Absolute quantification of AAV episomes per cell by standard curve qPCR (normalized to Actb). f, As in b but correlating a,e. g, As in c but for Adar1. h, As in b but correlating a,g. i, As in c but for Adar1 p150. j, As in b but correlating a,i. k, As in c but for Adar2. l, As in b but correlating a,k. m, Bystander off-target events at the guide RNA-binding sites and the TS. n, All amplicon reads with on-target editing binned according to their number of bystander events (based on Supplementary Fig. 14). o, Global RNA editing at 2,533 endogenous sites (coverage ≥ 50 reads, REDIportal55). p, Thalamus sections stained for MeCP2 and DAPI (nuclei). For a, data are shown as the median editing percentage ± 95% CI determined in n = 3 mice (nontargeting virus) and n = 5 mice (targeting virus). For statistical analysis, a Mann–Whitney U-test (two-tailed, nonparametric) was applied. For c,e,g,i,k,m,n, data are shown as the median fold change ± 95% CI or median number of copies per cell ± 95% CI determined in n = 2 mice (three technical replicates each). The NGS analysis in o is based on results from n = 1 (nontargeting virus) or n = 2 (targeting virus) mice. The results in p are derived from n = 1 mouse per group. For b,d,f,h,j,l, the R² values were determined by simple linear regression.\n\nFigure 1: Figure 1. (a) Schematic of the utilized cis-acting editing reporter construct. (b) Editing yields when applying G·A mismatches or G·U wobbles for editing suppression at the 5’-UAG triplet in either ADAR1 p110-, ADAR p150- or ADAR2-Flp-In T-REx cells. The exact position of each mismatch or wobble is indicated below each bar. The target adenosine is highlighted in green, bold and underlined. Bases that induce wobbles or mismatches are highlighted in dark blue and bold. The 5’ and 3’ orientation of the triplet and the used ADAR isoform are shown above the grouped bars. (c) As b) but regarding editing yields when applying enhancing U·G wobbles. Data for b) and c) are shown as the mean ± s.d. of N = 3 biological replicates per bar. For statistical analysis, a student’s t-test (two-tailed, parametric) was applied.\n\nFigure 2: Figure 2. (a-b) Editing heat-map of the LEAPER guide RNA binding site within the indicated transcripts. The basic design column, LEAPER, lacks G·A mismatches and wobble base pairs. The other guide RNAs contain either G·A mismatches or G·U wobbles at G·U amenable sites or a combination of both solutions at all bystander sites. In the latter case, G·A mismatches are placed at sites not amenable to G·U wobbles. The triplet context for each listed editing event is given with the target adenosine highlighted in green and all off-target adenosines in blue. The position of each site is given relative to the transcript and the target adenosine (±0 position). The editing events detected at position 2546 ( + 47) and 2548 ( + 49) of the NUP43 transcript were natural events and were thus skipped in regard to bystander suppression. Editing was performed with plasmid-borne guide RNA and endogenous target transcripts in HEK293FT cells (endogenous ADAR). Data are shown as the mean editing percentage ± s.d. of N = 3 biological replicates.\n\nFigure 3: Figure 3. (a) Design of the cis-acting RNA editing reporter constructs used in e) and f). (b) Design of the linear trans-acting CLUSTER guide RNAs used in g). (c) Illustration of the base-pairing motifs applied to the constructs in a) (ocher) and b) (grey) that were used to suppress bystander editing at the 5´-U[AAG] sequence motif in e) and g). (d) As c) but for the 5´-[UAA]U sequence motif and the results in f). (e) Suppression of bystander editing at the 5´-NN A and concurrent effect on the target A editing yield in a 5’-U[AAG] sequence motif. (f) Similar to e) but targeting the A in a 5’-[UAA]U sequence motif and suppressing bystander editing at a 3´-NN A. Editing in e) and f) was performed in ADAR1 p110 Flp-In T-REx cells using plasmid-borne reporters as displayed in a). (g) Suppression of bystander editing at a 5´-NN A when editing a 5’-U[AAG] site (K984) of the human BMPR2 transcript using trans-acting CLUSTER guide RNAs. (h) Meta-analysis of bystander suppression at 5´- and 3´-NN sites over three different target transcripts (AHI1, BMPR2 and COL3A1), three different A-rich target triplets flanked either 5’ and/or 3’ by uridines (5’-[UAA]U, 5’-U[AAG], 5’-U[AAA]U), and applying two trans-acting site-directed RNA editing systems (CLUSTER/endogenous ADAR, boxB/λN-ADAR2Q). The full data set of the meta-analysis is shown in Supplementary Fig. S5. Editing in g) and h) was performed in HeLa cells using plasmid-borne editase (λN-ADAR2Q) and/or guide RNA (2x boxB, CLUSTER). Data in e) – g) are shown as the mean editing percentage ± s.d. of N = 3 biological replicates. Data in h) are shown as the mean editing percentage ± s.d. of three 5’-NN off-target sites, seven on-target sites, and five 3’-NN off-target sites containing N = 3 biological replicates per site. The center line represents the median, the plus-sign the mean. The whiskers extend to the minimum and maximum values. The box limits the 25th and 75th percentile. For statistical analysis, a student’s t-test (two-tailed, parametric) was applied.\n\nFigure 4: Figure 4. The guide RNA is expressed from either a polymerase III (for example U6) or a polymerase II (for example CAG) promoter with a corresponding terminator. 5’ and 3’ ribozymes auto-cleave the primary transcript resulting in a 5’-OH and a 2’,3’-cyclic phosphate overhang, respectively, which are subsequently ligated by the endogenous RTCB ligase. In the final guide RNA, the ligation stem (orange) forms a nearly continuous duplex with the split-R/G motif (light green), only interrupted by a five-nucleotide bulge. The circular guide RNA binds to its target transcript. Strategic placement of wobble base pairs within the recruitment sequences (RS) and/or the specificity domain (dark green) suppresses off-target editing, while a C-A mismatch within the specificity domain (SD) promotes on-target A-to-I RNA editing."
      }
    ]
  },
  {
    "id": "PMC11994451_multi_3",
    "image": [
      "images/PMC11994451-f5-2.png",
      "images/PMC11994451-f6-2.png",
      "images/PMC11994451-f7.png",
      "images/PMC11994451-f8.png",
      "images/PMC11994451-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Precise in vivo RNA base editing with a wobble-enhanced circular CLUSTER guide RNA\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 5: Figure 5. Panels (a) to (d) give schematic representations of the used linear and circular LEAPER and CLUSTER guide RNAs and their binding to the target mRNA. LEAPER guide RNAs were 111 nt long, centered with a C-A mismatch on the target adenosine. CLUSTER guide RNAs combined an ADAR-recruiting domain (R/G motif), a 20 nt long specificity domain containing the C-A mismatch with the target adenosine at position 8, and a cluster of three recruitment sequences of 20 nt length each. The circular CLUSTER guide RNA combines the ligation stem for circularization with the ADAR-recruiting motif into a split-R/G motif. (e) Editing heat-map using linear and circular LEAPER guide RNAs as seen in a) and b). (f-h) Editing heat map using linear and circular CLUSTER guide RNAs as seen in c) and d). Notably, the linear R/G version 21 guide RNA achieved already highly precise editing with an impressive 38 ± 7% on-target editing yield, clearly better than the best circular LEAPER guide RNA design (25 ± 2% on-target yield) with similar precision. A circular CLUSTER guide RNA with six recruitment sequences, but lacking the ADAR recruitment motif, achieved 54 ± 7% on-target editing with very high precision after applying the GU wobble strategy. However, adding a split-R/G recruiting motif achieved even better on-target editing yields of 75 ± 1% to 82 ± 1%, even though only 4 recruitment sequences were applied. GU wobbling was required to eliminate bystander editing at the binding sites of recruitment sequences. The triplet context for each listed editing event is given with the edited adenosine highlighted in bold green. The position of each bystander site (bold blue) is given relative to the target adenosine (±0 position). Editing was performed with plasmid-borne guide RNA and murine Mecp2 in HeLa cells (endogenous ADAR). Data are shown as the mean editing percentage ± s.d. of N = 3 biological replicates.\n\nFigure 6: Figure 6. The circular state of the split-R/G CLUSTER guide RNA (V27.2.4, pTS2108) targeting mMecp2 W104Amber was verified by using quantitative RT-PCR on in vitro samples from transfected HeLa cells. As reference a linear version of the same guide RNA was used. The dataset was normalized to human RNU6 snRNA. The amplicon of the outward primer pair in a) is 187 bp long and requires reverse transcription and PCR through a strong hairpin structure. It can thus not be directly compared to the inward primer pair in d) which is smaller (75 bp) and does not contain inhibitory secondary structures. (a) Binding sites of the outward primer pair, which can only amplify circular guide RNAs. (b) Fold change of linear and circular split-R/G CLUSTER guide RNAs (V27.2.4, pTS2108, pTS2228) relative to endogenous human RNU6 as detected by using the outward primer pair. The 2984-fold difference between linear and circular shows that the endogenous circularization of the guide RNAs though the RTCB ligase (Extended Data Fig. 4) was successful and that the outward primer pair can identify circular guide RNAs with high confidence (low type-I error rate). (c) Type-I error rate calculated from b) amounts to only 0.03%, thus 99.97% of circular guide RNAs are correctly identified. (d) Binding sites of the inward primer pair, which can amplify both linear and circular guide RNAs. (e) Fold change of linear and circular split-R/G CLUSTER guide RNAs (V27.2.4, pTS2108) relative to endogenous human RNU6 snRNA as detected by using the inward primer pair. The 235-fold difference between linear and circular shows the high level of total guide RNA enrichment achieved after circularization. (f) Percentage of successfully circularized guide RNAs calculated from e). Under the assumption that the 235-fold increase detected for circular guide RNAs compared to linear ones solely depends on circularization, 99.6% of all guide RNAs were successfully processed by the ribozymes of The tornado expression system and then ligated by RTCB. Data in b) and e) are shown as the mean editing percentage ± s.d. of N = 3 biological replicates.\n\nFigure 7: Figure 7. (a) Editing heat map of the indicated brain tissue of Rett syndrome mice treated with either the scrambled circular CLUSTER guide RNA virus (nontargeting virus) or (b) the circular CLUSTER guide RNA virus (targeting virus). The triplet context for the target-site row is boxed, and the target adenosine underlined and green. All other triplet contexts contain an off-target adenosine in blue. The position of each site is given relative to the transcript and the target adenosine (±0 position). The dataset covers the complete guide RNA binding region including all binding sites (BS) and the target sequence (TS) containing the target adenosine. Data are shown as the mean editing percentage of N = 2 mice.\n\nFigure 8: Figure 8. (a) Rett mice injected with wobble-optimized circular CLUSTER guide RNA (targeting virus) versus scrambled guide RNA (nontargeting virus). (a) (top) A-to-G RNA editing index in coding sequences. An index of 1 means 1% of RNA nucleotides mapped to genomic adenosines are guanosines. The index was stable (no change in global editing activity due to the targeting guide RNA). (a) (bottom) Global RNA editing at 2,528 endogenous sites (coverage ≥ 50, REDIportal55). With only 3 sites showing > 25% Δ-editing (beyond blue dotted lines), no clear off-target editing was detectable in comparison to panel b. (b) Reanalyzed RNA-seq data (previous study44). With respect to the tissue selected in panel c), data from the brainstems of two untreated Rett mice are compared. (b) (top) Both untreated mice show a stable editing index. (b) (bottom) Global RNA editing at 2,301 endogenous sites (coverage ≥ 50). These sites are also displayed in panel a) (bottom) and c) (bottom). The 7 sites showing > 25% Δ-editing are considered normal mouse to mouse and technical variability. (c) Reanalyzed RNA-seq data (previous study44). Rett mice injected with boxB/λN-ADAR2 virus were compared to untreated ones. The ADAR2 catalytic domain in the virus is from the native ADAR2 protein. (c) (top) The A-to-G index increase by 0.007 in the coding space reflects a substantial and somewhat concerning increase in global editing, probably due to the overexpressed ADAR2 catalytic subunit. (c) (bottom) Global RNA editing at 2,533 endogenous sites that include the 2,528 sites shown in panel a) (coverage ≥ 50 reads). 25 sites showing > 25% Δ-editing after injection of the λN-ADAR2 targeting virus. This is in clear contrast to the very high precision seen for CLUSTER guide RNAs recruiting endogenous ADARs in a) (bottom) or the untreated mice in b) (bottom). Importantly, the potential off-target sites included two ADAR2-specific, highly evolutionary conserved sites in GRM4 (glutamate transmission) and NOVA1 (splicing)49. Data in a), b) and c) are based on results from N = 1-2 mice per group. Thalamus and brainstem were selected for showing the highest editing yields in their respective study.\n\nFigure 9: Figure 9. (a) Confocal images of sections of thalamus stained for MeCP2 protein and DAPI to indicate nuclei. MeCP2 puncta staining, co-localizing with DAPI, only seen in middle and lower panels indicating restoration of endogenous protein expression. Nuclei (DAPI) were pseudo-colored to highlight colocalization puncta. (b) Each bar represents the total percentage of MeCP2 protein foci positive cells relative to DAPI positive cells in each mouse group. Each datapoint represents one microscopic field of view. Non-injected Rett mice show background levels of immunofluorescence44. The distribution of positive nuclei in non-injected wild-type mice reflects the cellular heterogeneity within the brain. Analysis was performed by confocal imaging in three sections from each brain region indicated in the figure. We selected the four brain regions with the highest editing yields. Data is shown as the median percentage of cells showing MeCP2 protein foci ± c.i. (confidence interval 95%) from N = 2 mice per bar, as counted in 3 (non-injected Rett mice) or 6 (injected Rett mice) fields of view per animal. (c) High correlation between the median editing yields (amplicon sequencing) and the percentage of cells with MeCP2 protein foci in the four brain regions in a). The abbreviations stand for Cortex (Cx), midbrain (Mb), thalamus (Th), and brainstem (Bs). Data is shown as one datapoint per brain region. Each datapoint represents the median result of the respective tissue from N = 2 mice injected with targeting virus per readout. For technical reasons the correlated editing yields and protein foci percentages are from different animals."
      }
    ]
  },
  {
    "id": "PMC11997137_multi",
    "image": [
      "images/PMC11997137-f1.png",
      "images/PMC11997137-f2.png",
      "images/PMC11997137-f3.png",
      "images/PMC11997137-f4.png",
      "images/PMC11997137-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal membrane protein PMP70 confers drug resistance in colorectal cancer\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A, B Western blot analysis and quantification of PMP70 protein levels in 38 primary tumor tissues and 9 LOHP-treated CRC tumor tissues. Protein levels were quantified using ImageJ. C PMP70 scores in CRC primary tumor tissues with and without recurrence, subgrouped by treatment types in the GSE106584 dataset. FOLFOX: LOHP + 5FU+Leucovorin; RT: Radiotherapy. D Western blot analysis of PMP70 protein levels and RNA-seq analysis of ABCD3 mRNA expression in 38 CRC primary tumor tissues at different T stages. Protein levels were quantified with ImageJ. E Representative immunofluorescence images showing colocalization of PMP70 and CD133. F Western blot analysis of PMP70 and CD133 protein levels in 13 CRC primary tumor tissues. G Correlation analysis of PMP70 and CD133 protein levels in 38 CRC tumor tissues based on ImageJ quantification of Western blots. H CD133 protein levels in CRC tumor tissues at early versus advanced T stages. *P < 0.05, **P < 0.01, ***P < 0.001.\n\nFigure 2: Figure 2. A Representative confocal images of PMP70 puncta in parental and LOHP-tolerant CRC cells treated with LOHP. B Quantification of PMP70 puncta in panel (A). C Confocal images of HCT116 cells expressing dKeima-SKL with or without LOHP treatment (60 μM). D Flow cytometry analysis and quantification of HCT116 cells expressing dKeima-SKL treated with LOHP (40 μM). Data represent 4–5 images and >15 cells per condition. E, F Confocal images and quantification of PMP70 puncta in HCT116 cells treated with vehicle or 10 μM CQ in the presence or absence of LOHP. Data represent 5–6 images and >25 cells per condition. G, H Colocalization of PMP70 puncta and LC3 puncta in HCT116 and HCT116L cells, both treated by vehicle and 60 μM LOHP. Panel (H) is the quantification of panel G. 5 ~ 6 images, total of 25+ cells counted per condition. I Ubiquitinated-PMP70 increased upon LOHP treatment in HCT116 than in HCT116L cells. HCT116 and HCT116L cells were transfected with HA-Ub for 24 h and then treated with LOHP (60 μM) for 24 h. Co-immunoprecipitation of PMP70 with HA, and corresponding inputs. *P < 0.05, **P < 0.01, ***P < 0.001.\n\nFigure 3: Figure 3. Representative images (A) and quantification (B) of colony formation and sphere formation assays of PMP70-depleted and control HCT116L cells. C Western blot analysis of PMP70, CD133, CD44, and Nanog expression in sgPMP70 and sgNC HCT116L cells. D Effects of LOHP on cell survival measured by CCK8 assays in sgNC and sgPMP70 HCT116L cells (left panel). Survival curves for HCT8L cells transfected with siRNA targeting PMP70 or control siRNA in response to LOHP (right panel). The IC50 of LOHP for each condition is indicated in the plots. E Representative images of xenograft tumors derived from sgPMP70 or sgNC HCT116L cells treated with LOHP or vehicle. F Tumor growth curves and tumor weight quantification in different treatment groups. G IHC staining of PMP70 and CD133 in tumor tissues from control or LOHP-treated mice bearing sgNC or sgPMP70 HCT116L xenografts. H Quantification of panel (G). *P < 0.05, **P< 0.01, ***P < 0.001.\n\nFigure 4: Figure 4. A Volcano plot showing lipid species significantly altered between sgPMP70#2 and control HCT116L cells. PE: phosphatidylethanolamine; ePE: ether-PE; PUFA: polyunsaturated fatty acid. B Lipid ROS levels measured using BODIPY 581/591-C11 in sgPMP70 and control HCT116L cells, as well as in HCT8L cells transfected with siRNA targeting PMP70 or control siRNA. C Fluorescence histograms of BODIPY 581/591-C11 and MitoSOX Red staining in sgPMP70 and control HCT116L cells, illustrating LPO and mitochondrial ROS levels, respectively. D Quantification of mean fluorescence intensity of MitoSOX Red staining in sgPMP70 and control HCT116L cells. E Mitochondrial stress profile of sgPMP70 and control HCT116L cells, assessed using Seahorse extracellular flux analysis. F Western blot analysis of PMP70 and GPX4 in various CRC cell lines. G Correlation between PMP70 and GPX4 protein levels in the CPTAC-COAD dataset (n = 97). H LPO in HT29 and DLD1 cells transfected with siRNA targeting PMP70 (siPMP70#1, #2), GPX4 (siGPX4#1, #2), or control siRNA. *P < 0.05, **P < 0.01, ***P < 0.001.\n\nFigure 5: Figure 5. A Cell viability of HCT116 and HCT8 cells treated with liproxstatin-1 (Lip-1, 2 μM) under different doses of LOHP (n = 6). B Percentage of oxidized lipids measured by BODIPY 581/591-C11 in HCT116L, HCT8L, and their parental cells, with or without LOHP treatment (20 μM, 48 h). C LPO levels in HCT116L cells transduced with sgPMP70 or sgNC and in HCT8L cells transfected with siPMP70 or siNC after LOHP treatment (10 μM). D Cell viability of siPMP70#1 and control cells treated with LOHP (HCT8L:20 μM, HCT116L:40 μM) and LOHP combined with different cell death inhibitors (2 μM Lip-1, 10 μM Z-VAD-fmk, 1 μM Nec1s, and 10 μM NAC). E 4-HNE IHC staining of control or LOHP-treated mice bearing HCT116L tumors transduced with sgNC or sgPMP70 (n = 5). Right chart: quantification of the staining intensity using ImageJ. F Survival curve and LPO levels in siPMP70 or control DLD1 cells after LOHP treatment (20 μM). *P < 0.05, **P < 0.01, ***P < 0.001."
      }
    ]
  },
  {
    "id": "PMC11997137_multi_2",
    "image": [
      "images/PMC11997137-f6.png",
      "images/PMC11997137-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Peroxisomal membrane protein PMP70 confers drug resistance in colorectal cancer\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A Volcano plots of lipid species significantly altered by LOHP compared to vehicle treatment in sgPMP70 #2 (right panel) and sgNC (left panel) HCT116L cells. LPI: lysophosphatidylinositols; ChE: cholesteryl ester; LPC: lysophosphatidylcholine; PS: phosphatidylserine; PC: phosphatidylcholine; PE: phosphatidylethanolamine. B Volcano plots of lipid species significantly altered between sgPMP70 #2 and sgNC HCT116L cells under LOHP (right panel) or vehicle treatment (left panel). TG: triacylglycerol. C–E HCT116L cells transduced with sgPMP70 (#2, #3) or sgNC were transfected with mCherry-SKL for 48 h. Scale bar = 10 μm. LDs were stained with Lipi-Blue (100 nM, Dojindo) for 30 min and analyzed by confocal microscopy (panel C). Quantification of LDs per cell is shown in panel (D). Quantification of peroxisome-LD contacts per cell is shown in panel (E). F Immunoblots of SOAT1, DGAT1, and GAPDH in sgPMP70 and sgNC HCT116L cells. *P < 0.05, **P < 0.01, ***P < 0.001.\n\nFigure 7: Figure 7. A Gene Set Enrichment Analysis (GSEA) showing the downregulated cell cycle pathway (KEGG HSA04110) in sgPMP70#2 vs. sgNC cells. B Volcano plots showing significantly differentially expressed genes between sgPMP70#2 or sgPMP70#3 and sgNC cells. ABCD3 and cell cycle-related genes (e.g., E2F1, CDT1, and MCM family members) are labeled. C Quantitative real-time PCR analysis of cell cycle-related gene expression in sgPMP70 or sgNC HCT116L. Data represent relative mRNA expression levels normalized to control. D Cell cycle distribution of sgPMP70#2 cells compared to sgNC, assessed by flow cytometry. The percentage of cells in G0/G1, S, and G2/M phases is shown. E Schematic representation of the effects and potential mechanisms underlying PMP70 downregulation in LOHP-resistant CRC cells. **p < 0.01, ***p < 0.001. Data are presented as mean ± SD."
      }
    ]
  },
  {
    "id": "PMC12021669_multi",
    "image": [
      "images/PMC12021669-f1.png",
      "images/PMC12021669-f2.png",
      "images/PMC12021669-f3.png",
      "images/PMC12021669-f4.png",
      "images/PMC12021669-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Establishment of CRISPR‐STAR System to Realise Simultaneous Transcriptional Activation and Repression in Yarrowia lipolytica\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Investigation of bidirectional transcriptional regulation by targeting different positions of the gene. (A) The schematic diagram of sgRNAs with dCas9‐VPR targeting the promoter PFBAin of gene FAR. (B) Relative transcriptional level of FAR measured by RT‐qPCR. (C) The schematic diagram of sgRNAs with dCas9‐VPR targeting the ORF of gene PEX10. (D) Relative transcriptional level of PEX10 measured by RT‐qPCR. Transcription levels are normalised to the control strain sg0. Values and error bars indicate mean ± standard deviation (SD) of three biological replicates. Asterisks denote two‐tail p value as determined by two‐sample t test, with *p ≤ 0.05.\n\nFigure 2: Figure 2. The optimization of CRISPR‐STAR system in Y. lipolytica. (A) ScRNA design when dCas9 was employed in CRISPR‐STAR system. (B) The schematic diagram of sgRNAs targeting different positions of synthetic promoter PGAL1UAS‐TEF. (C) Activation efficiency of GFP by the CRISPRa/dCas9‐STAR system recruiting different activator. (D) ScRNA design when dCpf1 was employed in CRISPR‐STAR system. (E) The schematic diagram of crRNAs targeting different positions of synthetic promoter PGAL1UAS‐TEF. (F) Activation efficiency of GFP by the CRISPRa/dCpf1‐STAR system recruiting different activator. (G) Activation of the GFP gene by CRISPR/dCas9‐STAR system recruiting VPR activator via MS2 hairpin. (H) Activation efficiency of PFBAin‐GFP by the CRISPRa/dCas9‐STAR system. (I) Flow cytometry results pertaining to strains expressing sg0, sg2 and sg6. (J) Fold change of mean fluorescence in flow cytometry analysis. All strains were cultured in SC‐Ura medium for 48 h. Values and error bars indicate mean ± SD of three biological replicates. Asterisks denote two‐tail p value as determined by two‐sample t test, with *p ≤ 0.05, **p ≤ 0.01, and ***p ≤ 0.0001.\n\nFigure 3: Figure 3. Activation of genes under endogenous promoters by CRISPR/dCas9‐STAR. (A) Activation of the FAR gene by CRISPR/dCas9‐STAR system recruiting VPR activator via MS2 hairpin. (B) Activation efficiency of the CRISPR‐STAR system targeting FAR gene. (C) Fatty alcohol production of engineered strains with activated expression of FAR gene. Samples were taken at 72 h. Activation efficiency of the CRISPR‐STAR system targeting ERG9 (D), ACL2 (E) and EXP1 (F) gene. Values and error bars indicate mean ± SD of three biological replicates. Asterisks denote two‐tail p value as determined by two‐sample t test, with *p ≤ 0.05, **p ≤ 0.01, and ***p ≤ 0.0001.\n\nFigure 4: Figure 4. Inhibition of endogenous genes by CRISPR/dCas9‐STAR. (A) Inhibition of the PEX10 gene by CRISPR/dCas9‐STAR system recruiting MXI1 domain via PP7 hairpin. (B) Inhibition efficiency of the CRISPR‐STAR system targeting PEX10 gene. (C) Fatty alcohol production of engineered strains with suppressed expression of PEX10 gene. All strains were cultured in rich YPD medium. Samples were taken at 72 h. Inhibition efficiency of the CRISPR‐STAR system targeting YALI1_D13496g (D), YALI1_F39818g (E) and ADE2 (F) gene. Values and error bars indicate mean ± SD of three biological replicates. Asterisks denote two‐tail p value as determined by two‐sample t test, with *p ≤ 0.05, and **p ≤ 0.01.\n\nFigure 5: Figure 5. The CRISPR‐STAR mediated simultaneous gene repression and activation in Y. lipolytica. (A) Schematic diagram of establishing the synthesis pathway of fatty alcohols. (B) Schematic diagram of simultaneous activation of FAR gene and inhibition of PEX10 gene by the CRISPR‐STAR system. (C) Fold change of transcriptional level of FAR and PEX10 genes. (D) Increased fatty alcohol production caused by bidirectional regulation. FAR‐a indicates activation of FAR gene and PEX10‐i indicates interference of PEX10 gene. “+” stands for performing corresponding regulation and “−” stands for without corresponding regulation. Values and error bars indicate mean ± SD of three biological replicates. Asterisks denote two‐tail p value as determined by two‐sample t test, with *p ≤ 0.05, **p ≤ 0.01, and ***p ≤ 0.0001."
      }
    ]
  },
  {
    "id": "PMC12033372_multi",
    "image": [
      "images/PMC12033372-f1.png",
      "images/PMC12033372-f2.png",
      "images/PMC12033372-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Glucose-6-phosphate-dehydrogenase on old peroxisomes maintains self-renewal of epithelial stem cells after asymmetric cell division\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a SNAP labeling and imaging of old and young peroxisomes in synchronously dividing hMECs. Representative image and quantification of age-selective (symmetric and asymmetric) apportioning of old and young peroxisomes between daughter cells in cell division. Each data point represents a cell division with x- and y-axis showing the ratio of old/young peroxisomes in daughter cells. Data from 86 cell division pairs, collected from four independent experiments. b Schematic of knock-in strategy for inducible SNAP-PTS1 mouse (black box), and FACS isolation of basal and luminal mMECs and in vitro labeling of peroxisomal age classes for analysis of age-selective apportioning of peroxisomes in cell division. Age-selective apportioning of peroxisomes occurs in basal cells (blue) but not luminal cells (gray, right conner). Each datapoint represents a daughter cell pair during cytokinesis. Representative image of a basal mMEC is shown. Data from 31 pairs of basal cells and 24 pairs of luminal cells, collected from three independent experiments. c In vivo labeling of different age classes of peroxisomes in mammary glands of K14-Cre;SNAP-PTS1 mice by injecting SNAP substrates into mammary glands. TEB: Terminal end-bud. d Schematic of in vivo and ex vivo labeling of peroxisomal age classes in mammary glands, and of the functional assays on daughter cells inheriting old (PO) or young (PY) peroxisomes of the mother cell in basal mMEC asymmetric cell divisions (ACD). Cells that had divided were analyze for enrichment of old and young peroxisomes, revealing the PO and PY populations (gray box). e Organoid forming capacity of PO and PY daughter cells emerging from the first basal mMEC cell division in vitro. Immunofluorescent staining of an organoid originating from a PO cell shows K14 positive basal cells and K8 positive luminal cells. Data from nine biological replicates, p-value from two tailed t-test. f Analysis of branching efficiency of the organoids from (e). Organoids originating from PO cells branch with a significantly higher frequency than the organoids originating from PY cells. Data from five biological replicates, p-value from two tailed t-test. g Representative immunofluorescence images of a PO branching organoid with a bi-layer structure resembling organization of the mammary epithelium in vivo, and a PY organoid with disorganized structure. Data are presented as mean ± SD. Source data are provided as a Source Data file.\n\nFigure 2: Figure 2. a Age-selective isolation of peroxisomes and their proteomic analysis using mass spectrometry. Volcano plot of proteins differentially enriched between old and young peroxisomes. Significantly enriched proteins are marked in red (enriched with old peroxisomes) and green (enriched with young peroxisomes). b Immunofluorescent labeling of G6PD in hMECs with age-selectively labeled peroxisomes shows colocalization of G6PD with peroxisomes. G6PD is significantly enriched on old peroxisomes. Data shows 38 individual cells (unfilled circles) from three independent experiments (filled circles), p-value from one-way ANOVA test of independent experiments. c Representative immunofluorescence images show localization of G6PD (green) over-expressed in cytosol (cG6PD), in the peroxisomal matrix (pmtxG6PD) using a PTS1 targeting signal, and on the peroxisomal membrane (pmembG6PD) using a YgiM tail anchor. PMP70 immunofluorescent labeling show peroxisomes. Overexpression of G6PD on the peroxisomal membrane, but not in the peroxisomal matrix or in the cytosol, increases mammosphere formation of hMECs significantly. Data from eight independent experiments, p-value from one-way ANOVA test. d Schematic showing the G6PD activity and peroxisomal ether lipid synthesis pathway. NADPH produced by G6PD activity on the peroxisomal membrane is potentially utilized for peroxisomal ether lipid synthesis, and inhibiting AGPS can be employed as a strategy to probe the function of pmembG6PD on peroxisomal ether lipid synthesis. e Mammosphere formation by cG6PD and pmembG6PD after continuous inhibition of AGPS. AGPS inhibition reduces mammosphere formation and mitigates the boost induced by pmembG6PD. Data from five experiments, p-value from paired, two tailed t-test and one-way ANOVA test. f Organoid formation and branching efficiency of mMECs after continuous inhibition AGPS activity. Inhibiting peroxisomal ether lipid synthesis reduces organoid formation and branching efficiency of mMECs. Data from four biological replicates, p-value from paired, two tailed t-test. Data are presented as mean ± SD. Source data are provided as a Source Data file.\n\nFigure 3: Figure 3. a Schematic of in vivo labeling of different age classes of peroxisomes in skin of K14-Cre;SNAP-PTS1 mice by injecting SNAP substrates subcutaneously. Representative images show the heterogeneity of peroxisomal ages in tissue. Note the enrichment of old label in the basal cells, and in the cells forming the outer layers of skin (white arrow heads). Wheat germ agglutinin (WGA) labels the cell membrane. b Representative images and quantification of age-specifically labeled peroxisomes in basal skin cells at cytokinesis in vivo. Cells dividing perpendicular to the basement membrane allocate old peroxisomes to the daughter cell staying at the basement membrane (left). Majority of cells dividing parallel to the basement membrane apportion peroxisomes symmetrically (middle image), but some apportion peroxisomes age-selectively (right, with blue border). Graph shows old/young peroxisomes ratio between the two daughter cells, classified by position of the two daughter cells relative to the basement membrane. Data shows 42 cell division pairs, from five biological replicates, p-value from two tailed t-test of biological replicates. c Schematic of in vivo labeling of peroxisomal age classes in skin, FACS sorting strategy and the functional assays on cells enriched with old (PO) or young (PY) peroxisomes in CD49fhi, Sca1+ EpSCs. Left panels show representative FACS data. Middle panels demonstrate that PO has a higher organoid-forming capacity compared to PY. Right images show phase contrast images of organoids from PO or PY. Data from six biological replicates, p-value from paired, two tailed t-test. d Immunofluorescent staining of organoids originating from a PO or PY cells and quantification of lineage markers in these organoids. Organoids from PO have significantly higher levels of the suprabasal differentiation marker, K10, than organoids from PY. Data from five biological replicates, p-value from paired, two tailed t-test. e Organoid formation by PO and PY EpSCs after transient inhibition of G6PD. G6PD inhibition reduces organoid forming capacity of PO. Data from four biological replicates, p-value from paired, two tailed t-test. f Organoid formation of EpSCs after continuous inhibition AGPS activity. Inhibiting peroxisomal ether lipid synthesis reduces organoid formation of EpSCs. Data from five biological replicates, p-value from paired, two tailed t-test. Data are presented as mean ± SD. Source data are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC12050408_multi",
    "image": [
      "images/PMC12050408-f1.png",
      "images/PMC12050408-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Rare Variants Cause Charcot‐Marie‐Tooth Disease in Malian Families\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigrees and phenotypic characteristics of CMT families. (A) Pedigree of Family 1 with BAG3‐neuropathy. Affected individuals are represented with black/grey squares. (B) Pedigree of family 2 with BSCL2‐neuropathy showing an autosomal dominant inheritance pattern. Affected individuals are represented with a black square and circle. (C) Pedigree of Family 3 with SH3TC2‐neuropathy showing an autosomal recessive inheritance with consanguinity (double horizontal line). Capital letters at the bottom are genotype information. (D) Pedigree of Family 4 with PEX10‐neuropathy showing an autosomal recessive inheritance pattern for the neuropathy phenotype with consanguinity (horizontal double line). Numbers on top stand for ages at examination, an arrow for proband, and an asterisk for those seen in the clinic. Grey‐filled circles are individuals sharing neuropathy and BAFME8 phenotypes, and black‐filled circles and squares are those having only the BAFME8 phenotype. For all pedigrees, numbers on top stand for ages at examination, an arrow for proband, an asterisk for those seen in the clinic, and capital letters in the bottom are genotype information. (E–G) Images of patient IV.3 of Family 3 showing distal muscle atrophy in four limbs and dorsal scoliosis. (H, I) Images of patient IV.5 of Family 3 showing less severe phenotype.\n\nFigure 2: Figure 2. Genetic and three‐dimensional structures data. (A) Electropherogram showing the heterozygous nucleotide “C” to “G” change in BAG3, (B) Electropherogram showing the heterozygous nucleotide “A” to “G” change and a normal sequence in BSCL2, (C) Electropherogram showing the homozygous nucleotide “C” to “T” change and a carrier in SH3TC2, (D) Portion of BAG3 protein showing the conservation of Pro374 across a wide range of species, (E) Portion of BSCL2 protein showing the conservation of Asn88 across a wide range of species, (F) Portion of SH3TC2 protein showing the conservation of Arg1109 across a wide range of species, (G–I) Superimposed structure of wildtype (green) and mutant BAG3 (light blue) protein showing the three‐dimensional conformational changes in the mutant compared to the wildtype. (J, K) InterPro protein domain search showing the extension of the disordered region of the protein in the mutant compared to the wild type."
      }
    ]
  },
  {
    "id": "PMC12070441_multi",
    "image": [
      "images/PMC12070441-f2.png",
      "images/PMC12070441-f3.png",
      "images/PMC12070441-f4.png",
      "images/PMC12070441-f5.png",
      "images/PMC12070441-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Phospholipids and peroxisomes in ferroptosis: the therapeutic target of acupuncture regulating vascular cognitive impairment and dementia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. Ferroptosis is closely related to VICD. The pathogenic factors of VICD include abnormal glucose and lipid metabolism, hypertension, diabetes, and atherosclerosis. The above etiology of VICD can lead to metabolic abnormalities in brain cells. Chronic cerebral ischemia is the pathological basis of VICD. Long term inadequate blood flow can lead to the occurrence of cerebrovascular inflammation, damage to the blood-brain barrier, and increased iron ions, collectively resulting in the production of a large amount of ROS in the brain. The occurrence of iron death in VICD is carried out through phospholipid peroxidation under the above conditions, which depends on transition metal iron, ROS and phospholipids containing polyunsaturated fatty acid chains (PUFA-PLs). The occurrence of ferroptosis is unfortunate for VICD, which means that brain neuron cells will face disadvantages, and this may include loss of membrane integrity, disruption of membrane properties through lipid cross-linking, as well as oxidative damage to macromolecules and cellular structures caused by ROS derived from PUFA-PL.\n\nFigure 3: Figure 3. The partial target of acupuncture in inhibiting ferroptosis for VICD. The membrane protein transferrin receptor 1 (TFR1) imports Fe3+ into cells after binding to transferrin (TF). STEAP3, a six-transmembrane epithelial antigen of prostate 3, then reduces Fe3+ to Fe2+ within endosomes. Divalent metal transporter 1 (DMT1) transports Fe2+ out of the endosomes. Cytosolic ferritin, composed of ferritin heavy chain 1 (FTH1), stores most of the Fe2+, while the membrane protein ferroportin 1 (FPN1) facilitates its export from the cell. Hepcidin internalizes and degrades FPN1, thereby reducing intracellular Fe2+ transport. Excess Fe2+ can generate reactive oxygen species (ROS) through the Fenton reaction or iron-catalyzed enzyme pathways. Additionally, Fe2+ can enhance the activity of lipoxygenases (ALOXs) and accelerate the oxidation of polyunsaturated fatty acids (PUFAs), leading to ferroptosis. The X<suprm>c</suprm> system imports cystine and exports glutamate, with cystine being reduced to cysteine for the production of glutathione (GSH). GSH serves as a substrate for the synthesis of glutathione peroxidase 4 (GPX4), both of which repair cell membrane lipids. GPX4 reduces lipid hydroperoxides (L-OOH) to lipid alcohols (L-OH). Overall, iron overload, an imbalance in the antioxidant system, and the accumulation of lipid peroxides contribute to the ferroptosis observed in VCID. Acupuncture has been shown to exert regulatory effects on these key processes (indicated by green arrows).\n\nFigure 4: Figure 4. The uptake, activation, remodeling, and storage pathways of lipid metabolism in ferroptosis. Free fatty acids enter cells via diffusion or transporters like CD36 and FATPs. Monounsaturated fatty acids (MUFAs) can be synthesized de novo, starting from malonyl-CoA and acetyl-CoA, elongated and desaturated by SCD1, and activated by ACSL3, which incorporates them into phospholipids to inhibit lipid peroxidation. In contrast, polyunsaturated fatty acids (PUFAs) are taken up from the extracellular environment and activated by ACSL4. Phospholipid remodeling enzymes such as PLA2G6, LPCAT3, and AGPAT3 regulate PUFA integration, influencing membrane oxidizability. TPD52, a lipid droplet synthesis enzyme, may protect against ferroptosis by sequestering PUFAs into lipid droplets, preventing their incorporation into membrane phospholipids. FASN, fatty acid synthase; SFA, saturated fatty acid; FATPs, fatty acid transport proteins; SCD1, Stearoyl-CoA desaturase 1; ACSL3, Acyl-CoA synthetase long-chain family member 3; ACSL4, Acyl-CoA synthetase long-chain family member 4; PLA2G6, phospholipase A2 group VI; LPCAT3, lysophosphatidylcholine acyltransferase 3; AGPAT3, 1-acylglycerol-3-phosphate O-acyltransferase 3; TPD52, tumor protein D52. The asterisk “*” denotes an esterification reaction. Specifically, it highlights key enzymatic steps—such as the activation of unsaturated fatty acids into acyl-CoA forms and the reassembly of PUFAs into membrane phospholipids—where enzymatic catalysis, energy input, or molecular modifications are typically required.\n\nFigure 5: Figure 5. Peroxisome-dependent and independent initiation of ferroptotic pathways. Polyunsaturated fatty acid (PUFA), arachidonic acid/adrenic acid (AA/AdA), acyl-CoA synthetase long-chain family member 4 (ACSL4), polyunsaturated fatty acid -coenzyme A (PUFA-CoA), lysophosphatidylcholine acyltransferase 3 (LPCAT3), polyunsaturated fatty acid- membrane phospholipid (PUFA-mPL), lipoxygenase (ALOX), cytochrome P450 oxidoreductase (POR), lipid hydroperoxides (LOOH), glutathione peroxidase 4 (GPX4), endosomal sorting complexes required for transport-III (ESCRT-III), alkylglycerone phosphate synthase (AGPS), 1-O-alkyl-glycerol-3-phosphate (AGP), 1-acylglycerol3-phosphate O-acyltransferase 3 (AGPAT3), dihydroxyacetone phosphate (DHAP), fatty acyl-CoA reductase 1 (FAR1), glyceronephosphate O-acyltransferase (GNPAT), plasmanylethanolamine desaturase 1 (PEDS1).\n\nFigure 6: Figure 6. The pathway of plasmalogens and peroxisomes in ferroptosis induction. PEXs, peroxisome biogenesis factors; AGPS, alkylglycerone phosphate synthase; FAR1, fatty acyl-CoA reductase 1; AGPAT3, 1-acylglycerol-3-phosphate O-acyltransferase 3; -OOH, lipid hydroperoxides; PEDS1, plasmalogen ether desaturase 1."
      }
    ]
  },
  {
    "id": "PMC12102243_multi",
    "image": [
      "images/PMC12102243-f1.png",
      "images/PMC12102243-f2.png",
      "images/PMC12102243-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Neurofilament light chain as a biomarker to indicate early activation of cerebral disease in boys with adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. NfL was determined at each age interval and accompanied by an MRI (Loes MRI score was zero for all boys at all timepoints). N = 6 individuals. The red line indicates 10 pg/mL.\n\nFigure 2: Figure 2. a–e shows five boys with baseline plasma NfL levels and normal MRIs prior to development of cerebral disease. Timepoints shown were chosen to indicate the association of lesion development with the rise in NfL. Change from mean baseline NfL level is indicated in each graph. Some boys had a single baseline timepoint while others had multiple pre-lesional samples. The score indicates the overall Loes MRI score for the T2-weighted MRI sequences obtained. Red boxes indicate magnified areas. Blue arrows indicate areas of gadolinium contrast enhancement.\n\nFigure 3: Figure 3. Two brothers were diagnosed with cerebral ALD in a similar time frame. a The left images show the brother with arrested cerebral disease (no gadolinium enhancement on lower image). b The right images show the brother with active cerebral disease indicated by gadolinium enhancement (white arrow). Plasma NfL levels at the time of MRI are indicated."
      }
    ]
  },
  {
    "id": "PMC12111468_multi",
    "image": [
      "images/PMC12111468-f1.png",
      "images/PMC12111468-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Revisiting the Pathogenesis of X-Linked Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Motor performance of Abcd1 KO mice (black squares) compared with wild type littermates (open circles) tested with rotarod (left) or bar walking score (right). The percentages of mice falling more quickly from the rotarod or having a low score on the bar is shown from 8 to 24 months of age [176].\n\nFigure 2: Figure 2. Simplified scheme of the main mechanisms that appear to contribute to X-ALD phenotypes. (1) The primary event is VLCFA accumulation in OLs and other glial cells that leads to synthesis of VLCFA-rich myelin and toxic lipids, e.g., sphingosine-1-P (S1P). (2) Peroxisomal dysfunction affects OLs and other glial cells. (3) Axon dysfunction and variable degrees of axonal degeneration. (4) In cALD patients, demyelination, brain inflammation, and axon degeneration are triggered by the subacute activation of microglia, astrocytes, macrophages, then extensive infiltration of the brain white matter by immune cells."
      }
    ]
  },
  {
    "id": "PMC12139734_multi",
    "image": [
      "images/PMC12139734-f1.png",
      "images/PMC12139734-f2.png",
      "images/PMC12139734-f3.png",
      "images/PMC12139734-f4.png",
      "images/PMC12139734-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Engineering precision zebrafish alleles of human disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A) Flow diagram of the CPAM evaluation and zebrafish model production pipeline. B-H) Human wildtype and patient nucleotide sequence and amino acid sequence near the patient variant. This is then aligned with the zebrafish wildtype sequence and potential patient mimetic alteration. Patient change sites are denoted in red font. Exonic sequence is in uppercase, while intronic sequence is in lower case.\n\nFigure 2: Figure 2. A) As an example of guide selection, three potential PAM sites for nf1a RQ project are depicted. B) Table depicting guides tested, IDT on-target and off-target scores, along with HRMA, NGS and ICE results. Results are color coded to depict strength of result, with green being ideal, yellow being moderate, and magenta being poor. Guide names highlighted in green were used to make the zebrafish line. C) HRMA based evaluation of the guides result in altered HRMA curves (red curves) relative to uninjected (blue curves) indicating guide directed indels generated in the gDNA. D) Evaluation of guide efficiency and identified indels (in order of frequency) by NGS and ICE analysis.\n\nFigure 3: Figure 3. A) Depicts the patient mimetic and mimetic plus additional silent mutations that were used in the oligo design for all the projects. The green font depicts the wildtype sequence, and red font depicts the patient mimetic change. The blue font depicts silent alterations. The yellow, green, or blue highlight denotes the PAM sequence of the guide (G1, G2, or G3) to be used. C) Table summarizing the HDR rates of different oligos using different guides, and with additional alterations. The red border defines combination used to obtain germline transmission of the desired allele; green highlight depicts strong HDR rates, while yellow highlight depicts moderate HDR rates. D) Table comparing HDR rates determined by NGS verse ICE.\n\nFigure 4: Figure 4. A) Table depicting how many F0 founders were analyzed and the NGS derived HDR rate in pooled (n=100) 5dpf F1 embryos. Animals used to identify adult F1 are denoted with red font. Green highlight denotes founders that give >5% HDR; while yellow denotes >2% HDR. B) NGS based HDR frequency evaluation of individual oligo/RNP injected F0 5dpf embryos. C) Table comparing HDR rates from F0 tail biopsy gDNA and pooled 5dpf F1 progeny gDNA; as well as HDR rates of pooled 5dpf F1 progeny gDNA defined by ICE analysis. Green highlights denote the highest HDR rates observed and the F0 from which the desired F1 was obtained. ** denotes false positives determined by ICE analysis (have only one of the 4 desired HDR alterations but were scored as HDR positive by ICE. D) Evaluation to determine if the germline HDR rate is maintained with age or transient germline populations.\n\nFigure 5: Figure 5. A) Allele specific PCR forward primer (underlined) design for each project. B) Use of each allele specific primer set with wildtype gDNA to determine if mutant specific primer sets amplify a product off of wildtype gDNA. Two wildtype tail biopsies derived gDNA samples are used per primer set. C) Agarose gel of PCR products amplified from nf1a GR F1 heterozygous and wildtype control tail gDNA and pooled 5dpf F1 progeny gDNA from NGS HDR rate defined F0 founders. 359 bp band denotes the presence of the HDR allele. D) Agarose gel of PCR products amplified from vma21 AV F1 heterozygous and wildtype control tail gDNA and pooled 5dpf F1 progeny gDNA from NGS HDR rate defined F0 founders. 303 bp band demotes the presence of the HDR allele. E) Agarose gel of PCR products amplified from pex10 HD F1 heterozygous and wildtype control tail gDNA and pooled 5dpf F1 progeny gDNA from NGS HDR rate defined F0 founders. 234 bp band denotes the presence of the HDR allele."
      }
    ]
  },
  {
    "id": "PMC12139734_multi_2",
    "image": [
      "images/PMC12139734-f6.png",
      "images/PMC12139734-f7.png",
      "images/PMC12139734-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Engineering precision zebrafish alleles of human disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A) Example of HRM analysis of F1 adult tail biopsies from nf1a GR F0#26 (22% HDR rate in pooled F1 embryos). Different curves and associated allelic sequences are denoted by colored curves. Below are Sanger sequencing chromatograms of gDNA from F1 animals with different curves; along with the frequency of the allele in 38 F1 analyzed and the pooled F1 embryos NGS data. B) Example of HRM analysis of F1 adult tail biopsies from fkrp CY F0#16 (2.1% HDR rate in F1 pooled embryos). Different curves and associated allelic sequence is denoted by colored curves. Below are Sanger sequencing chromatograms of gDNA from F1 animals with different curves; along with the frequency of the allele in 94 F1 analyzed and the pooled F1 embryos NGS data.\n\nFigure 7: Figure 7. A) Agarose gel of PCR products using nf1a GR allele specific PCR of F1 heterozygous patient variant and heterozygous indels. 359 bp band denotes the presence of the HDR specific allele. B) Agarose gel of PCR products using vma21 AV allele specific PCR of F1 heterozygous patient variant and heterozygous indels. 303 bp band demotes the presence of the HDR specific allele. C) Agarose gel of PCR products using spop DN allele specific PCR of F1 heterozygous patient variant and heterozygous indels. 274 bp band denotes the presence of the HDR specific allele. D) Agarose gel of PCR products using pex10 HD allele specific PCR of F1 heterozygous patient variant and heterozygous indels. 234 bp band demotes the presence of the HDR specific allele. Sequence of wt, HDR allele, and indel are depicted below. Allele specific primer is denoted by underlined sequence in the HDR allele. E) Agarose gel of restriction enzyme digested spop PCR product of F1 heterozygous patient variant and heterozygous indels. 321bp band denotes the uncut product, while 273 and 48 bp bands denote the cut product. Sequence of wt, HDR allele, and indel are depicted below with the XbaI restriction enzyme site underlined in the D144N sequence.\n\nFigure 8: Figure 8. A) For NF1 R*, NF1 M992del, TP53 R175H, TP53 K120R and PKD2 L656W models, human wildtype nucleotide and amino acid sequence near the patient variants. This is then aligned with the zebrafish wildtype sequence and potential patient mimetic alteration. Patient change sites are denoted in red font. B) summary of guides used, IDT scores, HRM results, and NGS derived HDR frequencies. C) Frequency of positive F0 and the germline transmission frequency for the projects."
      }
    ]
  },
  {
    "id": "PMC12154719_multi",
    "image": [
      "images/PMC12154719-f1.png",
      "images/PMC12154719-f2.png",
      "images/PMC12154719-f3.png",
      "images/PMC12154719-f4.png",
      "images/PMC12154719-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Molecular mechanism of substrate transport by human peroxisomal ABCD3\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Size-exclusion chromatography profile of purified hABCD3 and SDS gel of peak fraction. (B) ATPase activity of ABCD3 at basal level and in presence of its substrates (phytanoyl-CoA and palmitoyl-CoA). (C) Overall topology of ABCD3. (D) Cryo-EM map of ABCD3 as homodimer in GDN detergent (dark green representing protomer A and light green representing protomer B). (E) Model of ABCD3 with color theme as shown in (D).\n\nFigure 2: Figure 2. (A) The binding affinity of phytanoyl-CoA for human ABCD3 determined using MST to be 54.9 ± 9.03 μM (n = 3) with error bar representing S.D. (B) Cryo-EM map of phytanoyl-CoA bound ABCD3. Density correspond to phytanoyl-CoA is yellow in color, dark orange color representing protomer A and light orange color representing protomer B. (C) Model of phytanoyl-CoA bound ABCD3 with color code as in (B). The density corresponding to the phytanoyl-CoA is shown in mesh. Left panel showing the view as B, middle panel rotation of left panel at 90° on y-axis. Right panel rotation of middle panel at 90° on x-axis. (D) Hydrophobicity surface view of ABCD3 around the box region shown in (C) showing the phytanoyl-CoA binding site. The lipid tail of phytanoyl-CoA outside the transmembrane helix cavity shown in upper left panel with insight of hydrophobic interaction network in lower left panel. The trimmed view of the ABCD3 substrate binding pocket with phytanoyl-CoA bound in it (upper right panel) with highlighting the interactions detail in lower right panel. Phytanoyl-CoA is colored in yellow, glycines flanking the cavity are in teal, hydrophobic residues are colored in orange, polar-uncharged residues colored in green, negatively charged residues are in pink, and positively charged amino residues are in cyan; colored by atom- oxygen (red), nitrogen (blue), and sulfur (violet).\n\nFigure 3: Figure 3. (A) Structure and dynamics of Phytanoyl-CoA 1 within the dimer cavity. Its final conformation (sticks) is shown, segmented into adenine (Turquoise), ribose-3-P (Blue), diphosphate (Red), pantothenate (Green), and cysteine (Yellow). Correspondingly colored points illustrate the spatial volume explored by the center of mass (COM) for each segment during a representative trajectory. (B) Segmental flexibility of Phytanoyl-CoA 1. The standard deviation (SD, in Å) of COM displacement quantifies the positional fluctuation for each segment (colors as in A). Larger SD values for the terminal adenine and cysteine segments highlight their greater conformational flexibility. (C) System stability assessed by Root Mean Square Deviation (RMSD) relative to the initial structure, shown for a representative trajectory. Top: Protein backbone Cα RMSD for Protomer A (dark orange) and B (light orange). Bottom: Heavy atom RMSD for Phytanoyl-CoA 1 (dark blue) and 2 (light blue). (D) Persistent substrate-protein interactions identifying key binding residues. Interaction fractions (% time) depict significant hydrogen bonds and ionic contacts between Phytanoyl-CoA 1 and residues from Protomer A and B’ (prime denotes Protomer B). Displayed interactions represent consistent contacts, maintained for ≥10% of the time across all three replicate simulations.\n\nFigure 4: Figure 4. (A) Distance between TMDs and NBDs and angles between protomers in apo state (B) Phytanoyl-CoA bound state (C) overlay of apo and phytanoyl-CoA bound states. Change is measured as distance between E82 residue of TMH 1 of ABCD3 protomers (A) in apo state (top panel) to (B) in phytanoyl-CoA bound state (top panel). (C) overly of both structure (top panel). The change of NBDs position measured as angles and distance between the V605 and R642 residues of NBDs from each protomers of ABCD3. (A) in apo state (lower panel) to (B) in phytanoyl-CoA bound state (lower panel). (C) overlay of both structure (lower panel) highlighting the rearrangement in the relative positions of V605 and R642 residues of NBDs in apo (green sphere) and phytanoyl-CoA bound (orange sphere).\n\nFigure 5: Figure 5. (A) Comparison of the transmembrane helices of apo and phytanoyl-CoA bound protomer A obtained from superimposition of the NBD region. In phytanoyl-CoA bound state, TMH 4 and 5 rotate and move inwards. (B) The rearrangement of TMH 4 and 5 in the apo state increases the distance between phytanoyl-CoA and residues (Y330, T326, of TM5 and Y357, S368 of TM6) (upper panel) from those in the phytanoyl-CoA-bound structure (lower panel). (C) Phytanoyl-CoA binding leads to a decrease in distance between phytanoyl-CoA and residues (Y330, T326, of TM5 and Y357, S368 of TM6) (lower panel) in comparison to the apo-state."
      }
    ]
  },
  {
    "id": "PMC12170509_multi",
    "image": [
      "images/PMC12170509-f1.png",
      "images/PMC12170509-f2.png",
      "images/PMC12170509-f3.png",
      "images/PMC12170509-f4.png",
      "images/PMC12170509-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Fbxo16 mediates degradation of NF-κB p65 subunit and inhibits inflammatory response in dendritic cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PDLIM2 bound to Cullin 1 and Skp1 forming a ubiquitin E3 ligase complex. (A) Expression of Cullin 1 and Cullin 7 in cytoplasmic and nuclear extracts of dendritic cells (BMDC) and fibroblasts (MEFs). The purity of the fractions of cytoplasmic and nuclear extracts was checked with anti-PKC and anti-LSD1 antibodies, respectively. NS, Non-specific band. (B) Interaction of PDLIM2 and Cullins in whole cell lysates of HEK293T cells, transfected with Flag-PDLIM2, then immunoprecipitated (IP) with anti-Flag, and immunoblotted (IB) with anti-Cullin 1, Cullin 2 or Cullin 3. (C) Densitometric analysis of the coimmunoprecipitated amount of each Cullin protein relative to the total amount of input. Shown are the mean ± SD. **P < 0.01. (D) Interaction of PDLIM2 and Skp1 in whole cell lysates of HEK293T cells, transfected with Flag-PDLIM2, then immunoprecipitated with anti-Flag, and immunoblotted with anti-Skp1. (E) Effect of Cullin 1 or Skp1 deficiency on PDLIM2-mediated p65 degradation in soluble and insoluble nuclear extracts of HEK293T cells, first transfected with control siRNA or siRNA against Cullin 1 or Skp1, then transfected with Flag-p65 without or with c-Myc-PDLIM2 and analyzed by immunoblot with anti-Flag antibody. (F) Effect of Cullin 1 or Skp1 deficiency on the interaction of PDLIM2 and p65 in HEK293T cells, first transfected with control siRNA or siRNA against Cullin 1 or Skp1 and then transfected with Flag-p65 without or with c-Myc-PDLIM2. Whole cell lysates were immunoprecipitated with anti-c-Myc and immunoblotted with anti-Flag. Data are representative of three (A-F) independent experiments.\n\nFigure 2: Figure 2. Fbxo16 is a substrate-recognizing component in the PDLIM2-containing ubiquitin E3 ligase complex. (A) Effect of deficiency of Fbxo proteins on the interaction of PDLIM2 and p65 in HEK293T cells, first transfected with control siRNA or siRNA-specific to Fbxo9, 22, 47, 48, 16, 2, 7, 10, 15, 41 or 18 and then transfected with Flag-p65 without or with c-Myc-PDLIM2. Whole cell lysates were immunoprecipitated with anti-c-Myc and immunoblotted with anti-Flag. (B) HEK293T cells first transfected without or with siRNA-specific to Fbxo2, 7, 9, 10, 15, 16, 22, 41, 47 or 48, then transfected with plasmids encoding Flag-p65 without or with c-Myc-PDLIM2. The soluble nuclear extracts were analyzed by anti-Flag antibody. (C) Real-time PCR analysis of Fbxo16 expression in immune cells, including CD4+T, CD8+T, CD19+B cells, BMDC and macrophages. (D) Effect of deficiency of Fbxo proteins on IL-6 expression in GM-CSF-BMCs transfected with control siRNA or siRNA against Fbxo2, 7, 9, 10, 15, 16, 22, 41, 47 or 48, left untreated or stimulated with LPS (0.1 ng/ml) for 5 h, and analyzed by real-time PCR. Data are representative of three (A), five (B), three (C; means ± SD) or four (D; means ± SD) independent experiments.\n\nFigure 3: Figure 3. Fbxo16 forms a CRL1 complex, binds to p65 and negatively regulates NF-κB signaling. (A) Interaction of Fbxo16 and Cullins in whole cell lysates of HEK293T cells, transfected with c-Myc-Fbxo16, then immunoprecipitated with anti-Flag, and immunoblotted with anti-Cullin 1, Cullin 2 or Cullin 3. (B) Interaction of Fbxo16 and Skp1 in whole cell lysates of HEK293T cells, transfected with c-Myc-Fbxo16, then immunoprecipitated with anti-c-Myc, and immunoblotted with anti-Skp1. (C) Interaction of Fbxo16 and p65 in whole cell lysates of HEK293T cells, transfected with a Flag-p65 or p50 along without or with c-Myc-Fbxo16, then immunoprecipitated with anti-c-Myc, and immunoblotted with anti-p65 or p50. (D) Interaction of Fbxo16 and PDLIM2 in whole cell lysates of HEK293T cells, transfected with a Flag-PDLIM2 along without or with c-Myc-Fbxo16, then immunoprecipitated with anti-c-Myc, and immunoblotted with anti-Flag. (E) Luciferase assay in MEFs transfected with ELAM−1 luciferase reporter and pRL-Null renilla constructs along with increasing amounts (wedge) of Fbxo16, then left untreated or stimulated with LPS for 5 hr. (F) Luciferase assay in HEK293T cells transfected with ELAM−1 luciferase reporter and pRL-Null renilla constructs without or with MyD88, IKKβ, TRAF6 or p65 along with increasing amounts (wedge) of Fbxo16. Data are representative of three (A, B), four (C, D) or three (E, F; means ± SD, **P<0.01) independent experiments.\n\nFigure 4: Figure 4. Fbxo16 mediates the polyubiquitination and degradation of p65 through its F-box domain. (A) Ubiquitination assay of p65 in HEK293T cells transfected with His-ubiquitin (His-Ub), p65 and increasing amounts (wedge) of Fbxo16. The purified ubiquitinated proteins were analyzed by immunoblot with anti-p65. (B) Effect of Fbxo16 on soluble and insoluble nuclear p65 in HEK293T cells transfected with Flag-p65 and increasing amounts (wedge) of c-Myc-Fbxo16, analyzed by immunoblot with ant-Flag antibody. (C) Effect of proteasome inhibitor on PDLIM2-mediated p65 degradation in soluble and insoluble nuclear extracts of HEK293T cells, transfected with Flag-p65 without or with c-Myc-Fbxo16, then left untreated or treated for 4 h with MG132 (10μM) and analyzed by immunoblot with anti-Flag antibody. (D) The structure of the wild-type Fbxo16 protein and Fbxo16 mutant lacking the F-box domain (ΔF). (E) Effect of the deletion of F-box domain on the interaction of Fbxo16 and Cullin 1 (top) or PDLIM2 (bottom) in HEK293T cells, transfected without or with c-Myc-wild-type or ΔF Fbxo16, immunoprecipitated with anti-c-Myc and immunoblotted with anti-Cullin 1 antibody (top), or transfected with Flag-PDLIM2 along with or without c-Myc-wild-type or ΔF Fbxo16, immunoprecipitated with anti-c-Myc and immunoblotted with anti-Flag antibody (bottom). (F) Ubiquitination assay of p65 in HEK293T cells cotransfected with His-ubiquitin, p65 along without or with wild-type or ΔF Fbxo16. The purified ubiquitinated proteins were analyzed by immunoblot with anti-p65. (G) Effect of the deletion of F-box domain on Fbxo16-mediated p65 degradation in soluble and insoluble nuclear extracts of HEK293T cells transfected with Flag-p65, along without or with wild-type or ΔF Fbxo16 and analyzed by immunoblot with anti-Flag antibody. (H) Luciferase assay in HEK293T cells transfected with ELAM−1 luciferase reporter, pRL-Null renilla constructs and Flag-p65 without or with wild-type or ΔF Fbxo16. Data are representative of three (A–C, E–G) or three (H; means ± SD, **P<0.01) independent experiments.\n\nFigure 5: Figure 5. Confocal microscopy of F-box-dependent p65 degradation by Fbxo16 (A) Immunofluorescence staining of HEK293T cells transfected with the Flag-p65-IRES-Venus construct without or with c-Myc-Fbxo16 plasmid. Anti-Flag staining (top); Venus expression (middle). The nucleus was stained with DAPI (bottom) (B) Immunofluorescence staining of HEK293T cells transfected with the Flag-p65-IRES-Venus construct without or with c-Myc-wild-type or ΔF Fbxo16 plasmid. Anti-Flag staining (top); Venus expression (bottom). The percentage of Flag+•Venus + cells per total Venus+ cells was shown. Data are representative of three (A, B) independent experiments."
      }
    ]
  },
  {
    "id": "PMC12170509_multi_2",
    "image": [
      "images/PMC12170509-f6.png",
      "images/PMC12170509-f7.png",
      "images/PMC12170509-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Fbxo16 mediates degradation of NF-κB p65 subunit and inhibits inflammatory response in dendritic cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. NF-κB-mediated inflammatory responses were enhanced in Fbxo16 deficient dendritic cells. (A) Expression of proinflammatory cytokine genes in GM-CSF-BMCs transfected with control siRNA or Fbxo16 against siRNA, stimulated with LPS (0.1 ng/ml) for 1, 2.5 and 5 hr, and analyzed by real-time PCR. (B) Effect of Fbxo16 deficiency on cytoplasmic and soluble and insoluble nuclear p65 in GM-CSF-BMCs transfected with control siRNA or Fbxo16 against siRNA, then stimulated with 0, 1, or 10 ng/ml of LPS for 1 h and analyzed with indicated antibodies. (C) Effect of Fbxo16 and/or PDLIM2 deficiency on IL-6 expression in GM-CSF-BMCs transfected with control siRNA or siRNA against Fbxo16 and/or PDLIM2, then stimulated with 0 (-) or 0.1 (+) ng/ml of LPS for 2 h and analyzed by real-time PCR. (D) Synergistic effect of Fbxo16 and PDLIM2 expression on soluble nuclear p65 in HEK293T cells transfected with Flag-p65, together with c-Myc-tagged Fbxo16 and/or HA-tagged PDLIM2 in the indicated combination and analyzed by immunoblot with anti-Flag antibody. (E) Effect of Fbxo16 deficiency on soluble and insoluble nuclear p65 in HEK293T cells first transfected with control siRNA or siRNA against Fbxo16, transfected with Flag-p65 without or with c-Myc-PDLIM2 and analyzed by immunoblot with anti-Flag antibody. Data are representative of four (A; means ± SD, **P<0.01), three (B), three (C; means ± SD, **P<0.01) or three (D, E) independent experiments.\n\nFigure 7: Figure 7. Fbxo16 does not promote polyubiquitination and degradation of STAT3/4. (A) Effect of Fbxo16 deficiency on the interaction of PDLIM2 and STAT3 (left) or STAT4 (right) in HEK293T cells, transfected Flag-STAT3 (left) or Flag-STAT4 (right) together without or with c-Myc-PDLIM2, then immunoprecipitated with anti-c-Myc and immunoblotted with anti-Flag (left) or anti-STAT4 (right). (B) Ubiquitination assay of STAT3/4 in 293T cells transfected with His-Ub, Flag-STAT3 (left) or Flag-STAT4 (right) without or with c-Myc Fbxo16 or PDLIM2. The purified ubiquitinated proteins by Ni-NTA beads were analyzed with anti-STAT3 (left) or anti-STAT4 (right) antibodies, respectively. (C) Effect of Fbxo16 or PDLIM2 expression on the degradation of p65 (left), STAT3 (middle) or STAT4 (right) in whole cell lysates of HEK293T cells transfected with Flag-p65 (left), STAT3 (middle) or STAT4 (right) along without or with c-Myc-Fbxo16 or PDLIM2 and analyzed with anti-Flag (left and middle) or anti-STAT4 (right) antibodies. Data are representative of three (A-C) independent experiments.\n\nFigure 8: Figure 8. Enhanced p65-mediated inflammatory responses, but normal Th1 and Th17 differentiation in Fbxo16-deficient mice. (A) Fbxo16 expression in GM-CSF-BMCs and total spleen cells from Fbxo16++/ (WT; gray bar) and Fbxo16-/- (KO; black bar) mice, analyzed by real-time PCR. (B) IL-6 (left) and IL-12 (right) production in culture supernatants of GM-CSF-BMCs from Fbxo16++/ and Fbxo16-/- mice, stimulated for 24 h with the indicated concentration of LPS and analyzed by ELISA. (C) CD4+T cells, isolated from the spleen of Fbxo16++/ and Fbxo16-/- mice, were differentiated under Th1 and Th17-skewing conditions for 4 days and then restimulated with plate-bound anti-CD3 antibody for 24 (h) IFNγ (left) and IL17 (right) production in culture supernatants were analyzed by ELISA. (D) The mechanisms by which Fbxo16 in the PDLIM2-containing CRL1 complex acts as substrate-recognizing receptor for p65 in dendritic cells, but not for STAT3/4 in CD4+T cells. Data are representative of three (A; means ± SD, **P<0.01), four (B; means ± SD, *P<0.05, **P<0.01) or three (C; N.S., not significant) independent experiments."
      }
    ]
  },
  {
    "id": "PMC12219479_multi",
    "image": [
      "images/PMC12219479-f1.png",
      "images/PMC12219479-f2.png",
      "images/PMC12219479-f3.png",
      "images/PMC12219479-f4.png",
      "images/PMC12219479-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"FAF2 is a bifunctional regulator of peroxisomal homeostasis and saturated lipid responses\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Experimental design of the genome-wide CRISPR-Cas9 KO viability screen. Cells were treated with BSA or 500 μM PA for 14 days to identify genetic KOs that sensitize or protect cells from PA-induced toxicity (P < 0.05). (B) Correlation plot showing the reproducibility of screen hits among replicates 1 and 2 of the CRISPR KO viability screen treated with BSA or 500 μM PA. (C) Volcano plot of screen hits in epithelial cells. All genes were plotted for their Log2FC enrichment in PA versus BSA conditions and significance level [−Log10(P)]. (D) GSEA of PA screen hits showing select KEGG pathways that are most significantly enriched or depleted in epithelial cells. FDR < 25%. NES, normalized enrichment scores. (E) Enrichment analysis of GO terms comparing significant hits from PA screens in epithelial cells or K562 leukemia cells identifies unique lipotoxicity modulators between cell types. The clustered network plot was generated using clusterProfiler with P-adjusted value cutoff adjP < 0.25. Correction for multiple testing was performed using the Benjamini-Hochberg method. The gene count of a node is the number of genes within each GO term.\n\nFigure 2: Figure 2. (A) GSEA of gene KOs that enrich or deplete in PA conditions shows high enrichment of peroxisomal processes. GSEA NES are displayed for differentially enriched sets of guides; gene sets include KEGG, GOBP, and REACTOME pathway entries. The size of the data points corresponds to the NES. (B) Top-ranking enriched guides that contributed to the KEGG peroxisomal gene set are significantly KO-protective in epithelial cells (black) but not K562 leukemia cells (gray). (C) Peroxisomal genes are organized by their functional process with red indicating genes that are KO protective and blue indicating genes that are KO sensitizing. Genes with a black outline indicate P < 0.05 in the PA screen. (D) FAF2 and ether lipid synthesis enzymes lie at the intersection of lipid and peroxisomal biology. Genes are plotted by a peroxisomal score (x axis) and enrichment in the PA screen (y axis). Peroxisomal scores were calculated as a correlation with peroxisomal biogenesis factors, i.e., the average Pearson correlation score of each gene versus PEX genes (DepMAP CRISPR and Chronos). (E) Log2 enrichment (y axis) of all genes that were significantly enriched in the PA screen plotted against enrichment in cellular peroxisomal IP fractions (x axis). Multiple unpaired t tests with two-stage step up (Benjamini correction FDR = 1%) was calculated for peroxisomal enriched samples compared to control IP. Ether lipid synthesis enzymes and FAF2 are enriched in both datasets. (F) Loss of peroxisomal ether lipid synthesis enzymes or FAF2 protects cells from PA-induced toxicity over a 5-day growth period. Cells were treated with BSA or 125 μM PA for 5 days and measured for cell death using PI dye. **P < 0.01; ****P < 0.0001, ordinary two-way ANOVA with Tukey’s multiple comparisons test with a single pooled variance.\n\nFigure 3: Figure 3. (A) Volcano plots of Log2FC (x axis) plotted against −Log10(adjP) significance (y axis) of normalized proteins in FAF2 KO, AGPS KO, and GNPAT KO cells compared to WT cells. (B) Hierarchical clustering of proteomics revealed three distinct clusters of proteins commonly changed between all KO cell lines. Log2FC was calculated for normalized protein intensity values of KO samples versus the average of WT cells, with proteins increased in KO samples (in red) or decreased (in blue). (C) Immunofluorescence imaging of peroxisomal proteins, AGPS, ABCD3, and CAT in WT and FAF2 KO cells. **P < 0.01; ***P < 0.001, ordinary two-way ANOVA with Šídák’s multiple comparisons test. Scale bar, 50 μm. (D) Liver-specific depletion of FAF2 was achieved with an AAV8-TBG–driven CRE recombinase delivered to FAF2-floxed mice. Controls were injected with an equal volume of PBS. n = 3 per condition. RO, retro-orbital. (E) Protein was collected from mouse liver for Western blot, and the intensity was quantified. Multiple unpaired t test, no correction. *P < 0.05; **P < 0.01. (F) A total of 84 proteins with significantly altered abundances in all three KO cell lines were identified. (G) DAVID GO functional clustering highlights overrepresented processes that are commonly enriched or depleted across all three KO cell lines. We conducted functional enrichment of biological processes of proteins belonging to the clusters identified in (B). Adjusted Benjamini values [−Log10(adjP)] are reported for discovered processes. (H) The mean difference between experimental groups and WT was calculated to determine proteins that are changed in the KO cell lines compared to WT. (I) Selected commonly altered proteins in KO cell lines. Significantly increased proteins are shown in red, whereas significantly decreased proteins are shown in blue [size indicates −Log10(adjP)].\n\nFigure 4: Figure 4. (A) Schematic representing essential genes in the ether lipid synthesis pathway. (B) Volcano plots showing Log2FC of normalized lipid intensities in peroxisomal KO cells show a decrease in plasmenyl lipid species compared to WT cells treated with PA. Dotted line shows cutoff for lipid fold changes that are significant at adjP < 0.05. PC, phosphatidylcholine; PS, phosphatidylserine; PA, phosphatidic acid; LPC, lysophosphatidylcholine; LPE, lysophosphatidylethanolamine; PE, phosphatidylethanolamine; TG, triacylglycerol; DG, diacylglycerol; Plasmenyl-PC, plasmenyl-phosphatidylcholine; Plasmenyl-PE, plasmenyl-phosphatidylethanolamine. (C) Plasmenyl-PEs and PCs are globally down-regulated in PA-treated FAF2 and peroxisomal KO cells compared to WT cells. (D) Heatmap of various lipid species’ Log2FC values across genotypes showing a decrease in ether lipid species in peroxisomal KO cells, which is reversible with ether lipid treatment, but not ester lipid. Cells were treated with PA+DMSO, PA+ether lipid (EL) intermediate (1-O-hexadecyl-sn-glycerol), or PA+ester lipid (ES) (dl-α-palmitin) as a control. (E) Supplementation of DMSO/EL/ES in addition to BSA or PA treatment shows that increased ether lipid concentration further increases PA toxicity. ****P < 0.0001, ordinary two-way ANOVA with Tukey’s multiple comparisons test. n.s., not significant.\n\nFigure 5: Figure 5. (A) Schematic of the FAF2/UBXD8 hairpin-anchored protein and FAF2 domain deletion constructs. aa, amino acid. (B) Western blot of FAF2 in WT or FAF2 KO cells transduced with full or domain-deleted (ΔUBX, ΔUAS, or ΔUBA domain) myc-tagged FAF2 constructs. (C) Western blots of peroxisomal proteins AGPS, GNPAT, and PEX10 in WT, KO, and KO cells with reexpressed full or domain-deleted FAF2 constructs (ΔUBX, ΔUAS, or ΔUBA domain) show that UBX and UAS domains are necessary to restore peroxisomal protein abundance. (D) (Top) Immunofluorescence images (60X) show that CAT punctae and AGPS protein abundance are dependent on the FAF2 UBX and UAS domains. Scale bar, 50 μm. (Bottom) CAT localization was quantified by training the dataset with the Harmony high-content imaging software on WT and FAF2 KO phenotypes. Cells in each sample were then assigned to either a WT or FAF2 KO phenotype, and the percentage of results is displayed. N = 3 biological replicates per genotype, quantification is of one representative experiment. (E) PA-induced toxicity is dependent on the UBX and UAS domains of FAF2. Cell death was quantified by the percentage of PI positive cells. ****P < 0.0001, ordinary two-way ANOVA with Tukey’s multiple comparisons test."
      }
    ]
  },
  {
    "id": "PMC12248560_multi",
    "image": [
      "images/PMC12248560-f1.png",
      "images/PMC12248560-f2.png",
      "images/PMC12248560-f3.png",
      "images/PMC12248560-f4.png",
      "images/PMC12248560-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Alterations in Prostate Cancer: Metabolic Shifts and Clinical Relevance\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Differential expression of peroxisome-related genes in primary prostate adenocarcinoma compared to normal tissue. Volcano plots display differential gene expression between primary prostate adenocarcinoma (n = 497) and normal prostate tissue (n = 52): genes encoding proteins involved in (A) peroxisome homeostasis, (B) peroxisomal lipid metabolism, and (C) peroxisomal redox metabolism. Only genes with statistically significant changes in expression (adjusted p-value < 0.05; −Log10 adjusted p-value > 1.3; indicated by a dotted horizontal line) are labeled. Data were obtained from The Cancer Genome Atlas Program (TCGA) mRNA expression profiles of primary prostate cancer and normal tissue, accessed via the University of Alabama at Birmingham Cancer Data Analysis portal (UALCAN; https://ualcan.path.uab.edu/; accessed on 12 March 2025).\n\nFigure 2: Figure 2. Peroxisomal involvement in ether lipid synthesis. The pathway initiates in peroxisomes, where glycerone-3-phosphate O-acyltransferase (GNPAT) catalyzes the formation of 1-acyl-dihydroxyacetone-3-phosphate (1-acyl-DHAP) from DHAP and acyl-CoA. 1-alkyl-glycerone-3-phosphate synthase (AGPS) then replaces the acyl moiety with a fatty alcohol, produced by fatty acyl-CoA reductase (FAR), to form the ether bond in 1-O-alkyl-DHAP. This intermediate is subsequently transferred to the ER for further processing into ether lipids. Although peroxisomal membrane protein 4 (PXMP4) is predicted to act upstream of, or within, the ether lipid metabolic process, its exact function remains unclear. Structural differences at the sn-1 position between plasmanyl and plasmenyl ether lipids are highlighted. Downregulation in PCa is represented by a red arrow pointing downward.\n\nFigure 3: Figure 3. Schematic representation of the peroxisomal β-oxidation machinery. The diagram depicts the key transporters, enzymes, and metabolic steps involved in the peroxisomal β-oxidation pathway. Upregulation and downregulation in PCa are represented by red upward and downward arrows, respectively. Notable components include ATP binding cassette subfamily D (ABCD), peroxisomal 3-ketoacyl-CoA thiolase (ACAA1), acyl-CoA oxidase (ACOX), acyl-CoA thioesterase (ACOT), calcium/calmodulin-dependent kinase II (CaMKII), carnitine acetyltransferase (CRAT), carnitine octanoyltransferase (CROT), hydroxysteroid 17-beta dehydrogenase 4 (HSD17B4), enoyl-CoA hydratase and 3-hydroxyacyl CoA dehydrogenase (EHHADH), and sterol carrier protein x (SCPx).\n\nFigure 4: Figure 4. Auxiliary enzymes involved in peroxisomal β-oxidation. This schematic illustrates the chemical reactions catalyzed by (A) α-methylacyl coenzyme A racemase (AMACR), (B) 2,4-dienoyl CoA reductase 2 (DECR2), (C) 2-enoyl-CoA isomerase (ECI2), and (D) Δ3,5,Δ2,4-enoyl-CoA isomerase (ECH1) in the peroxisomal β-oxidation pathway. AMACR is essential for the β-oxidation of 2-methyl-branched-chain fatty acids, whereas DECR2, ECI2, and ECH1 participate in the β-oxidation of unsaturated fatty acids. Red upward arrows represent upregulation.\n\nFigure 5: Figure 5. Schematic overview of the enzymatic steps involved in the peroxisomal α-oxidation of phytanic acid. Key enzymes include ATP-binding cassette subfamily D member 3 (ABCD3), α-methylacyl coenzyme A racemase (AMACR), 2-hydroxyacyl-CoA lyase 1 (HACL1), peroxisomal trans-2-enoyl-CoA reductase (PECR), and phytanoyl-CoA 2-hydroxylase (PHYH). Upregulation and downregulation in PCa are indicated by red upward and downward arrows, respectively."
      }
    ]
  },
  {
    "id": "PMC12263615_multi",
    "image": [
      "images/PMC12263615-f1.png",
      "images/PMC12263615-f2.png",
      "images/PMC12263615-f3.png",
      "images/PMC12263615-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The neurological pathology of peroxisomal ACBD5 deficiency – lessons from patients and mouse models\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Overview of peroxisomal very-long-chain fatty acid (VLCFA) β-oxidation. Long chain fatty acid- CoA ligase (ACSL1) activates VLCFAs generating VLC-acyl-CoA. ACBD5 can capture VLC-acyl-CoA via its acyl-CoA binding domain and hands it over to the peroxisomal ABC transporters for VLCFAs (e.g., ABCD1 and ABCD2). VLCFAs are then imported into the peroxisomal matrix and degraded by the peroxisomal β- oxidation pathway in four consecutive steps: (i) dehydrogenation catalyzed by acyl-CoA oxidase (ACOX), (ii) hydration and (iii) second dehydrogenation mediated by L-bifunctional protein (L-BP) with enoyl-CoA hydratase and 3-hydroxyacyl-CoA dehydrogenase activity, and (iv) thiolytic cleavage by 3-ketothiolase. The chain-shortened acyl-CoAs can be routed to mitochondria for complete degradation via the mitochondrial β-oxidation pathway or used for the synthesis of omega-3 polyunsaturated fatty acids (PUFAs) such as docosahexaenoic acid (DHA). (B) ACBD5 domain structure. Known mutations are indicated. FFAT, two phenylalanines (FF) in an acidic tract (adapted from Schrader et al., 2020). BAcPrec, bile acid precursors; BC, branched-chain; DCA, dicarboxylic acid; FA, fatty acid; LC, long-chain, MUFA, monounsaturated fatty acid; SFA, saturated fatty acid; VLC, very-long-chain.\n\nFigure 2: Figure 2. Overview of ACBD5 cellular functions. The FFAT motif of peroxisomal ACBD5 interacts with the major sperm protein (MSP) domain of ER-resident VAP to mediate peroxisome (PO)-ER membrane contacts. The PO-ER membrane contacts have been implicated in peroxisome motility and positioning, the transfer of ether lipid/plasmalogen precursors for further synthesis in the ER, and the transfer of membrane lipids for peroxisome membrane expansion and proliferation. ACBD5 possesses an acyl-CoA binding (ACB) domain which can capture very-long-chain acyl CoA (VLCFA) for peroxisomal β-oxidation (adapted from Kors et al., 2022b).\n\nFigure 3: Figure 3. Peroxisomal metabolic interaction with the ER. The ether lipid synthesis pathway (shown in magenta) is initiated in peroxisomes by acylation of dihydroxyacetone phosphate (DHAP). In/at peroxisomes, 1-acyl-DHAP is converted stepwise to 1-alkyl-DHAP and 1-alkyl-2-hydroxy-glycerophosphate (GPA), which must be transferred to the ER for completion of the pathway. At the ER, GPA is supplied with an acyl-chain at the sn2-position and a phosphatidylethanolamine (PE) or phosphatidylcholine (PC) head group to yield ether phospholipids. Alternatively, the ether lipids can receive a second acyl group at sn3 to be stored in lipid droplets. Consequently, a disruption of the pathway might lead to GPA accumulation, which has not yet been experimentally analyzed. Peroxisomal β-oxidation is required for the synthesis of n3-polyunsaturated fatty acids like DHA (pathway in green). At the ER, α-linolenic acid is elongated and desaturated to tetracosahexaenoic acid (C24:6n-3), which must be delivered to peroxisomes to be shortened to DHA (C22:6n3) in one single round of β-oxidation. Loss of the ACBD5-mediated tethering complex could presumably lead to local enrichment of C24:6n3 at the ER to be further elongated and desaturated by the ER fatty acid elongation system. This could lead to the accumulation of VLC-PUFA to be finally incorporated into phospholipids or triglycerides (adapted from Darwisch et al., 2020). For details see text. FA, fatty acid; PUFA, polyunsaturated fatty acid; UCL, ultra-long-chain.\n\nFigure 4: Figure 4. Graph depicting variability of the earliest onset of symptoms in patients. Note that cerebellar and visual dysfunction commonly occur as first signs for an ACBD5-deficiency. “Extrapyramidal” excludes motor dysfunctions, which can be related to a cerebellar degeneration."
      }
    ]
  },
  {
    "id": "PMC12264594_multi",
    "image": [
      "images/PMC12264594-f1.png",
      "images/PMC12264594-f2.png",
      "images/PMC12264594-f3.png",
      "images/PMC12264594-f4.png",
      "images/PMC12264594-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Identifying and characterizing a missing peroxin—PEX8—in Arabidopsis thaliana\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Arabidopsis PEX8 is structurally similar to S. cerevisiae Pex8. A) AlphaFold2-predicted structure of At PEX8 (At1g73970) colored by pLDTT, an indicator of prediction confidence, shows a solenoid of repeated helix-turn-helix motifs similar to Huntingtin, EF3, a-PP2A, TOR1 (HEAT) repeats. B) AlphaFold2-predicted structures of Sc Pex8 (blue), At PEX8 (green), and their alignment. Predicted peroxisomal targeting signals (PTS1 and 2) are in magenta with consensus residues displayed as balls and sticks. C) Maximum-likelihood reconstruction of phylogenetic relationships of apparent PEX8 orthologs across the plant kingdom constructed using Molecular Evolutionary Genetic Analysis and derived from the sequence alignment in Supplementary Fig. S2. Numbers at nodes indicate bootstrap support for the unrooted tree, and the scale bar indicates the number of amino acid substitutions per site. D) Structural alignment of predicted PEX8 structures colored as in C from species marked with asterisks in C. The PTS1 and 2 are displayed as magenta spheres. E) AlphaFold3-predicted structures and interactions of At PEX8 (space-filling) and At PEX5 (ribbon, colored by pLDTT). F) The AlphaFold3-predicted At PEX8 structure colored by amino acid conservation (Glaser et al. 2003; Yariv et al. 2023) using the multiple sequence alignment in Supplementary Fig. S2 and the phylogenetic tree in C. This structure was aligned to the At PEX8-At PEX5 interaction structure in E to display predicted interactions with At PEX5 (ribbon, orange). G) Predicted At PEX5 (ribbon) interaction with At PEX8 from E colored by hydrophobicity (space-filling). The left image zooms in on hydrophobic pockets (ovals) on the concave surface of PEX8, where α-helices in the PEX5 N-terminal region are predicted to interact.\n\nFigure 2: Figure 2. PEX8 is essential in Arabidopsis thaliana. A) PEX8 gene diagram showing positions of a T-DNA insertion (pex8-1), CRISPR/Cas9-generated mutations (e.g. pex8-04), and an artificial miRNA (pex8-amiR) target site. B–D) Two siliques (columns) from 3 individual plants (rows) were cleared from wild type (Wt) (B), PEX8/pex8-1 (C), and PEX8/pex8-04 (D) plants. pex8-1/PEX8 and pex8-04/PEX8 siliques contain shriveled seeds (teal asterisks) and gaps (gray asterisks) where seeds appear to be missing. Images were digitally extracted for comparison. E) pex8-01 and pex8-04 siliques have significantly fewer seeds than wild type. The mean number of seeds (filled and shrunken) in the 6 imaged siliques for each genotype (dots) is shown. Error bars indicate standard deviations of the means. Letters are assigned groups from the Tukey post-hoc test following one-way ANOVA across genotypes. Lack of shared letters indicates a significant difference between means (P < 0.05). F, G) Chi-square tests on the number of shrunken seeds and seedling genotypes reject the hypotheses that the homozygous pex8 mutants are embryo lethal (P < 0.05), suggesting that the mutations affect gametogenesis in addition to embryogenesis.\n\nFigure 3: Figure 3. An artificial miRNA directed to PEX8 (pex8-amiR) impairs β-oxidation. A, B) Growth assays for responsiveness to the auxin precursor, indole-3-butyric acid (IBA), and dependence on exogenous sucrose for elongation. A shows hypocotyl lengths of 6-day-old seedlings grown in the dark for 4 days, and B shows root lengths of 8-day-old, light-grown seedlings. Individual seedlings (dots) from 3 biological replicates are shown in 3 shades of gray, green, or purple; the mean of the three biological replicates is represented by a horizontal line. Letters are assigned groups from the Tukey post-hoc test following one-way ANOVA comparing means of each biological replicate (diamonds) across genotypes within each treatment. Lack of shared letters indicates a significant difference between means (P < 0.05). C) Thin-layer chromatography plate of lipids extracted from seedlings of indicated genotypes. Relative TAG levels normalized to pex14-1 at day 3 are indicated below the image. D) Quantification of relative triacylglycerol (TAG) levels from 3 biological replicates (dots), including the one shown in C and 2 shown in Supplementary Fig. S5. Error bars indicate standard deviations of the means, and letters are assigned groups from Tukey post-hoc test following one-way ANOVA across genotypes for each time point. Lack of shared letters indicates a significant difference between means (P < 0.05).\n\nFigure 4: Figure 4. Oleosin is elevated and peroxisomal PTS2 processing is impaired in seedlings expressing an artificial miRNA directed to PEX8 (pex8-amiR). A, C) Representative immunoblots of proteins extracted from 6-day-old seedlings grown in the dark for 4 days (A) or 8-day-old, light-grown seedlings (C). HSC70 is a loading control. B) Quantification of OLE1 levels relative to wild type (Wt) from 2 (for 7A3) or 3 biological replicate immunoblots (Supplementary Fig. S6, A to C). A log10 transformation of the OLE1 levels was performed to improve normality of the data distribution for statistical analysis. D) Percent of uncleaved, precursor PTS2 protein (PMDH or thiolase) versus total PTS2 protein level quantified from 2 (for 7A3) or 3 biological replicate immunoblots (Supplementary Fig. S6). In B and D, error bars indicate standard deviations of the means (in cases with 3 biological replicates), and letters are assigned groups from the Tukey post-hoc test following one-way ANOVA across genotypes for each protein. Lack of shared letters indicates a significant difference between means (P < 0.05).\n\nFigure 5: Figure 5. An artificial miRNA directed to PEX8 (pex8-amiR) impairs PTS1 protein import. A, B) Confocal images (5-µm maximum-intensity z-projections) of cotyledon epidermal cells from 3.5-day-old wild-type (A) and T3 pex8-amiR (B) seedlings expressing mRuby3-PTS1 (magenta) and mNeonGreen-mPTSPEX26 (green) (Wright and Bartel 2020). mPTS is the C-terminal region of PEX26 that includes a membrane peroxisomal targeting signal. C, D) Relative fluorescence intensity across the yellow arrows in A and B, which each span across 2 peroxisomes and 2 cell boundaries."
      }
    ]
  },
  {
    "id": "PMC12311911_multi",
    "image": [
      "images/PMC12311911-f1.png",
      "images/PMC12311911-f2.png",
      "images/PMC12311911-f3.png",
      "images/PMC12311911-f4.png",
      "images/PMC12311911-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Whole organism and tissue-specific analysis of pexophagy in Drosophila\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generation of the pexo-QC Drosophila melanogaster for in vivo detection of pexophagy and peroxisomal abundance. (A) Diagram of the cassette used for expression of an EGFP-mCherry-SKL fusion protein (pexo-QC) to create the pexo-QC Drosophila (elements not to scale). This includes a mini-white gene, upstream activating sequence (UAS), a D. melanogaster Kozak sequence (Dm-Kozak), the EGFP-mCherry-SKL coding sequence, an SV40 polyadenylation sequence, an attB site for site-directed insertion and an ampicillin resistance gene (AmpR). At neutral pH, peroxisomes display both GFP and Cherry fluorescence, whereas only Cherry fluorescence is retained at the acidic pH of the lysosome (pexolysosomes, magenta). (B) Bright field images of w1118 flies and tub-Gal4>UAS-pexo-QC flies (9–12 days old), indicating no observable phenotypical changes or gross morphological abnormalities in the pexo-QC Drosophila model. (C) High-resolution Airyscan live images of L3 larval epidermis comparing EGFP fluorescence signal (green) of pexo-QC with exogenous expression of peroxisomal membrane protein PMP34-Cer (Tub-PMP34-Cerulean, shown in magenta) representative of three independent experiments, with at least three animals per condition in each experiment. Scale bar: 20 μm. (D) Confocal live imaging analysis of pexo-QC larval epidermal cells costained with LysoTracker to identify lysosomes (blue). Representative of three independent experiments, with at least three animals per condition in each experiment: >LysoTracker(+), mCherry(−) puncta; filled arrowhead, LysoTracker(+)/mCherry(+) puncta. Scale bar: 10 μm. (E) Representative confocal images of pexo-QC larval epidermal cells upon expression of an Atg5-RNAi transgene (Atg5RNAi) to inhibit autophagy or exposure to the iron chelator deferiprone (DFP, 65 µM) to induce pexophagy. Scale bar: 20 μm. Also shown is a pexophagy mask, automatically generated from the mCherry/GFP ratio using the Fiji macro previously reported [23]. (F) The graph shows the number of pexolysosomes per cell for each condition. The mean and s.d. of three colour-coded independent experiments are shown; one-way ANOVA with Dunnett’s multiple comparison test for three colour-coded independent experiments with a minimum of three animals per condition in each experiment. *p < 0.05. Genotypes analysed were w1118; UAS-pexo-QC/+; tub-Gal4/tub-PMP34-Cer (C), w1118; UAS-pexo-QC/+; tub-Gal4/+ (D) and w1118; UAS-pexo-QC/+; tub-Gal4/+, w1118; UAS-pexo-QC/UAS-Atg5RNAi; tub-Gal4/+ (E).\n\nFigure 2: Figure 2. Light sheet microscopy reveals tissue-specific distribution of pexophagy in intact Drosophila larvae and pre-pupae. (A) Schematic representation of Drosophila embryo, larval development and early pupariation stage (white pre-pupa). (B',B'') Light sheet fluorescence microscopy (LSFM) multiview images of fixed pexo-QC L3 larva (tub>pexo QC), ventral view (B') and dorsal view (B''). (C–F) Enlarged insets of the specimen shown in (B') and (B''). Z-thickness and image contrast settings were adjusted to highlight the differential distribution of peroxisomes and pexolysosomes in the respective tissues. (C) Pexophagy in the ventral nerve cord (VNC) with heterogeneous pexophagy levels. (D) Enrichment of pexolysosomes in a portion of the larval midgut (mg). (E) Enrichment of pexolysosomes in the larval anal plates (ap). Insets shown in (D) and (E) were rotated by −45° and −90°, respectively, for improved visualization and clarity. (F) Peroxisomal enrichment in larval oenocyte (oe) clusters. Asterisks indicate two individual oenocyte clusters. Salivary glands (sg); nerves (n). (G',G'') LSFM multiview images of white pexo-QC pre-pupae (tub>pexo QC), ventral view (G') and dorsal view (G''). Optical lobes (OL); salivary glands (sg); larval anal plates (L. ap); larval spiracles (L. s). The genotype analysed was w1118; UAS-pexo-QC/+; tub-Gal4/+. Scale Bar 500 μm. Single channel images of (B',B'') and (G',G'') are shown in electronic supplementary material, figures S3 and S4, respectively.\n\nFigure 3: Figure 3. Drosophila oenocytes are enriched with peroxisomes but show low levels of pexophagy. (A) A representative Z-stack maximum intensity projection image acquired from a dorsolateral (DL) view of pexo-QC L3 larvae (tub > pexo QC) using a light sheet microscope reveals seven identifiable peroxisome-rich clusters (white asterisks, A1–A7) that based on their localization and morphology, can be classified as oenocytes. Scale bar: 500 μm. (B) Representative confocal images comparing pexophagy levels between oenocytes and the surrounding epidermis in living pexo-QC larvae using the same driver (tub-Gal4). Images were acquired using a 3i confocal microscope with a 63× NA 1.4 objective lens. Scale bar: 20 μm. (C) Schematic representation of a cross section of the larval skin in Drosophila melanogaster, showing the relative positions of epidermal cells, rich in pexolysosomes (shown in magenta) and oenocytes that have few pexolysosomes. Genotype analysed was w1118; UAS-pexo-QC /+; tub-Gal4/+. (D–F) Graphs show the number of pexolysosomes and peroxisomes per cell as well as their respective ratios. At least 30 cells from a minimum of three animals were analysed per condition in each of the three independent experiments. The mean and s.d. of three colour-coded independent experiments are indicated. Statistical significance was determined by unpaired t‐test; ***p < 0.001, ****p < 0.0001.\n\nFigure 4: Figure 4. Visualization of neuronal and glial pexophagy (in vivo) in the nervous system of Drosophila larvae. (A) The imaging set-up utilized to explore in vivo pexophagy in the nervous system of pexo-QC L3 larvae using a 3i spinning disc confocal microscope is depicted schematically. Top: position of larvae immobilized in 10% chloroform halocarbon oil. Bottom: ventral view of the sample’s central and peripheral neural systems, ventral nerve cord (VNC) and nerves (N), respectively. A: anterior; P: posterior; D: dorsal; V: ventral; CB: central brain; OL: optical lobes. (B) Table displaying the different neural drivers employed in the study to analyse pexophagy in the pexo-QC larvae’s nervous system: elav-Gal4, a pan-neuronal, ok6-Gal4, a motor neuronal and repo-Gal4, a pan-glial driver. (C) Representative maximum intensity projection images of confocal Z-stacks of the VNC of living pexo-QC larvae acquired using the imaging set-up described in (A). Images were acquired using a 10× NA 0.3 objective. Scale bar: 50 μm. (D) Higher magnification images of maximum projection images of confocal Z-stacks of the VNC of live pexo-QC larvae using a 63× NA 1.4 oil immersion objective. Scale bar: 10 μm. (E) Representative confocal maximum intensity projection images of confocal Z-stacks of nerves in live pexo-QC larvae using distinct neural drivers. Left. in vivo pexophagy in motor neurons (ok6-Gal4). Right. in vivo pexophagy in wrapping glial cells (repo-Gal4). Scale bar: 20 μm. Genotypes analysed were w1118; UAS-pexo-QC/+; elav-Gal4/+ (neurons), w1118; UAS-pexo-QC/ok6-Gal4; +/+ (motor neurons), w1118; UAS-pexo-QC/+; repo-Gal4/+ (glial cells).\n\nFigure 5: Figure 5. Pexophagy (ex vivo) in neuronal and glial cells in the adult central nervous system of pexo-QC flies. Representative confocal images of live pexo-QC adult brains from 9−12 day old flies, using distinct neural drivers (3i spinning disc confocal microscope, 63× NA 1.4 objective). (A) Neuronal pexophagy in the optical lobe of ex vivo Drosophila pexo-QC adult brain (elav > pexo QC). (B) Ex vivo pexophagy in the motor neurons of the suboesophageal zone of Drosophila pexo-QC adult brain (ok6 > pexo QC). (C) Glial pexophagy in the optical lobe of ex vivo Drosophila pexo-QC adult brain (repo > pexo QC). Genotypes analysed were w1118; UAS-pexo-QC/+; elav-Gal4/+ (neurons) (A), w1118; UAS-pexo-QC/ok6-Gal4; +/+ (motor neurons) (B), w1118; UAS-pexo-QC/+; repo-Gal4/+ (glial cells) (C). Scale bar: 20 μm."
      }
    ]
  },
  {
    "id": "PMC12359231_multi",
    "image": [
      "images/PMC12359231-f1.png",
      "images/PMC12359231-f2.png",
      "images/PMC12359231-f3.png",
      "images/PMC12359231-f4.png",
      "images/PMC12359231-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Zinc oxide nanoparticles disrupt peroxisome-endoplasmic reticulum contacts and increase very-long-chain fatty acid content\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Dietary ZnO NPs induce hepatic lipid accumulation, alter VLCFA profile, and reduce peroxisomal β-oxidation. A, representative image of liver histochemistry (Oil Red O staining). Scale bar, 1 mm or 0.5 mm. On the right is a partially enlarged view. B, analysis of biochemical indicators, TG, T-CHO levels in each yellow catfish group. C, analysis of liver fatty acid (C ≥ 20) contents in each yellow catfish group. D, analysis of liver total β-oxidation and peroxisomal β-oxidation in each yellow catfish group. E, relative liver mRNA level of peroxisomal β-oxidation-related gene in each yellow catfish group. F, representative ultrastructure (Transmission Electron Microscope, TEM) images of peroxisomes. black outlines indicate peroxisome and ER. On the right is a partially enlarged view. scale bar, 1 um. Arrows indicate the peroxisomes associated with the ER. Group of control Po-ER attachment was 10.37 nm. Group of ZnO NPs was 91.21 nm. It is judged to be in attachment within 15 nm. N, nucleus; M, mitochondria; Po, peroxisomes; ER, endoplasmic reticulum. G, dot plot of Po-ER contact distances (n = 90, mean ± SD, 30 peroxisomes/liver; 3 fishes/group.) and quantitative analysis (n = 3, mean ± SD, independent biological replicates) of the mean fraction of Po associated with ER after ZnO NPs treatment; The line indicates the median distance between these organelles (Control: 26.45 nm; ZnO NP: 45.80 nm). H, analysis of biochemical indicators, hepatic Zn, H2O2, CAT, T-AOC and SOD levels in each yellow catfish group. Data are expressed as mean ± SD (n = 3, independent biological replicates). p value was calculated by Student’s t tests. Asterisks (∗) indicate significant differences between the two groups. ∗(p < 0.05), ∗∗(p < 0.01), ∗∗∗(p < 0.001).\n\nFigure 2: Figure 2. Po-ER contacts and peroxisomal β-oxidation are mediated by ACBD5. A, (a, b) representative ultrastructure (TEM) images of peroxisomes. Black outlines indicate peroxisome and ER Seale bar 0.9 um. Red arrows and circles indicate Po contacted with ER. (c, d) dot plot of Po-ER contact distances (n = 90, mean ± SD, 30 peroxisomes/liver; 3 mouse/group.) and quantitative analysis (n = 3, mean ± SD, independent biological replicates) of the mean fraction of Po associated with ER after ZnO NPs treatment; The line indicates the median distance between these organelles (Control: 23.88 nm; ZnO NP: 30.31 nm). B, analysis of hepatocytes total β-oxidation and peroxisomal β-oxidation in each yellow catfish group. C, Western blot image and statistical analysis on the relative protein content of ACBD5 in the yellow catfish liver and hepatocytes. D, Western blot image of ACBD5. PNS (Supernatant), Cyto (Cytosol), Mic (Microsomal), HM (Heavy Mitochondria), LM (Light Mitochondria), and Po (Peroxisomes) are the products obtained during density gradient centrifugation. E, (a) representative images of DAPI (blue), EGFP-ACBD5 (green) and ER-Tracker (red) confocal microscopy in hepatocytes. The scale bar indicates 10 μm. (b, c) fluorescence intensity analysis with red and green lines indicating the corresponding color of fluorescence. Vertical coordinates indicate the gray values of the fluorescence channels, and horizontal coordinates indicate the relative positions of the green lines in the merged plot in (a). (d) statistics of Pearson's correlation coefficients of merged channels after ZnO NPs treatment in (a). F, relative mRNA level of β-oxidation in each yellow catfish hepatocytes group. oe-A5 means overexpression-acbd5. si-A5 means siRNA-acbd5. Data are expressed as mean ± SD (n = 3 independent experiments). A–E, p value was calculated by Student’s t tests. F, one-way ANOVA compared with Control. Letters indicate significant differences among different groups, as determined by one-way ANOVA with Tukey’s test. p value was calculated by Student’s t tests. Asterisks (∗) indicate significant differences between the two groups. ∗(p < 0.05), ∗∗(p < 0.01), ∗∗∗(p < 0.001). ER, endoplasmic reticulum; M, mitochondria; Po, peroxisomes.\n\nFigure 3: Figure 3. FOXO3 regulates ACBD5 transcription via direct binding to its promoter.A, putative FOXO3 binding sequences (MRE) and the schematic diagram showing the location of the FOXO3-targeted motif (in the acbd5 promoter region) when inserted upstream of the luciferase gene. B, Western blot image and statistical analysis on the relative protein content of FOXO3 in the yellow catfish liver and hepatocytes. C, relative mRNA level of foxo3 and acbd5 in each yellow catfish hepatocytes group. oe-F3 means overexpression-foxo3. si-F3 means siRNA-foxo3. D, Western blot image and statistical analysis on the relative protein content of ACBD5 in the yellow catfish hepatocytes. oe-F3 means overexpression-foxo3. si-F3 means siRNA-foxo3. E, dual-luciferase reporter assay. Relative luciferase activity in each group of HEK293T cells. The constructed mutant plasmids (Mut 1, Mut 2, Mut3) were transfected with wild-type plasmids into three environments (control, ZnO NP-treated, empty plasmid control, overexpression). a graph reacts to the regulation of the acbd5 promoter by ZnO NPs and the key role of Mut3 in it. b graph reacts to the regulation of the acbd5 promoter by overexpression of FOXO3 and the Mut 3 key role in it. oe-F3 means overexpression-foxo3. F, analysis of yellow catfish hepatocytes EMSA. The 5′-biotin labeled double-stranded oligomers were incubated with nuclear protein. A 100-fold excess of the competitor and mutative competitor oligomers was added to the competition and mutant competition assays, respectively. n = 3, independent experiments. Values are means ± SD. B and E, p value was calculated by Student’s t tests. C–E, letters indicate significant differences among different groups, as determined by one-way ANOVA with the Tukey’s test. p value was calculated by Student’s t tests. Asterisks (∗) indicate significant differences between each group. ∗(p < 0.05), ∗∗(p < 0.01), ∗∗∗(p < 0.001).\n\nFigure 4: Figure 4. ZnO NPs induce liver acetylation modification, inhibiting nuclear entry of FOXO3. A, relative mRNA level of histone deacetylation and histone acetylation in hepatocytes. B, Western blot image and statistical analysis on the relative protein content of pan acetylation in the hepatocytes. Low ZnO means 10 ug/ml ZnO NPs, High ZnO means 30 ug/ml ZnO NPs. C, Western blot image and statistical analysis on the relative protein content of FOXO3 in the hepatocytes from yellow catfish, hepatocytes were treated with two concentrations of ZnO NPs for 48 h, and nucleoprotein was extracted for WB analysis. Low ZnO means 10 ug/ml ZnO NPs, High ZnO means 30 ug/ml ZnO NPs. D, Western blot image and statistical analysis on the relative protein content of SIRT1 in the hepatocytes. E, Western blot image and statistical analysis on the relative protein content of SIRT1, FOXO3 and ACBD5 in the hepatocytes from yellow catfish, oe-S1 means overexpression-sirt1. si-S1 means siRNA-sirt1. n = 3, independent experiments. Values are means ± SD. A and D, p value was calculated by Student’s t tests. B, C, and E, one-way ANOVA compared with Control. Letters indicate significant differences among different groups, as determined by one-way ANOVA with the Tukey’s test. p value was calculated by Student’s t tests. Asterisks (∗) indicate significant differences between each group. ∗(p < 0.05), ∗∗(p < 0.01), ∗∗∗(p < 0.001).\n\nFigure 5: Figure 5. SIRT1 directly regulates FOXO3 deacetylation at lysine 243.A, in vitro FOXO3 acetylation assay. Different concentrations (100/500/1000 ug) EGFP-ACBD5 plasmid and 6∗His-FOXO3 plasmid were expressed in HEK293T cells, detected by immunoblotting using anti-lysine, anti-GFP or anti-His antibodies. The acetylation level of SIRT1 was quantified by using an acetylation antibody to detect acetylation levels on immunoprecipitation-conjugated FOXO3 proteins. Inputs represent 1% of total lysate. B, immunoprecipitation analysis of SIRT1 binds to FOXO3. both 6∗His-FOXO3 and EGFP-SIRT1 were expressed in HEK293T cells and detected by immunoblotting using EGFP or 6∗His antibodies. Inputs represent 1% of total lysate. The level of SIRT1 protein on bound FOXO3 proteins by immunoblotting using anti-EGFP antibody. Levels of immunoprecipitated FOXO3 protein were detected using 6∗His antibody. C, alignment of FOXO3 amino acid sequence from other species. Red outline indicates the conserved K226, K243 and K275. D, schematic diagram showing 3 sites insert upstream of 6∗His gene and mutative sites of three. K226R, K243R, K275R means lysine 226, lysine 243 and lysine 275 residues were replaced by arginine (R). E, mutations of K226, K243, and K275 in FOXO3 with arginine (R) abolish acetylation modification induced. HEK293T cells were transfected with wild-type (WT) FOXO3 or K226R or K243R or K275R, and then cells were harvested for immunoprecipitation using anti-pan acetylation or anti-6∗His antibody and the immunocomplex was analyzed by Western blot."
      }
    ]
  },
  {
    "id": "PMC12360241_multi",
    "image": [
      "images/PMC12360241-f1.png",
      "images/PMC12360241-f2.png",
      "images/PMC12360241-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Pyridoxine-dependent epilepsy: Current perspectives and questions for future research\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Continuous monitoring with an ambulatory electroencephalographic recorder was performed in a three-month-old girl undergoing evaluation for pyridoxine-dependent epilepsy. (A) Clinical seizure, consisting of eye deviation to the right and asymmetric clonic movements of the extremities, was associated with widely distributed high-voltage electrographic seizure activity. (B) Five minutes after patient received 100 mg pyridoxine by intravenous infusion, electrographic seizure activity was markedly reduced. All clinical and electrographic seizure activity resolved within 7 min of administration of pyridoxine. (C) At 10 min after the administration of pyridoxine, electrographic activity was markedly depressed without evidence of epileptiform activity. The electroencephalogram remained depressed throughout the next 12 h, at which point the monitoring was discontinued. Compound heterozygous pathogenic variants in ALDH7A1 were subsequently demonstrated. Horizontal calibration = 1 s; vertical calibration = 200 mv. Reproduced with permission of the publisher from Gospe.5\n\nFigure 2: Figure 2. T1-weighted sagittal magnetic resonance image of a 35-year-old man with PDE-ALDH7A1 that demonstrates thinning of the isthmus of the corpus callosum and mega cisterna magna.\n\nFigure 3: Figure 3. Lysine is metabolized through two distinct pathways usually referred to as the pipecolate and saccharopine pathways, respectively, as these are the prominent metabolites. PDE-ALDH7A1 is caused by the deficiency of α-aminoadipic semialdehyde dehydrogenase (AASADH). This results in the accumulation of multiple metabolites within the lysine metabolism pathway, including two biomarkers purposed for newborn screening: 6-oxo-pipecolate and 2-OPP. Created with BioRender.com."
      }
    ]
  },
  {
    "id": "PMC12361609_multi",
    "image": [
      "images/PMC12361609-f1.png",
      "images/PMC12361609-f2.png",
      "images/PMC12361609-f3.png",
      "images/PMC12361609-f4.png",
      "images/PMC12361609-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Stem cell and gene therapies for leukodystrophies\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Milestone timeline of stem cell and gene therapies for leukodystrophies The spaces between the lines are not to scale. AAV, adeno-associated virus; ARSA, Arylsulfatase A; ASPA, Aspartoacylase; CALD, cerebral adrenoleukodystrophy; CD, Canavan disease; EMA, European Medicines Agency; FDA, US Food and Drug Administration; GALC, Galactocerebrosidase; GLD, globoid cell leukodystrophy, Krabbe disease; HSCT, hematopoietic stem cell transplantation; HSC-GT, hematopoietic stem cell gene therapy; IEMs, inborn errors of metabolism; IIEs, inherited inborn errors; IMDs, inherited metabolic disorders; LSDs, lysosomal storage disorders; MDs, metabolic disorders; MLD, metachromatic leukodystrophy; MSC, mesenchymal stem cell; NDs, neuro-degenerative disorders; NSC, neural stem cell; PDs, peroxisomal disorders; PMD, Pelizaeus-Merzbacher disease; UCBT, umbilical cord blood transfusion. IEMs, IIEs, IMDs, NDs, LSDs, PDs, and MDs are broad disease categories, each of which includes at least one form of leukodystrophy. Some clinical trials have received applications from both the FDA and EMA, but the figure indicates only FDA approvals. Created in https://BioRender.com.\n\nFigure 2: Figure 2. Schematic representation of HSC-based therapies for leukodystrophies (A) HLA-matched health donor CD34+ HSCs are transplanted to the patient after cytoreductive conditioning. (B) Autologous CD34+ HSCs are corrected by LVs for the deficient gene and reinfused with reduced-intensity conditioning. (C) Transplanted HSCs cross the BBB and differentiate into microglia-like cells (MGLCs). (D and E) Post-transplantation, the lipid metabolic pathways are restored, preventing OL toxicity and halting the demyelination process, facilitated by the enzyme complementation from MGLCs. Created in https://BioRender.com.\n\nFigure 3: Figure 3. Key mechanisms involved in NSC and MSC transplantation for leukodystrophies (A) NSCs with normal functions undergo sequential differentiation into neurons, OLs, astrocytes, peripheral neurons, and Schwann cells to reconstruct and replace damaged and functionally impaired CNS and PNS. (B) MSCs secrete a variety of cytokines and exosomes to reduce inflammation and promote nerve reconstruction and vascular regeneration and MSCs can address osteogenic defects of leukodystrophy patients. In addition, MSCs possess the potential to differentiate into NSCs, CNS cells, and PNS cells under specific conditions. Created in https://BioRender.com.\n\nFigure 4: Figure 4. Advanced PSC-based technologies for leukodystrophy treatment (A) Design of off-the-shelf PSC-derived NPCs can be achieved using two strategies. One can completely knock out B2M (core genes of HLA-I molecules) and CIITA (core genes of HLA-II molecules) of PSCs while knocking in HLA-E to avoid NK cell killing, or one can knock out HLA-A, HLA-B, and CIITA of PSCs, and can avoid killing by T cells and NK cells. After these, differentiation produces off-the-shelf PSC-derived NPCs. (B) Autologous iPSC-based cell therapy is an individualized therapeutic strategy in which somatic cells are isolated from patient biopsy tissues, reprogrammed to obtain patient iPSCs, genetically corrected to repair disease-causing mutations, and directed to differentiate into NSCs, NPCs, or OPCs. Ultimately, functional cells are transplanted back into the original patient. (C) iPSC-based disease models can be used to explore the developmental process of diseases, develop novel therapies and personalized medicine, and to replace animal testing to study the applicability of therapies. (D) iPSC-derived models combined with technologies such as RNA sequencing and immunofluorescent labeling can be used for high-throughput, highly consistent and personalized drug screening and development. Created in https://BioRender.com.\n\nFigure 5: Figure 5. Route of administration and use of AAV serotypes in ongoing clinical trials for AAV-based gene replacement therapy for leukodystrophies CD, Canavan disease; GLD, globoid cell leukodystrophy, Krabbe disease; ICM, intracisterna magna; ICV, intracerebroventricular; IP, intraparenchymal; IT, intrathecal; IV, intravenous; MLD, metachromatic leukodystrophy. Created in https://BioRender.com."
      }
    ]
  },
  {
    "id": "PMC12374088_multi",
    "image": [
      "images/PMC12374088-f1.png",
      "images/PMC12374088-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Treatment of Inborn Errors by Product Replacement: The Example of Inborn Errors of Bile Acid Synthesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The ‘neutral pathway’ for bile acid synthesis. Enzymes catalysing the individual steps are indicated by the genes encoding them—see the table for the full enzyme name. In adults, the major pathway for the synthesis of CDCA and CA is the so‐called ‘neutral pathway’ that starts with the modification of the steroid nucleus of cholesterol by hydroxylation, isomerisation, and reduction reactions catalysed by enzymes located in the cytosol and endoplasmic reticulum (encoded by CYP7A1, HSD3B7, AKR1D1, and AKR1C1/C4 for CDCA and additionally CYP8B1 for CA). This is followed by side chain oxidation in the mitochondria, producing the C27 bile acids, 3α,7α‐dihydroxy‐5β‐cholestanoic acid (DHCA) and 3α,7α,12α‐trihydroxy‐5β‐cholestanoic acid (THCA). The 25R isomers of DHCA and THCA (as their CoA esters) are imported into the peroxisomes by the ABCD3 transporter (PMP70) and are converted to the 25S isomers by α‐methylacyl‐CoA racemase (AMACR). In the peroxisomes, oxidation of the side chain is completed by the β‐oxidation enzymes, acyl‐CoA oxidase 2 (ACOX2), the D‐bifunctional protein (HSD17B4) and the peroxisomal thiolase, SCPX (SCP2) [2]. The resulting CoA esters of CA and CDCA are converted to the glycine and taurine conjugates of the bile acids by the peroxisomal enzyme bile acid CoA; amino acid N‐acyl transferase [BAAT].\n\nFigure 2: Figure 2. The first steps of the ‘acidic pathway’ for bile acid synthesis. Enzymes catalysing the individual steps are indicated by the genes encoding them—see the table for the full enzyme name. The acidic pathway starts with oxidation of the cholesterol side‐chain in the mitochondria, producing 27‐hydroxycholesterol and 3β‐hydroxy‐5‐cholestenoic acid. This is catalysed by the mitochondrial sterol 27‐hydroxylase encoded by CYP27A1. 3β‐Hydroxy‐5‐cholestenoic acid is then hydroxylated in the 7α‐position by the oxysterol 7α‐hydroxylase encoded by CYP7B1. Subsequent steps include (i) the completion of nuclear modifications which are thought to be catalysed by the same enzymes as in the neutral pathway (enzymes encoded by HSD3B7, AKR1D1 and AKR1C1/C4), and (ii) beta‐oxidation in the peroxisomes (again using the same enzymes and transporter as in the neutral pathway), and finally conjugation to produce mainly the taurine and glycine conjugates of CDCA."
      }
    ]
  },
  {
    "id": "PMC12383759_multi",
    "image": [
      "images/PMC12383759-f1.png",
      "images/PMC12383759-f2.png",
      "images/PMC12383759-f3.png",
      "images/PMC12383759-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Gene Therapy of Adrenomyeloneuropathy: Challenges, Target Cells, and Prospectives\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Regions of the cervical spinal cord white matter corresponding to the main ascending and descending tracts affected by AMN pathology. These regions were sampled by Y. Özgür Günes in Abcd1y/- mice to study cell transduction by the AAV9-MAG-hABCD1 vector [129]. (1) fasciculus cuneatus, fasciculus cerebrospinalis (pyramidal tract); (2,3) dorsolateral thalamic tract, dorsal spinocerebellar tract, rubrospinal tract; (4,5) ventral spinothalamic tract, ventral spinocerebellar tract; (6,7) ventral spinocerebellar tract, rostral reticulospinal tract.\n\nFigure 2: Figure 2. Immunofluorescence images of colocalization of ALDP-HA in peroxisomes and transcription factors in the nucleus of an oligodendrocyte (Olig2) or of an astrocyte (GFAP). Punctate dots indicate that ALDP is localized in peroxisomes [128].\n\nFigure 3: Figure 3. Evolution of the latency to fall from the rotarod in the three groups of mice from 18 to 24 months of age showing the rapid recovery of motor performances in mice treated with the AAV9-MAG vector [135]. p < 0.005 vs. untreated Abcd1-/y mice.\n\nFigure 4: Figure 4. Two long axons traveling the white matter of the spinal cord form the descending corticospinal tracts (cst in green) and the ascending spinocerebellar tracts (sct, in brown). Their respective neurons of origin are in the motor cortex of mouse brain, or in lumbar dorsal root ganglia (DRG). The three main glial cells of the white matter are schematized. The four routes of AAV9 vector administration to Abcd1y/- mice that have been used are figured as IV (intravenous) in newborns [129] or adults [132,134], IT (intrathecal) in adults [49,132,145], ICM (intra-cisterna magna) in adults [128], or ICV (intra-cerebro-ventricular) in adults [132,134]. Neurons of the motor cortex and microglia were not transduced by any vector. Oligodendrocytes and astrocytes were abundantly transduced by the neonatal IV [129] or the adult ICM [128] administration of the AAV9-MAG vector. DRG neurons and astrocytes were transduced by the IT administration of the AAV9-CAG vector [49]."
      }
    ]
  },
  {
    "id": "PMC12392333_multi",
    "image": [
      "images/PMC12392333-f1.png",
      "images/PMC12392333-f2.png",
      "images/PMC12392333-f3.png",
      "images/PMC12392333-f4.png",
      "images/PMC12392333-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Elovl1 inhibition reduced very long chain fatty acids in a mouse model of adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Elovl1 heterozygous knockout characterization (A) qPCR analysis of relative Elovl1 expression in brains of WT and heterozygous Elovl1 knockout mice (2 WT, 4 mutant). (B) Total C26:0 fatty acid quantification as a function of mouse age across tissues (Spinal cord n = 4, Brain, Kidney, Liver n = 8–10, Plasma n = 8–10, mixed sex). (C) Representative images from H&E-stained tissue sections, scale bar = 200 μm. Statistical significance was determined using one-way ANOVA, Sidak correction for multiple comparisons test. Error bars represent the mean ± S.D.\n\nFigure 2: Figure 2. In vitro characterization of CPD37 (A) Structure of CPD37. (B) Inhibition of sphingomyelin (SM) C26:0 upon treatment of ALD-patient fibroblasts with CPD37, normalized to SM C22:0 (n = 2 technical replicates). (C) Inhibition of elongation of a stable-isotope labeled substrate with CPD37 treatment. (D) Cellular thermal shift assay (CETSA) results from intact Jurkat cells treated with and without CPD37. Error bars represent the mean ± S.D.\n\nFigure 3: Figure 3. In vivo PK/PD of CPD37 (A) Plasma exposure of CPD37 following a single oral administration in mice (N = 3, FVB, males). (B) Plasma and brain exposure of CPD37 following a 3 mg/kg IV administration (N = 3, FVB, males). (C) Total C26:0 levels in the brain and spinal cord of WT mice treated with CPD37 for 12 days (N = 4, FVB, males). (D) Total C20:0 levels in the brain and spinal cord of WT mice treated with CPD37 for 12 days (N = 4, FVB, males). All animals were 8–15 weeks old. Statistical significance was determined using one-way ANOVA followed by Dunnett’s multiple comparisons test. Error bars represent the mean ± S.D.\n\nFigure 4: Figure 4. Stable isotope labeled in vivo elongation assay in WT mice (A) 13C-labeled C20:0 and C22:0 levels in the brain of mice treated with CPD37. (B) Total C22:0 and C26:0 levels. (C) Levels of 13C-labeled C22:0 in the spinal cord. (D) 13C-labeled C22:0, C24:0 levels in the liver. Vehicle (2%PVP k25, 0.1%SLS in water) n = 5, 10 mg/kg n = 6, 30 mg/kg n = 10, 100 mg/kg n = 9, mixed sex, 17–20 days old pups. Statistical significance was determined using one-way ANOVA followed by Dunnett’s multiple comparisons test. Error bars represent the mean ± S.D.\n\nFigure 5: Figure 5. Abcd1-/y mouse characterization Changes in total fatty acids of various chain lengths and saturation states as a function of mouse age. Brain samples were of the dissected cortex, while spinal cord samples were the whole tissue. The lipid levels at 1 week of age were taken as the baseline and relative changes are shown at 2, 4, 8, 16, 32, 52, and 78 weeks of age. N = 5 for all mutant ages, n = 3 for WT 1 week, n = 4 for WT 52 weeks, n = 5 for all other WT ages. All mice were males. Error bars represent the mean ± S.D."
      }
    ]
  },
  {
    "id": "PMC12392333_multi_2",
    "image": [
      "images/PMC12392333-f6.png",
      "images/PMC12392333-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Elovl1 inhibition reduced very long chain fatty acids in a mouse model of adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. PK/PD studies of CPD37 in Abcd1-/y mice (A) Changes in total C26:0 levels in Abcd1-/y mice following daily oral administration of CPD37 at three doses: 10, 30, and 100 mg/kg for 7, 14, and 30 days (n = 7–8 male animals). Statistics are shown relative to the untreated age-matched Abcd1-/y mice. two-way ANOVA followed by Dunnett’s multiple comparisons test. ∗∗∗∗ indicates adjusted p-value <0.0001, ∗∗∗ indicates adjusted p-value <0.001, ∗∗ indicates adjusted p-value <0.01, ∗ indicates adjusted p-value <0.05, ns = not significant. (B) Plasma exposure of CPD37 measured 2 h post dose (n = 5 animals). (C–F) Untargeted lipidomics showing accumulation of PCs with ≥42 carbons were reduced with CPD37 treatment. Volcano plot for identified lipids, colored by lipid class and sized according to total number of carbons in monoacyl-, diacyl-, and triacyl-chains. Dashed line indicates 0.05 FDR-corrected p-value. Full data are available Table S1. (C) Spinal cord lipids in Abcd1-/y vs. WT mice. (D) Spinal cord lipids in CPD37-treated Abcd1-/y vs. Abcd1-/y mice. (E) Brain lipids in Abcd1-/y vs. WT mice. (F) Brain lipids in CPD37-treated Abcd1-/y vs. Abcd1-/y mice. (G) Changes in C26:0 levels after 7-month treatment of Abcd1-/y mice with 100 mg/kg/day of CPD37 formulated in feed (n = 10–12 animals). All mice were males. Statistical significance was determined using one-way ANOVA followed by Dunnett’s multiple comparisons test. For all panels, error bars represent the mean ± S.D.\n\nFigure 7: Figure 7. Single-nuclei RNA-seq analysis of long term CPD37 treated Abcd1-/y animals Single-Nuclei RNA-seq study on the effects of Abcd1-/y and ELOVL1 inhibitor CPD37 in mouse brain and spinal cord (n = 4 per group, 13-month old males). (A) UMAP visualization of all cells from twelve samples from the mouse brain cell-type annotated by SARGENT. (B) UMAP visualization of all cells from twelve samples from the mouse spinal cord cell-type annotated by SARGENT, mNEUR: mature neurons. (C) (Top) Volcano plot of differentially expressed genes by pseudobulk differential expression comparison in Mouse Oligodendrocytes in the Brain comparing Abcd1-/y model with wild-type mice. (D) Grouped bar plot comparing number of genes which are up or downregulated in a DGE comparison between Abcd1-/y model and wild-type mice across cell types in (left) brain and (right) spinal cord. (E) Heatmap of gene ontology pathway NES score from genes comparison by cell type, split by tissue in (left) Abcd1-/y model and wild-type mice and (right) CPD37 + Abcd1-/y model and Abcd1-/y model comparisons."
      }
    ]
  },
  {
    "id": "PMC12393905_multi",
    "image": [
      "images/PMC12393905-f1.png",
      "images/PMC12393905-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Successful Treatment of Severe Hepatopulmonary Syndrome as a Rare Complication of Zellweger Spectrum Disorder\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Imaging results at the age of 7 years 3 months. (A) Abdominal ultrasound scan showing nodular liver surface. (B) Abdominal ultrasound scan demonstrating recanalization of the ductus venosus. (C) 99 m‐Tc MAA scan demonstrating uptake of tracer in both kidneys and the brain, with a calculated right‐to‐left shunt of 39.8%.\n\nFigure 2: Figure 2. Macroscopic (A) and microscopic (B) view of the explanted liver, showing evidence of nodular cirrhosis."
      }
    ]
  },
  {
    "id": "PMC12426611_multi",
    "image": [
      "images/PMC12426611-f1.png",
      "images/PMC12426611-f2.png",
      "images/PMC12426611-f3.png",
      "images/PMC12426611-f4.png",
      "images/PMC12426611-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"O‐GlcNAcase Inhibitor Improves Denervation‐Induced Muscle Atrophy in Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Inhibition of OGA enhances phosphorylation of Akt and decreased expression of muscle‐specific ubiquitin ligases in C2C12 myotubes. Representative western blots (left) and summary data (right) of O‐GlcNAc and OGA (A), p‐Akt (Ser473), Akt, atrogin‐1 and MuRF1 (B) levels in C2C12 myotubes transfected with si‐Scramble or si‐OGA (n = 6 in each group). Representative western blots (left) and summary data (right) of O‐GlcNAc (C), p‐Akt (Ser473), Akt, atrogin‐1 and MuRF1 (D) levels in C2C12 myotubes treated with PBS or different doses of thiamet G (10−8, 10−7 and 10−6 mol/L) (n = 6 in each group). p‐Akt was normalized to total Akt, and other results were normalized to non‐specific bands of the CBB‐stained gel. Data are shown as the mean ± SD. p values were calculated by the unpaired Student t‐test or Mann–Whitney U test for Panels A and B and one‐way ANOVA followed by the Dunnett post hoc test or Kruskal–Wallis test followed by Dunn's post hoc test for Panels C and D. Atrogin‐1, muscle atrophy F‐box; CBB, Coomassie Brilliant Blue; MuRF‐1, muscle RING Finger‐1; NS, not significant; OGA, O‐GlcNAcase; O‐GlcNAc, O‐linked N‐acetylglucosamine; p‐Akt, phosphorylated Akt; PBS, phosphate‐buffered saline; si, small interfering.\n\nFigure 2: Figure 2. O‐GlcNAcylation is reduced in skeletal muscle undergoing denervation‐induced atrophy. Summary data of body weight (A) and gastrocnemius weight (B) of mice 1, 3, 5 and 7 days after the sham or denervation operation (n = 5 in each group). (C) Representative high‐magnification photomicrographs (left) of gastrocnemius muscle tissue sections stained with Picrosirius Red 7 days after the sham or denervation operation. Summary data (right) of cross‐sectional area of myocytes in the gastrocnemius muscle of mice 1, 3, 5 and 7 days after the sham or denervation operation (n = 5 in each group). Representative western blots (left) and summary data (right) of p‐Akt (Ser473), Akt, p‐FoxO3A (Thr32), FoxO3A, atrogin‐1 and MuRF1 (D), and O‐GlcNAc, OGA, OGT, GFAT1 and GFAT2 (E) levels in the gastrocnemius of mice 1, 3, 5 and 7 days after the sham or denervation operation (n = 4 in each group). Results were normalized to non‐specific bands of the CBB‐stained gel. Data are shown as the mean ± SD. p values were calculated by one‐way ANOVA followed by the Dunnett post hoc test or Kruskal–Wallis test followed by Dunn's post hoc test. Atrogin‐1, muscle atrophy F‐box; CBB, Coomassie Brilliant Blue; GFAT, glutamine fructose‐6‐phosphate amidotransferase; MuRF‐1, muscle RING Finger‐1; NS, not significant; OGA, O‐GlcNAcase; O‐GlcNAc, O‐linked N‐acetylglucosamine; OGT, O‐GlcNAc transferase; p‐Akt, phosphorylated Akt; p‐FoxO3A, phosphorylated forkhead box O3A.\n\nFigure 3: Figure 3. Thiamet G treatment improves denervation‐induced skeletal muscle atrophy. (A) Experimental protocol for thiamet G treatment of skeletal muscle undergoing denervation‐induced atrophy. Summary data of body weight (B) and gastrocnemius weight/body weight (C) in sham + vehicle, sham + thiamet G, denervation (Den) + vehicle and Den +thiamet G groups (n = 7 in each group). (D) Representative high‐magnification photomicrographs (left) and summary data (right) of the cross‐sectional area of myocytes in gastrocnemius tissue sections stained with Picrosirius Red from the four groups (n = 7 in each group). (E) Distribution of fibre numbers per cross‐sectional area in the gastrocnemius tissue sections of the four groups. Data are shown as the mean ± SD. p values were calculated by the unpaired Student t‐test for Panel B. p values of the main effect for each factor and interaction effect between two factors were calculated by two‐way ANOVA with the factors of denervation and thiamet G, and if there was an interaction effect between two factors, the Tukey post hoc test was performed. Den, denervation; NS, not significant.\n\nFigure 4: Figure 4. Thiamet G treatment suppresses the decrease in Akt activation and the enhancement of protein degradation in denervation‐induced skeletal muscle atrophy. (A) Representative western blots (left) and summary data (right) of O‐GlcNAc and OGA levels in gastrocnemius muscle of sham + vehicle, denervation (Den) + vehicle and Den + thiamet G groups (n = 7 in each group). Results were normalized to non‐specific bands of the CBB‐stained gel. (B) Immunoprecipitation assays using lysates of the gastrocnemius muscle of mice of the three groups (n = 7 in each group). After immunoprecipitation with control IgG or an O‐GlcNAc antibody, immunoblotting for Akt and O‐GlcNAc was performed. Representative western blots (left) and summary data (right) of O‐GlcNAc‐Akt are shown. Representative western blots (left) and summary data (right) of p‐Akt (Ser473), Akt, p‐FoxO3A (Thr32), FoxO3A, atrogin‐1 and MuRF1 (C) and ubiquitination (D) levels in the gastrocnemius muscle of mice of the three groups (n = 7 in each group). Results were normalized to non‐specific bands of the CBB‐stained gel. Data are shown as the mean ± SD. p values were calculated by one‐way ANOVA followed by the Tukey post hoc test. Atrogin‐1, muscle atrophy F‐box; CBB, Coomassie Brilliant Blue; Den, denervation; IB, immunoblotting; IP, immunoprecipitation; MuRF‐1, muscle RING Finger‐1; NS, not significant; OGA, OGlcNAcase; O‐GlcNAc, O‐linked N‐acetylglucosamine; O‐GlcNAc‐Akt, O‐GlcNAcylated Akt; p‐Akt, phosphorylated Akt; p‐FoxO3A, phosphorylated forkhead box O3A.\n\nFigure 5: Figure 5. Muscle‐specific suppression of OGA improves denervation‐induced skeletal muscle atrophy. (A) Experimental protocol for AAV1‐sh‐OGA treatment of skeletal muscle undergoing denervation‐induced atrophy. (B) Representative western blots (left) and summary data (right) of O‐GlcNAc and OGA levels in gastrocnemius muscle of denervation (Den) + AAV1‐sh‐Scramble and Den + AAV1‐sh‐OGA groups (n = 7 in each group). Results were normalized to non‐specific bands of the CBB‐stained gel. Summary data of body weight (C) and gastrocnemius weight/body weight (D) in sham + AAV1‐sh‐Scramble, sham + AAV1‐sh‐OGA, Den + AAV1‐sh‐Scramble and Den + AAV1‐sh‐OGA groups (n = 7 in each group). (E) Representative high‐magnification photomicrographs (left) and summary data (right) of the cross‐sectional area of myocytes in gastrocnemius tissue sections stained with Picrosirius Red of the four groups (n = 7 in each group). Data are shown as the mean ± SD. p values were calculated by the unpaired Student t‐test for Panels B and C. p values of the main effect for each factor and interaction effect between two factors were calculated by two‐way ANOVA, with the factors denervation and AAV1‐sh‐OGA, and if there was an interaction effect between two factors, the Tukey post hoc test was performed. AAV1, adeno‐associated virus serotype 1; CBB, Coomassie Brilliant Blue; Den, denervation; NS, not significant; OGA, O‐GlcNAcase; sh, short hairpin."
      }
    ]
  },
  {
    "id": "PMC12426611_multi_2",
    "image": [
      "images/PMC12426611-f6.png",
      "images/PMC12426611-f7.png",
      "images/PMC12426611-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"O‐GlcNAcase Inhibitor Improves Denervation‐Induced Muscle Atrophy in Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Thiamet G treatment improves fasting‐induced skeletal muscle atrophy and grip strength of mice. (A) Experimental protocol of thiamet G treatment for fasting‐induced skeletal muscle atrophy in mice. Summary data of body weight (B) and gastrocnemius weight/tibial length (C) in the fasted + vehicle and fasted + thiamet G groups (n = 7 in each group). (D) Representative high‐magnification photomicrographs (left) and summary data (right) of the cross‐sectional area of myocytes in gastrocnemius tissue sections stained with Picrosirius Red from the two groups (n = 7 in each group). (E) Changes in grip strength before (0 h) and after fasting in the two groups (n = 7 in each group). Data are shown as the mean ± SD. p values were calculated by the unpaired Student t‐test. NS, not significant.\n\nFigure 7: Figure 7. Interaction between phosphorylation of Akt at serine 473 and O‐GlcNAcylation of Akt at threonine 479 in C2C12 myotubes. (A) Representative immunoblotting (left) and summary data (right) of p‐Akt (Ser473 and Thr308) and Akt levels in C2C12 myotubes treated with an adenovirus expressing wild‐type Akt (Ad‐Akt wt) or mutant Akt (T479A) (Ad‐Akt T479A) and transfected with si‐OGA (n = 6 in each group). p‐Akt was normalized to total Akt. Immunoblots of the lysates of C2C12 myotubes transfected with si‐Scramble are also shown. (B) Immunoprecipitation assays using lysates of C2C12 myotubes of the two groups (n = 6 in each group). After immunoprecipitation with control IgG or an O‐GlcNAc antibody, immunoblotting for Akt and O‐GlcNAc was performed. Representative western blots (left) and summary data (right) of O‐GlcNAc‐Akt are shown. Data are shown as the mean ± SD. p values were calculated by the unpaired Student t‐test. ad, adenovirus; CBB, Coomassie Brilliant Blue; IB, immunoblotting; IP, immunoprecipitation; NS, not significant; OGA, O‐GlcNAcase; O‐GlcNAc, O‐linked N‐acetylglucosamine; O‐GlcNAc‐Akt, O‐GlcNAcylated Akt; p‐Akt, phosphorylated Akt; siRNA, small interfering RNA; wt, wild type.\n\nFigure 8: Figure 8. Schematic diagram of the potential roles of O‐GlcNAcylation and a possible therapeutic target for OGA inhibitors in skeletal muscle atrophy. Atrogin‐1, muscle atrophy F‐box; FoxO3A, forkhead box O3A; mTOR, mechanistic target of rapamycin; MuRF1, muscle RING Finger‐1; OGA, O‐GlcNAcase; p70S6K, p70S6 kinase."
      }
    ]
  },
  {
    "id": "PMC12441361_multi",
    "image": [
      "images/PMC12441361-f1.png",
      "images/PMC12441361-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Protein quality control systems in neurodegeneration – culprits, mitigators, and solutions?\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Protein quality control by the ubiquitin-proteasome system and the autophagy-lysosome pathway. (A) Ubiquitin serves as a recognition signal that marks proteins destined for degradation. These proteins are either misfolded/denatured or otherwise damaged proteins, or proteins that completed their function (e.g., cell cycle regulators). Ubiquitinated proteins can be recognized by inherent proteasomal ubiquitin receptors, and/or via soluble ubiquitin receptors which serve as shuttle proteins. These shuttle proteins (e.g., SQSTM1/p62) can target ubiquitinated proteins to either proteasomal or autophagic degradation. (B) The removal of proteins by the ubiquitin-proteasome system begins with the ATP-dependent activation of ubiquitin molecules by the ubiquitin-activating enzyme E1. Ubiquitin moieties are next transferred to a ubiquitin-conjugating enzyme (also known as ubiquitin-carrier protein), or E2. A third enzyme, E3 or ubiquitin ligase, brings the ubiquitin-carrying E2 and the substrate protein to the proximity that facilitates the transfer of the ubiquitin moiety to a lysine residue in the substrate. E3 ligases largelly belong to one of two classes: RING (Really INteresting Genes) E3s catalyze ubiquitin transfer from the E2 directly to the substrate, while HECT (Homologous to the E6-AP Carboxyl Terminus) domain E3s first bind the ubiquitin molecule, prior to its conjugation to the substrate. In both cases, a ubiquitin chain is elongated through the conjugation of additional ubiquitin moieties on lysine residues of a previously attached ubiquitin. (C) Protein degradation via autophagy is facilitated by deliverying substrates into the lysosome, where they are digested by acidic proteases. There are 3 different mechanisms through which proteins are delivered into the lysosome for their degradation: (1) Microautophagy, in which proteins are swallowed through invagination of cytoplasmic droplets into the lysosome. (2) Chaperone-mediated autophagy, where certain proteins are recognized by chaperones and are inserted into the lysosome via channels located on the lysosomal membrane. (3) Macroautophagy, under which proteins, voxels of cytoplasm, and/or organelles are engulfed by a growing membrane to eventually form an autophagosome, which subsequently fuses with the lysosome (producing an autolysosome) thereby injecting its cargo into the acidic and catalytic environment of the lysosome. Organelles such as the mitochondria are also destined for macroautophagy via ubiquitination (e.g., of outer mitochondrial proteins), which is recognized by shuttle proteins such as p62 that also binds to the autophagic receptor LC3, thereby securing the binding of its cargo to the forming autophagosome which will later be delivered into the lysosome.\n\nFigure 2: Figure 2. Mechanisms for neuronal toxicity caused by aggregated proteins in neurodegenerative diseases. NDD-related aggregated proteins exert neurotoxicity via different mechanism, including impairment of adequate proteostasis, damage to cellular structures, inhibition of molecule trafficking along axons, and neural injury due to oxidative stress and inflammation. See Table 1 and text for further details and references."
      }
    ]
  },
  {
    "id": "PMC12442749_multi",
    "image": [
      "images/PMC12442749-f1.png",
      "images/PMC12442749-f2.png",
      "images/PMC12442749-f3.png",
      "images/PMC12442749-f4.png",
      "images/PMC12442749-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A Scoping Review of Human Teratogens and Their Impact on the Developing Brain: A Contribution From the ConcePTION Project\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PRISMA flowchart showing the study selection and screening process.\n\nFigure 2: Figure 2. Map showing the location of empirical cohorts included in this scoping review. Note that there were two multinational studies and that in both cases all individual participating countries are shown here.\n\nFigure 3: Figure 3. Timelines showing the market authorisation date and timing of case series and empirical studies included in this review that report neurodevelopmental outcomes for sodium valproate, carbamazepine and phenytoin. Ŧ = the first empirical study to include formal analysis and a comparator group; * = case studies reporting a significant neurodevelopmental impairment; ♦ = cohort results reported in a single publication for this medication; > − <= cohort results reported in multiple publications for this cohort, showing the period of time over which results are reported.\n\nFigure 4: Figure 4. Timelines showing the market authorisation date and timing of case series and empirical studies included in this review that report neurodevelopmental outcomes for phenobarbital, phenytoin and topiramate. Ŧ = the first empirical study to include formal analysis and a comparator group; * = case studies reporting a significant neurodevelopmental impairment; ♦ = cohort results reported in a single publication for this medication; > − <= cohort results reported in multiple publications for this cohort, showing the period of time over which results are reported.\n\nFigure 5: Figure 5. Timelines showing the market authorisation date and timing of case series and empirical studies included in this review that report neurodevelopmental outcomes for non‐antiseizure medications included in this review. Ŧ = the first empirical study to include formal analysis and a comparator group; * = case studies reporting a significant neurodevelopmental impairment; ♦, X , = cohort results reported in a single publication for the medication indicated in the key on each timeline."
      }
    ]
  },
  {
    "id": "PMC12486197_multi",
    "image": [
      "images/PMC12486197-f1.png",
      "images/PMC12486197-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Research advancements regarding the relationship between FBXO2 and malignant tumors (Review)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic diagram of the ubiquitination process. E1, ubiquitin-activating enzyme; E2, ubiquitin-conjugating enzyme; E3, ubiquitin ligase; TPP II, tripeptidyl peptidase II; RBX1, ubiquitin ligase with zinc finger structure; CUL1, Cullin-1 proteins; SKP1, S-phase kinase-related protein 1; F-box, F-box protein; Ub, ubiquitin; PPi, pyrophosphate.\n\nFigure 2: Figure 2. Schematic diagram of FBXO2 generation. FBXO2, F-box protein 2; MHC, major histocompatibility complex."
      }
    ]
  },
  {
    "id": "PMC12492069_multi",
    "image": [
      "images/PMC12492069-f1.png",
      "images/PMC12492069-f2.png",
      "images/PMC12492069-f3.png",
      "images/PMC12492069-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A Novel Missense Variant of the ABCD1 Gene in X‐Linked Adrenoleukodystrophy in Chinese Family\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Analysis of skin pigmentation and MRI characteristics in the X‐ALD proband. (A, B) The proband exhibits marked pigmentation in specific areas of the skin. As indicated by the white arrows in the images, significant pigment deposition is observed in the ankles, toes, and palms. (C–F) MRI scans of the proband's brain reveal lesions primarily localized to the white matter surrounding the posterior region (C), posterior horns (D, E), and inferior horns (F) of the bilateral lateral ventricles, with involvement of the corpus callosum. On T1‐weighted imaging (T1WI), these lesions appear as areas of hypointensity, whereas on T2‐weighted imaging (T2WI), they demonstrate hyperintensity. The region denoted by the red arrow demonstrates an abnormal signal within the white matter.\n\nFigure 2: Figure 2. Pedigree analysis of Chinese families with a novel ABCD1 mutation. (A) The figure illustrates the pedigree of a family affected by X‐linked adrenoleukodystrophy (X‐ALD). Unaffected males are represented by blank squares, female carriers by circles with black dots, and confirmed X‐ALD patients by filled black squares. The proband, identified as a hemizygote, is marked with a red arrow. (B) Sanger sequencing of peripheral blood cDNA samples from the proband (II‐1) and his parents revealed that both the proband and his mother (carrier, I‐2) harbor a novel mutation in the ABCD1 gene: C.773T>G. This mutation results in a missense change at the protein level, substituting leucine with arginine at position 258 (p.Leu258Arg), and is identified as a newly discovered pathogenic variant. (C) Mutation analysis of the ABCD1 gene is depicted in two panels. The upper panel provides a schematic representation of the genomic structure of ABCD1, which comprises 10 exons (indicated by rectangular boxes). The lower panel illustrates the structural domains of the adrenal leukodystrophy protein (ALDP) encoded by ABCD1, including the transmembrane domain (TMD) and the nucleotide‐binding domain (NBD). The red arrow highlights the specific nucleotide alteration and the corresponding site of the amino acid substitution in the ALDP protein. (D) Cross‐species conservation analysis of the ABCD1 gene sequence reveals that leucine at position 258 (p. Leu258) is highly conserved across multiple species. Following the mutation, leucine is substituted by arginine (p.Leu258Arg), as indicated by the red arrow, underscoring the potential functional significance of this residue. (E) Various bioinformatics tools predict the potential pathogenicity of the ABCD1 p.Leu258Arg mutation.\n\nFigure 3: Figure 3. Protein structure and molecular dynamics simulation results of ABCD1. (A) Ramachandran diagram of ABCD1. (B, C) The 3D computer model (SWISS‐MODEL) predicts the protein structures of normal ABCD1 and ABCD1 with p.L258R mutation, and the red arrow shows the substituted amino acids. (D–F) shows the molecular dynamics simulation results of ABCD1 WT (black), ABCD1 p.L258R (red), RMSF (D), RMSD (E) and Rg (F).\n\nFigure 4: Figure 4. Immunofluorescence Analysis. (A) Human ABCD1 WT and mutant ABCD1 Leu258Arg expression plasmids were transfected into HEK293 cells to examine the co‐localization of ABCD1 WT (green), ABCD1 Leu258Arg (green), and ABCD3 (red) proteins. Nuclei were stained with DAPI (blue). (B, C) The fluorescence intensity distribution of ABCD1 WT, ABCD1 Leu258Arg and ABCD3 was quantified along a white line drawn through the cells using ImageJ software. Scale bar = 10 μm."
      }
    ]
  },
  {
    "id": "PMC12508092_multi",
    "image": [
      "images/PMC12508092-f1.png",
      "images/PMC12508092-f2.png",
      "images/PMC12508092-f3.png",
      "images/PMC12508092-f4.png",
      "images/PMC12508092-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ret finger protein deficiency attenuates adipogenesis in male mice with high fat diet-induced obesity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Western blot analysis of eWAT from WT mice after ND or HFD feeding. b qPCR analysis of RFP and adipogenic marker (AP2 and Adipsin) expression in autopsied fat tissue from obese human subjects. All data are presented as mean ± s.e.m. Statistical analysis was performed using unpaired Student’s t-tests. c RFP expression of omental fat tissue from lean and obese individuals. Scale bar, 100 μm. d Western blot analysis of adipose tissue from WT and RFP KO mice. e Immunofluorescence staining of eWAT from HFD-fed mice. Scale bar, 50 μm.\n\nFigure 2: Figure 2. a, b Body weight (a) and fat mass (b) in WT and RFP KO mice after ND or HFD feeding. n = 5. Statistical analysis was performed using one-way ANOVA with post hoc Tukey’s test. c, d Weights of eWAT (c) and iWAT (d). n = 5. Statistical analysis was performed using one-way ANOVA with post hoc Dunnett’s T3 test. e, f H&E-stained sections of eWAT (e) and iWAT (f). Scale bar, 100 μm. n = 4. Statistical analysis was performed using a one-way ANOVA with post hoc Dunnett’s T3 test. All data are presented as mean ± s.e.m.\n\nFigure 3: Figure 3. a−c Blood glucose levels (a), GTT (b) and AOC (c) from the GTT on WT and RFP KO mice after ND or HFD feeding. n = 4. Statistical analysis was performed using one-way ANOVA with post hoc Tukey’s test (a and b) and Dunnett’s T3 test (c). d−f Blood insulin levels (d), ITT (e) and AOC (f) from ITT on WT and RFP KO mice after ND or HFD feeding. n = 4~6. Statistical analysis was performed using one-way ANOVA with post hoc Tukey’s test (d and e) and Bonferroni’s test (f). g−i Analysis of serum metabolic parameters including leptin (g), FFA (h) and TG (i) of WT and RFP KO mice after ND or HFD feeding. n = 4~9. Statistical analysis was performed using one-way ANOVA with post hoc Dunnett’s T3 test (g and h) and Bonferroni’s test (i). All data are presented as mean ± s.e.m.\n\nFigure 4: Figure 4. a−d Body weight (a), adipose tissue morphology (b), and adipose tissue mass (eWAT (c) and iWAT (d)) of RFP flox (WT) and RFP cKO mice after ND or HFD feeding. n = 9~10. Statistical analysis was performed using two-way ANOVA with post hoc Tukey’s test (a) and one-way ANOVA with post hoc Tukey’s test (c and d). e, f H&E-stained sections of adipose tissue (eWAT (e) and iWAT (f)) in WT and RFP cKO mice after ND or HFD feeding. Scale bar, 100 μm. n = 4. Statistical analysis was performed using two-way ANOVA with post hoc Tukey’s test. g−k Analysis of metabolic parameters (glucose (g), insulin (h), leptin (i), FFA (j) and TG (k)) of WT and RFP cKO mice after ND or HFD feeding. n = 8~11. Statistical analysis was performed using one-way ANOVA with post hoc Tukey’s test. All data are presented as mean ± s.e.m.\n\nFigure 5: Figure 5. a, b Body weight (BW) (a) and adipose tissue (eWAT, iWAT and BAT) mass (b) in WT and RFP KO mice under feed−fast−refeed conditions. n = 6~8. Statistical analysis was performed using two-way ANOVA with post hoc Šidák’s test. c Histological analysis of eWAT in fed and fast groups. Scale bar, 100 μm. n = 100. Two-way ANOVA with post hoc Šidák’s test. d, e Serum FFA (d) and glycerol (e) levels in WT and RFP KO mice of fed, fast and refed groups. n = 6~8. Statistical analysis was performed using two-way ANOVA with post hoc Sidak’s test. f ISP-induced FFA release in primary adipocytes isolated from eWAT of WT and RFP KO mice. n = 12. Statistical analysis was performed using one-way ANOVA with post hoc Tukey’s test. g, h ISP-induced FFA release in 3T3-L1 adipocytes with RFP knockdown (g) or overexpression (h). n = 8. Statistical analysis was performed using two-way ANOVA with post hoc Šidák’s test. All data are presented as mean ± s.e.m."
      }
    ]
  },
  {
    "id": "PMC12508092_multi_2",
    "image": [
      "images/PMC12508092-f6.png",
      "images/PMC12508092-f7.png",
      "images/PMC12508092-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Ret finger protein deficiency attenuates adipogenesis in male mice with high fat diet-induced obesity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. DEGs between WT-HFD and RFP KO-HFD were identified based on criteria of P value ≤0.05 and |log2 fold change| ≥2. a A heat map of DEGs between WT-HFD and RFP KO-HFD groups. b KEGG pathway analysis of DEGs. c GO enrichment analysis categorizing DEGs into biological processes, cellular components and molecular functions. d DEG expression patterns in several GO category classifications. e GSEA showing enrichment of adipogenesis and obesity-related pathways. NES represents the degree to which a gene set is overrepresented at the top or bottom of the ranked gene list, normalized across all analyzed gene sets. FDR indicates the estimated probability that the observed enrichment is a false positive. Both gene sets are significantly downregulated in RFP KO-HFD. FDR, false discovery rate; NES, normalized enrichment score.\n\nFigure 7: Figure 7. a, b Oil red O staining of adipocytes derived from primary SVCs of WT and RFP KO male mice (a) and RFP-knockdown 3T3-L1 cells (b). n = 9. Statistical analysis was performed using one-way ANOVA with post hoc Tukey’s test. c Western blot analysis of adipogenic markers of RFP-knockdown 3T3-L1 adipocytes. d Densitometric analysis of protein expression of RFP, AP2 and adiponectin in RFP-deficient 3T3-L1 adipocytes. n = 6. Statistical analysis was performed using unpaired Student’s t-test. e RT−qPCR analysis of adipogenic genes, including AP2, adiponectin, Plin, adipsin and Lpl in RFP-depleted 3T3-L1 cells compared with controls. n = 12. Statistical analysis was performed using one-way ANOVA with post hoc Dunnett’s T3 test. All data are presented as mean ± s.e.m.\n\nFigure 8: Figure 8. a, b Effect of RFP knockdown (a) or overexpression (b) on AP2 promoter activity in 3T3-L1 cells. n = 8. Statistical analysis was performed using one-way ANOVA with post hoc Dunnett’s T3 test. c, d Immunoprecipitation (IP) experiments in HEK293T cells expressing Flag−RFP and HA−PPAR-γ reveal robust protein−protein interactions, which were further confirmed by reciprocal immunoprecipitation. IP with anti-HA followed by immunoblotting with anti-Flag confirmed the interaction (c), while IP with anti-Flag followed by detection with anti-HA yielded consistent results (d). e In situ PLA in differentiated 3T3-L1 adipocytes. Scale bar, 20 μm. f, g The effect of RFP knockdown (f) or overexpression (g) on PPAR-γ binding to PPRE in 3T3-L1 cells. h The electrophoretic mobility shift assay demonstrates that RFP promotes PPAR-γ binding to PPRE sequences within the AP2 promoter. i A Schematic diagram showing that the metabolic improvements observed in RFP-deficient mice under HFD conditions result from attenuated PPAR-γ-dependent adipogenic programming. Panel i was created with BioRender.com. All data are presented as mean ± s.e.m."
      }
    ]
  },
  {
    "id": "PMC12550973_multi",
    "image": [
      "images/PMC12550973-f1.png",
      "images/PMC12550973-f2.png",
      "images/PMC12550973-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Newborn Screening of X-Linked Adrenoleukodystrophy in Italy: Clinical and Biochemical Outcomes from a 4-Year Pilot Study\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. X-ALD healthy plate for complementary feeding. Allowed protein-rich foods according to C26:0 and total fatty acids content: Meat alternatives (beef lean cuts, chicken meat without skin, horse meat, ham (cooked and raw) with fat completely trimmed, turkey breast, pork meat lean cuts); Fish alternatives (flat fish, flounder, monkfish, octopus, perch, pike, sole, squid and cuttlefish (no tentacles), seabream, turbot, tuna fish canned natural); Egg white; Legumes (lentils peeled, white beans peeled, tofu); Milk-derived products (cottage cheese 1% fat, yogurt from skimmed milk plain 0% fat, skimmed milk 0% fat).\n\nFigure 2: Figure 2. Plasma C26:0-LPC concentration trends in patients undergoing clinical follow-up. C26:0-LPC concentrations over time. Note the initial decline in the first six months, followed by stabilization. Red lines indicate the start of dietary treatment, which did not normalize metabolite levels. Legend: Pt = patient, mo = months, 1TT = first-tier test, 2TT = second-tier test, LPC = lysophosphatidylcholine.\n\nFigure 3: Figure 3. Box and whisker plots illustrating neonatal C26:0-LPC concentrations. Data are presented for male and female ABCD1 variant carriers and ZSD patients. Legend: ALD = adrenoleukodystrophy, ZSDs = Zellweger Spectrum Disorders, 1TT = first-tier test, 2TT = second-tier test, LPC = lysophosphatidylcholine."
      }
    ]
  },
  {
    "id": "PMC12561199_multi",
    "image": [
      "images/PMC12561199-f1.png",
      "images/PMC12561199-f2.png",
      "images/PMC12561199-f3.png",
      "images/PMC12561199-f4.png",
      "images/PMC12561199-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Acidosis Forces Fatty Acid Uptake and Metabolism in Cancer Cells Regardless of Genotype\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Extracellular pHe determines the extent of fatty acid (FA) uptake. A) Normalised quantification of 14C FA uptake during stepwise medium acidification in SiHa cells (vs maintaining stable pHe) for palmitic acid (PA) (left graph) and docosahexaenoic acid (DHA) (right graph) (N = 3, n = 1). B,C) Representative pictures B) and quantification C) of ORO‐stained lipid droplets (LD) in SiHa cells maintained at pHe 7.4 (7.4 > 7.4) or shifted to pHe 6.5 (7.4 > 6.5) upon supplementation for 24 h with the indicated concentration ranges of PA or DHA (N = 3, n = 5 fields). D) Schematic protocol of pHe swap in cancer cells maintained at physiological pHe (7.4) or chronically adapted to acidic pHe (6.5). E) Time‐course quantification of LD accumulation (expressed as a ratio to LD content at time 0) in SiHa performed using Nanolive imaging after supplementation with 25 µm DHA or FA‐free BSA as vehicle (N = 1, n = 2). α = early phase slope values (i.e., before the plateau). F,G) Representative end‐point pictures F) and quantification G) of LD in SiHa cells maintained at the indicated pHe (7.4 > 7.4 and 6.5 > 6.5) or following pHe swapping (7.4 > 6.5 and 6.5 > 7.4) and supplemented with 50 µm DHA or FA‐free BSA as vehicle (N = 2, n = 10 fields). H) Quantification of BODIPY‐stained LD in SiHa cells maintained in 7.4 (7.4 > 7.4) or shifted in 6.5 (7.4 > 6.5) upon supplementation for 6 h with DHA and coupled with FA transporter inhibitors (2 µg mL−1 JC63.1, 10 µm SSO, 2 µm FATP1i, 2 µm FATP2i) or DMSO as vehicle (N = 3, n = 5). I,J) Representative pictures I) and quantification J) of ORO‐stained LD in SiHa cells exposed to the indicated pHe and supplemented with 50 µm DHA or FA‐free BSA as vehicle (N = 2, n = 5 fields). K,L) Representative pictures K) and quantification L) of pHi in HCT116 cells transduced with a ratiometric pH‐sensitive protein (pHluorin2) and exposed for 160 min to 50 µM DHA or FA‐free BSA as vehicle (N = 3, n = 1). M. HPLC‐MS quantification of DHA esterified in phospholipids from SiHa cells maintained at 7.4 (7.4 > 7.4) or shifted to 6.5 (7.4 > 6.5) and supplemented with 50 µm DHA or Methyl‐DHA for 24 h (N = 3, n = 1). All scale bars: 10 µm. Vehicles consist of an equivalent concentration of FA‐free BSA for DHA or DMSO for the drugs. Graphs are presented as mean ± SEM (A, C, J, L), min to max whisker plots, range = Q1 to Q3, and line = median G,H) or mean ± SD (M). N = biological replicates, and n = technical replicates. ns = non‐significant; ***p < 0.001. Significance was determined by two‐way ANOVA with Tukey's multiple comparison test. The p‐values reported for A and C refer to the column factor, whereas those in L indicate the differences between the final points of the kinetics.\n\nFigure 2: Figure 2. Extracellular acidification by hypoxia or stimulated glycolysis enhances DHA uptake across cancer cell types. A) Schematic protocol for inducing hypoxia (1% O2) in cancer cells cultured in either non‐buffered or buffered bicarbonate buffer, resulting in spontaneous medium acidification or preventing pHe drop, respectively. B,C) Representative pictures B) and quantification C) of ORO‐stained LD in SiHa and HCT116 cells supplemented with 25 µm DHA or FA‐free BSA as vehicle in the indicated conditions (N = 2, n = 10 fields). D) Schematic protocol for reducing or increasing pHe using MPC inhibitor 7ACC2, and PDK inhibitor DCA, respectively. E,F) Representative pictures E) and quantification F) of ORO‐stained LD in SiHa and HCT116 cells supplemented with 25 µm DHA or FA‐free BSA as vehicle after the indicated pharmacological treatments (DMSO as vehicle) (N = 2, n = 10 fields). All scale bars: 10 µm. The vehicle consists of an equivalent concentration of FA‐free BSA for DHA and DMSO for drugs. All graphs are presented as min‐max whisker plots, with the range indicated by Q1 to Q3, and the line representing the median. N = biological replicates, and n = technical replicates. ns = non‐significant; ***p < 0.001. Significance was determined by two‐way ANOVA with Tukey's multiple comparison test.\n\nFigure 3: Figure 3. Enhanced DHA uptake under acidosis sensitizes cancer cells to peroxisomal inhibition. SiHa cells maintained at the indicated pHe (7.4 > 7.4 and 6.5 > 6.5) or following pHe swapping (7.4 > 6.5 and 6.5 > 7.4) were supplemented with 50 µm DHA or FA‐free BSA as vehicle, and treated as indicated. A) Effects of DGAT1 inhibition (15 µm A922500 vs DMSO, 72 h) in the different pHe conditions (N = 3, n = 6). B) Quantification of membrane fluidity in SiHa cells exposed for 48 h to 15 µm DGAT1i (or DMSO as vehicle); Generalized polarization (GP) was calculated for both plasma and endo‐membranes (n = 30 independent cells). C,D) Representative pictures of the Hyper3 oxidized and reduced forms in transduced SiHa cells maintained at acid pH 6.5 C) and quantification of Ex488/Ex405 Ratio (reflecting H2O2 production) normalised to control in SiHa cells exposed for 48 h to 15 µm DGAT1i (or DMSO as vehicle) in each pHe condition (N = 2, n = 10 fields) D). E) Effects of ACOX1 inhibition (60 µm tricosadiynoic acid vs DMSO, 24 h) in the different pHe conditions during supplementation with 50 µm DHA, C22:1, or FA‐free BSA as vehicle (N = 3, n = 6). F,G) Representative pictures F) and quantification G) of ORO‐stained LD in SiHa cells undergoing the indicated pHe changes and exposed to 30 µm ACOX1i for 48 h (N = 2, n = 10 fields). H–J) HPLC‐MS quantification of DHA or C22:1 esterified in TG H) and in Phospholipids I), or their β‐oxidation intermediates J) from SiHa cells maintained at 7.4 (7.4 > 7.4) or shifted to 6.5 (7.4 > 6.5) and supplemented with 50 µm DHA or C22:1 and treated with 7.5 µm DGAT1i or 15 µm ACOX1i (DMSO as vehicle) during 24 h (N = 3, n = 1). All scale bars: 10 µm. The vehicle consists of an equivalent concentration of FA‐free BSA for DHA or DMSO for drugs. Graphs are presented as mean ± SD A,E,H,I,J) or min to max whisker plots, range = Q1 to Q3, and line = median B,D,G). bdl = below detection limit. N = biological replicates, and n = technical replicates. ns = non‐significant; ***p < 0.001. Significance was determined by two‐way ANOVA with Tukey's multiple comparison test.\n\nFigure 4: Figure 4. DHA and ACOX1i combination induce apoptosis without triggering ferroptosis. SiHa and HCT116 cells maintained at acidic pHe 6.5 were supplemented with 50 µm DHA or FA‐free BSA as vehicle, and treated as indicated. A) Representative flow cytometry plots depicting 7‐AAD versus FITC‐Annexin V staining of pH6.5‐adapted SiHa and HCT116 cells treated for 8 h with 60 µm ACOX1i (DMSO as vehicle). B) Quantification of the cell number (%) in the 7‐AAD and Annexin V double‐positive quadrants (N = 3, n = 1). C) Effect of cell death inhibitors (30 µm Z‐VAD‐FMK for apoptosis or 30 µm Ferrostatin‐1 and 20 µm α‐tocopherol for ferroptosis) on the viability of SiHa and HCT116 cells exposed to 40 µM ACOX1i, or 5 µm RSL3 as positive control of ferroptosis (DMSO as vehicle) (N = 3, n = 6). D,E) Representative flow cytometry histograms D) and quantification E) of ROS in SiHa and HCT116 cells treated for 5 h with 60 µm ACOX1i (DMSO as vehicle), as determined using DCFDA (N = 4, n = 1). F) Live cell confocal microscopy assessment of ER morphology in SiHa upon exposure for 5 h to 60 µm ACOX1i (DMSO as vehicle), as determined using 1 µm ER‐tracker green reporter. G) Quantification of membrane fluidity (2 µm Laurdan) in SiHa cells exposed for 24 h to 15 µm ACOX1i (or DMSO as vehicle); Generalized polarization (GP) was calculated for ER membrane thanks to 1 µm ER‐tracker red staining (N = 3, n = 4). H,I) Representative pictures H) and quantification I) of nuclear CHOP immunofluorescence in fixed SiHa cells treated for 4 h with 60 µm ACOX1i (DMSO as vehicle) (n = 60 independent cells). J,K) RT‐qPCR of genes associated with UPR J) and immunoblotting of ubiquitinylated proteins K) in SiHa cells treated for 5 h with 60 µm ACOX1i (DMSO as vehicle) and 50 µm DHA treatments (FA‐free BSA as vehicle) (N = 6 for qPCR and N = 1 for Immunoblotting). All scale bars: 10 µm. Graphs are presented as mean ± SD B,C,E), mean ± SEM J), or min to max whisker plots, range = Q1 to Q3, and line = median G,I). N = biological replicates, and n = technical replicates. ns = non‐significant; ***p < 0.001. Significance was determined by one‐way ANOVA B,E,G,I,J) and two‐way ANOVA C) with Tukey's multiple comparison test.\n\nFigure 5: Figure 5. Acidosis‐inducing MPCi enhances the cytotoxic effects of DHA supplementation. Cancer cells, spheroids, and organoids were pre‐challenged with 10 µM 7ACC2 (DMSO as vehicle) to stimulate glycolysis and induce medium acidification and treated as indicated with ACOX1 inhibitor (tricosadiynoic acid) (DMSO as vehicle) and DHA (FA‐free BSA as vehicle). A) Effects of combining 75 µm DHA and ACOX1 inhibition (60 µm, 72 h) on the viability of SiHa and HCT116 cells under induced acidification (N = 3, n = 6). B,C) Representative pictures B) and quantification C) of ORO‐stained LD in SiHa and HCT116 cells under induced acidification and exposed to 50 µm DHA and 30 µm ACOX1i (N = 2, n = 10 fields). Scale bar: 10 µm. D) Effects of combining 75 µm DHA and DGAT1 inhibition (30 µm, 72 h) (DMSO as vehicle) on the viability of SiHa and HCT116 cells under induced acidification (N = 3, n = 6). E,F) Representative pictures E) and quantification F) of cytotoxic effects measured by Cytotox Green Reagent of combining 100 µm DHA and 60 µm ACOX1i in HCT116 spheroids under induced acidification (N = 3). Scale bar: 300 µm. G,H) Representative pictures G) and quantification H) of cytotoxic effects of combining 50 µm DHA and 60 µm ACOX1i on colorectal cancer organoids under induced acidification (N = 18). Scale bar: 100 µm. Graphs are presented as mean ± SD A,D, H), mean ± SEM F), or min to max whisker plots, range = Q1 to Q3, and line = median C). N = biological replicates, and n = technical replicates. ns = non‐significant; ***p < 0.001. Significance was determined by two‐way ANOVA with Tukey's multiple comparison test."
      }
    ]
  },
  {
    "id": "PMC12624746_multi",
    "image": [
      "images/PMC12624746-f1.png",
      "images/PMC12624746-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Clinical, biochemical & molecular spectrum of adrenoleukodystrophy: A single centre experience\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. ROC curve for cut-off values of very long chain fatty acids for the identification of ALD. (A) At cut-off values of 0.69, C20:0 LPC was found to have a sensitivity of 66 per cent and specificity of 98 per cent. (B) At cut-off value of 0.8, C22:0 LPC was found to have a sensitivity of 66 per cent and specificity of 100 per cent. (C) At cut-off values of 0.907 C24:0 LPC was found to have a sensitivity and specificity of 100 per cent each. (D) At cut-off values of 0.604 (µmol/L) C26:0 LPC was found to have a sensitivity and specificity of 100 per cent.\n\nFigure 2: Figure 2. Electropherogram of a novel mutation c.493_494 [ins CAC]; p.165Pro; identified in a study participant with adrenomyeloneuropathy. The insertion of 3 nucleotides CAC results in generation of one extra protein i.e., Proline."
      }
    ]
  },
  {
    "id": "PMC12631431_multi",
    "image": [
      "images/PMC12631431-f1.png",
      "images/PMC12631431-f2.png",
      "images/PMC12631431-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Case Report: D-bifunctional protein deficiency caused by novel compound heterozygote HSD17B4 variants in a neonate in China\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Diagram outlining clinical events, diagnostics, and treatments of the patient.\n\nFigure 2: Figure 2. Sanger sequencing validation of HSD17B4 variants identified by whole-genome sequencing in the family. (A) Proband carries both variants of c.1145G>A(p.Gly382Asp) and c.1193C>G(p.Ser398*). (B) The father carries c.1145G>A(p.Gly382Asp). (C) The mother carries c.1193C>G(p.Ser398*).\n\nFigure 3: Figure 3. Brain magnetic resonance imaging (MRI) images on the patient’s 51st day of life. (A) T2-weighted imaging (T2WI) showing symmetrical bilateral cerebral hemispheres with normal gray and white matter signal intensities. (B) T1-weighted imaging (T1WI) showing high signal intensity in the posterior limb of the internal capsule and the cavum septum pellucidum. (C) Diffusion-weighted imaging (DWI) showing no obvious abnormal signal. (D) Fluid-attenuated inversion recovery (FLAIR) sequence showing the corpus callosum genu and body with normal morphology."
      }
    ]
  },
  {
    "id": "PMC12651281_multi",
    "image": [
      "images/PMC12651281-f1.png",
      "images/PMC12651281-f2.png",
      "images/PMC12651281-f3.png",
      "images/PMC12651281-f4.png",
      "images/PMC12651281-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Maximizing Diagnostic Yield in Intellectual Disability Through Exome Sequencing: Genotype–Phenotype Insights in a Vietnamese Cohort\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Workflow of genetic testing for patients with intellectual disability (ID) and/or autism spectrum disorder (ASD): Patients meeting the inclusion and exclusion criteria for ID/ASD underwent a stepwise diagnostic workflow. Tier 1 (blue): Cytogenetic and targeted testing, including karyotype analysis and FMR1 CGG repeat expansion testing to detect Fragile X syndrome and gray-zone alleles. Tier 2 (green): Exome-based sequencing, using either whole-exome sequencing (WES) or clinical exome sequencing (CES), with detected variants assessed for pathogenicity. Tier 3 (orange): Confirmation and reporting, in which pathogenic or likely pathogenic variants were validated using orthogonal methods—Sanger sequencing for SNVs/indels and CNVs—followed by interpretation according to ACMG/AMP/ClinGen guidelines and clinical correlation with genetic counseling. For patients with negative findings, re-analysis or additional testing (e.g., chromosomal microarray, methylation analysis, trio sequencing, or long-read sequencing) was recommended.\n\nFigure 2: Figure 2. The frequency distribution of gene mutations categorized by case confirmation, zygosity, mutation type, and inheritance pattern. (A) Mutation frequency by case confirmation: red represents confirmed cases, while light blue represents unconfirmed cases. (B) Mutation distribution by zygosity: red for heterozygous (HET), green for hemizygous (HEM), and purple for homozygous (HOM). (C) Mutation classification by type: brown for frameshift, red for missense, green for nonsense, blue for splice acceptor, and orange for synonymous mutations. (D) Mutation distribution by inheritance pattern: red for autosomal dominant (AD), light blue for autosomal recessive (AR), purple for X-linked recessive (XLR), rose for mixed inheritance patterns (AD, AR), and grey for no information.\n\nFigure 3: Figure 3. The Venn diagram visually represents the overlap of clinical phenotypes among different genetic conditions. Orange: neurological features (e.g., seizures, hypotonia, spasticity). Blue: motor development issues (e.g., loss of ambulation, fine motor impairment). Green: intellectual disability (mild to severe cognitive impairment). Yellow: dysmorphism (distinct facial or skeletal anomalies).\n\nFigure 4: Figure 4. (Left) Hierarchical Cluster Analysis (HCA) of Clinical Severity Scores. Dendrogram representing hierarchical cluster analysis (HCA) based on standardized clinical severity scores across 15 domains. Each branch corresponds to an individual patient, and the height of linkage reflects Euclidean distance between multivariate score profiles. Three major clusters were identified, indicating distinct phenotypic patterns among patients. (Right) Distribution of Clinical Severity Scores Across HCA Clusters: Box plots showing the distribution of semi-quantitative clinical severity scores (1–4) for each phenotypic domain, stratified by hierarchical cluster group (1–3) derived from HCA. Each dot represents an individual patient score.\n\nFigure 5: Figure 5. Integrated Heatmap of Clinical Severity, Pathway, and Diagnostic Features. Heatmap integrating z-scored clinical severity profiles (rows) and individual patient data (columns), annotated by cluster assignment, sex, clinical diagnosis, and molecular pathway. Hierarchical clustering was performed on both axes (Euclidean distance, Ward’s linkage) to visualize phenotypic co-variation and potential genotype–phenotype convergence. The color scale represents standardized z-scores of severity (from low [white] to high [red]), while side bars denote categorical annotations for each patient."
      }
    ]
  },
  {
    "id": "PMC12651281_multi_2",
    "image": [
      "images/PMC12651281-f6.png",
      "images/PMC12651281-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Maximizing Diagnostic Yield in Intellectual Disability Through Exome Sequencing: Genotype–Phenotype Insights in a Vietnamese Cohort\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Correlation Matrix of Clinical Severity Domains (R with p-values). Heatmap illustrating pairwise Pearson correlation coefficients (R) among clinical severity domains, with overlaid p-values. Red shades indicate positive correlations, blue shades indicate negative correlations, and color intensity corresponds to the correlation strength. Hierarchical clustering was applied to both axes to identify co-varying clinical features.\n\nFigure 7: Figure 7. The three-generation pedigree of proband CNV8 (III.6, index). Data highlight that two aunts (II.1 and II.6) and two siblings (III.5 and III.6) display intellectual disabilities along with distinct facial features, such as ptosis. Notably, both aunt II.1 and sibling III.6 possess the del(9)(q31.1-q31.3) variant, while their parents (II.2 & II.3; I.1 & I.2) show normal CNV and karyotype results. This indicates the possibility of a cryptic balanced rearrangement among other healthy members. Therefore, a prenatal diagnostic test was performed in the fetus (III.7) and no CNV or karyotype abnormality was detected. The black-filled symbols indicate affected individuals, and the arrows point to the patients who were clinically examined."
      }
    ]
  },
  {
    "id": "PMC12697678_multi",
    "image": [
      "images/PMC12697678-f1.png",
      "images/PMC12697678-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Synthesis of stable isotope labeled analogs of phytanic acid for separate and combined tracing of alpha-, beta- and omega-oxidation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Synthetic route to phytanic acid and 2,3,6,7,10,11,14,15-d8-phytanic acid.\n\nFigure 2: Figure 2. Synthetic route to 1,2-13C2-phytanic acid and 1,2-13C2-2,3,6,7,10,11,14,15-d8-phytanic acid."
      }
    ]
  },
  {
    "id": "PMC12715182_multi",
    "image": [
      "images/PMC12715182-f1.png",
      "images/PMC12715182-f2.png",
      "images/PMC12715182-f3.png",
      "images/PMC12715182-f4.png",
      "images/PMC12715182-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Balancing rice blast resistance and growth through suppression of the E3 ubiquitin ligase OsRING80\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. DEP2 controls rice grain size and negatively regulates rice immunity against M. oryzae. A and B) Gross morphology (A) and panicle morphology (B) of Kit and dep2 at the heading stage. Kit, Kitaake. C and D) Comparison of the grain length between the Kit plants and dep2 mutant. E to G) Phenotypes of leaves from 6-wk-old dep2 mutant inoculated with the compatible M. oryzae isolate RB22 (E), relative fungal biomass, as determined by RT-qPCR (F), and the relative lesion area, as measured using ImageJ (G). Bars: 1 cm. H to J) Phenotypes of leaves from 6-wk-old dep2-2 mutant inoculated with the compatible M. oryzae isolate RB22 (H), relative fungal biomass, as determined by RT-qPCR (I), and the relative lesion area, as measured using ImageJ (J). Bars: 1 cm. K) Chitin-induced ROS bursts in NPB and dep2-2 leaves. ROS, reactive oxygen species. L and M) Relative transcript levels of the defense-related genes OsPR1a (L) and OsWRKY45 (M) in dep2-2 mutant. Data shown as means ± SD (n = 12, 3, 6, 3, 6, 3, 3, and 3 in D, F, G, I, J, K, L, and M, respectively). Asterisks represent statistically significant differences between the samples (**P < 0.01 by a Student's t-test).\n\nFigure 2: Figure 2. DEP2 interacts with and is ubiquitinated by OsRING80. A) Y2H assay showing the interaction between DEP2 and OsRING80. DDO (double dropout supplements: SD-Leu/-Trp), QDO (quadruple dropout supplements: SD-Ade/-His/-Leu/-Trp). NT, N terminal; CT, C terminal. B) Pull-down assay to detect the interaction of DEP2 and OsRING80. MBP was used as negative control. Red arrowheads indicate the expected proteins. MBP, maltose-binding protein; GST, glutathione S-transferase. C) BiFC assay to test the interaction between DEP2 and OsRING80 in N. benthamiana leaves. Bars: 20 μm. D) Co-IP assay to test the interaction between DEP2 and OsRING80 in N. benthamiana leaves. Total protein was extracted from N. benthamiana leaves transfected with the indicated constructs. Red arrowheads indicate the expected proteins. E) OsRING80 promotes the degradation of DEP2 via the 26S proteasome pathway in N. benthamiana. DEP2-Flag was co-expressed with OsRING80-GFP and OsRING80 (H71Y)-GFP in N. benthamiana. Tissues were harvested 2 days after infiltration. The 26S proteasome inhibitor MG132 (50 μM) was infiltrated into the tissues at 24 h before sampling, with DMSO used as a control.\n\nFigure 3: Figure 3. OsRING80 negatively regulates rice immunity against M. oryzae. A) Phenotypes of the leaves from 6-wk-old osring80 mutant inoculated with the compatible M. oryzae isolate RB22. Bars: 1 cm. B) Relative lesion area in NPB and osring80 mutant after punch inoculation with M. oryzae isolate RB22. C) Relative fungal biomass in NPB and osring80 mutant after punch inoculation with M. oryzae isolate RB22. D) Chitin-induced ROS bursts in NPB and osring80 leaves. ROS, reactive oxygen species. E and F) Relative transcript levels of the defense-related genes OsPR1a (E) and OsWRKY45 (F) in osring80 mutant plants. G) The relative expression level of OsRING80 in the Kit and dep2 lines as determined by RT-qPCR. H) The relative expression level of OsRING80 in the NPB and dep2-2 lines. I) The relative expression level of OsRING80 in the Kit and dep2 rice protoplast. J) The relative expression level of OsRING80 in the NPB and dep2-2 rice protoplast. Data shown as means ± SD (n = 6, 3, 3, 3, 3, 3, 3, 3, and 3 in B, C, D, E, F, G, H, I, and J, respectively). Asterisks represent statistically significant differences between the samples (**P < 0.01 by a Student's t-test).\n\nFigure 4: Figure 4. Major agronomic traits measured in osring80 mutant lines. A) Gross morphology of osring80 mutant and NPB plants at the tillering stage. B) Gross morphology of osring80 mutant and NPB plants at the heading stage. C to H) Major agronomic traits measured: plant height (C), effective tiller number (D), spike length (E), grain number per panicle (F), seed setting rate (G), and 1,000-grain weight (H). Data shown as means ± SD (n = 10, 12, 20, 20, 16, and 23 in C to H, respectively). “ns” indicates no statistical significance at P > 0.05 according to Student's t-test.\n\nFigure 5: Figure 5. A proposed working model for the role of OsRING80 in balancing plant defense and growth. OsRING80 expression is induced by M. oryzae, while DEP2 expression is slightly suppressed. DEP2 is ubiquitinated and degraded by the E3 ligase OsRING80 through the 26S proteasome system. At the same time, DEP2 maybe feedback regulates OsRING80. OsRING80 can balance plant growth and defense response."
      }
    ]
  },
  {
    "id": "PMC12716710_multi",
    "image": [
      "images/PMC12716710-f1.png",
      "images/PMC12716710-f2.png",
      "images/PMC12716710-f3.png",
      "images/PMC12716710-f4.png",
      "images/PMC12716710-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Aging-related peroxisomal dysregulation disrupts intestinal stem cell differentiation through alterations of very long-chain fatty acid oxidation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) The model of ISC lineages in young and old Drosophila. The ISC (Dl+ and esg+) in young Drosophila produces a new ISC and differentiates into a precursor enteroblast (EB; esg+). The post-mitotic EB further differentiates into pre-enterocyte (preEC; esg+ and Pdm1+), and then differentiates into a mature enterocyte (ECs; Pdm1+). In aged ISCs, it differentiates into preEC, and weakly continues to differentiate into mature ECs. (B) A model illustrating chemical administration with esg-GFP Drosophila reporter line. The chemicals were fed to Drosophila on the 20th day after eclosion. After administration for 20 days, Drosophila were dissected for analysis. (C) Immunofluorescence images of midguts with or without Aspirin treatment. White arrows indicate preEC. (D, E) Quantification of the ration of esg+ cells (including ISC and EB cells) and preECs (esg-GFP+, Pdm1+cells) in midguts with indicated treatments. (F) Quantification of the deposits in indicated treatment. Excretions are quantified in 21 fields for each group of Drosophila. (G) Quantification of the ration of “Homeostasis” with or without Aspirin supplementation. (H) Quantification of the percentage of “Smurf” flies with or without Aspirin supplementation after consuming a non-absorbed food dye. Each sample contains three independent experiments. (I) Survival of female W1118 Drosophila with and without supplementation of Aspirin after eclosion for 20 days. Each treatment consisted of 50 mated females and the experiment was repeated three times independently. (J) The model of mouse intestinal organoid culture. (K, L) Representative images, and the quantification of organoid budding and forming ability of young and aged organoids in the presence or absence of Aspirin treatment. (M) Real-time qPCR analysis demonstrated that old mouse organoids treated with Aspirin enhanced the ability of aged ISC differentiation. (N) Representative images of hematoxylin and eosin (H&E) staining in paraffin-embedded mouse colon sections from young mice, aged mice, and aged mice with Aspirin treatment. (O) Average height and width of the crypts in colons from young mice, aged mice, and aged mice with Aspirin treatment. DAPI-stained nuclei (blue). Scale bars represent 10 µm (C), 20 µm (K), 40 µm (N). Error bars represent SDs. Student’s t-tests, Kruskal–Wallis test, one-way ANOVA, and log-rank test, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, and NS (non-significant) represents p > 0.05. Underlying data and statistical analysis in S1 Data.\n\nFigure 2: Figure 2. (A–C) Enrichment plot for transcriptional signature in old Drosophila midgut with or without Aspirin treatment. (D) Immunofluorescence images showed the abundance of peroxisomes in aged ISCs (as indicated by esg-GFP). The peroxisomes were labeled by mCherry (red). (E) The quantification of peroxisomes in (D). (F) Measurement of Catalase activity with sorted esg-GFP cells from young and aged Drosophila. n indicates three independent experiments. (G) Western blotting result of PMP70 in human normal para-carcinoma colon. Loading controls, α-Tubulin. (H, I) Immunofluorescence of PMP70 staining in young and aged human colons. Young and aged Normal para-carcinoma colons were collected. The boxed areas indicate crypts. (J, K) TEM from the mouse colon crypt. The green dashed lines: ISC; Pex, peroxisomes; Mito: mitochondrion. (L) The Catalase expression in intestinal crypts from young and aged human colons. Young and aged Normal para-carcinoma colons were collected. The boxed areas indicate crypts. (M, N) Immunofluorescence of PMP70 staining (red) in mouse intestinal crypts with or without Aspirin treatment. The boxed areas indicate crypts. (O, P) Immunofluorescence and statistical analysis of Catalase (green) in mouse intestinal crypts with or without Aspirin treatment. The boxed areas indicate crypts. DAPI-stained nuclei (blue). Scale bars represent 10 µm (D), 40 µm (H, L), 500 nm (K), 25 µm (M, P). Error bars represent SDs. Student’s t tests, Mann–Whitney test, and one-way ANOVA, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, and NS (non-significant) represents p > 0.05. Underlying data and statistical analysis in S2 Data.\n\nFigure 3: Figure 3. (A, B) The RNA-seq reveals that Aspirin can up-regulate peroxisome-related genes in aged fruit flies, especially increasing the expression of genes associated with PEX5-mediated peroxisomal matrix protein transportation. (C) The model of peroxisomal matrix protein transportation. (D) Real-time qPCR analysis conducted on sorted ISCs of Drosophila further confirmed a significant increase in Pex5, following Aspirin administration. (E–G) Western Blots, Real-time qPCR, and immunohistochemistry all showed a significant decrease in PEX5 and an increase in PEX7 expression in the aged human colon. (H, I) Western Blots, Real-time qPCR showed a significant decrease of PEX5 and an increase of PEX7 expression in aged mouse crypts. (J) Western blot analysis indicated that ACOX1 decreased similarly to PEX5 by using isolated peroxisomes from young and old mouse crypts. (K, L) Immunofluorescence analyses showed that PEX5 decreased significantly in ISCs of aged Drosophila. esg-GFP-labeled ISCs. (M) The intensity of GFP-SKL per peroxisome was decreased dramatically in aged ISCs of Drosophila, while Aspirin treatment increased its intensity. (N–P) Aging mice treated with Aspirin displayed an increase in PEX5 levels in crypts. (Q, R) Colonic organoids from aging mice treated with Aspirin also displayed an increase in PEX5 levels. (S, T) The Principal component analysis (PCA) of the proteomics. The import of matrix proteins into the peroxisomal lumen via PTS1 was enhanced following Aspirin treatment in aged mice. DAPI-stained nuclei (blue). Scale bars represent 10 µm (G, K, M, O). Error bars represent SDs. Student’s t tests, Kruskal–Wallis test, and Mann–Whitney test, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, and NS (non-significant) represents p > 0.05. Underlying data and statistical analysis in S3 Data.\n\nFigure 4: Figure 4. (A) Knocking down Pex5 in ISCs resulted in peroxisome-related proteins (as indicated by GFP-SKL) dispersing throughout the entire cell. (B–E) PEX5 downregulation directly leads to peroxisomal impairment, as indicated by decreased expression of ACOX1 and Catalase expression after knocked down Pex5 in ISCs. (F) Pex5 RNAi in ISCs led to a significant increase of preECs in mimic aging condition, which indicated as 29 °C for 20 days, while the control flies showed no differentiation defect. Aspirin treatment (for 7 days) did not rescue the ISC differentiation defect. (G) Quantification of the ratio of esg+ cells (including ISC and EB cells) and preECs (esg-GFP+, Pdm1+cells) in midguts as indicated genotypes. (H–K) The digestive functions of Pex5 RNAi flies declined, including excretion, and gastrointestinal acid–base homeostasis. Aspirin treatment (for 7 days) did not rescue the digestive functions of Pex5 RNAi flies. DAPI-stained nuclei (blue). Scale bars represent 10 µm (A, B, E, F). Error bars represent SDs. Student’s t tests, Mann–Whitney test, Kruskal–Wallis test, and one-way ANOVA, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, and NS (non-significant) represents p > 0.05. Underlying data and statistical analysis in S4 Data.\n\nFigure 5: Figure 5. (A, B) Overexpression of PEX5 started at intermediate age (40 days, 18 °C) significantly decreased age-associated preECs detain in aged midguts. (C, D) Overexpression of PEX5 started at intermediate age (40 days, 18 °C) significantly increased the intensity of GFP-SKL per peroxisome in aged ISCs. (E, F) Overexpression of PEX5 starting at an intermediate age significantly prevented further deterioration of gastrointestinal acid–base homeostasis and excretion in aged flies. (G, H) Overexpression of PEX5 improved the lifespan of flies, whereas knockdown of PEX5 resulted in a shortened lifespan. Each treatment consisted of 50 mated females, and the experiment was repeated three times independently. DAPI-stained nuclei (blue). Scale bars represent 10 µm (A, C). Error bars represent SDs. Student’s t tests, Mann–Whitney test, Kruskal–Wallis test, and log-rank test, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, and NS (non-significant) represents p > 0.05. Underlying data and statistical analysis in S5 Data."
      }
    ]
  },
  {
    "id": "PMC12716710_multi_2",
    "image": [
      "images/PMC12716710-f6.png",
      "images/PMC12716710-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Aging-related peroxisomal dysregulation disrupts intestinal stem cell differentiation through alterations of very long-chain fatty acid oxidation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Model of peroxisomal β-oxidation of VLCFAs. (B) The Principal component analysis (PCA) of free fatty acids. (C) Heatmap enrichment of quantified FFAs in indicated groups. (D, E) Bar charts and volcano plots show representative FFA levels in indicated groups. Error bars represent SDs. one-way ANOVA, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, and NS (non-significant) represents p > 0.05. Underlying data and statistical analysis in S6 Data.\n\nFigure 7: Figure 7. (A, B) Feeding flies with VLCFAs (Behenic acid, C22-0) significantly led to ISC differentiation defect. (C, D) Feeding old flies with Bezafibrate significantly relieved the ISC differentiation defect. (E, F) Inhibiting the degradation of VLCFAs in midguts of flies by ACOX1 RNAi led to the accumulation of progenitor cells and preECs under mimic aging conditions. (G, H) Knocking down of Elovl in ISC could inhibit ISC differentiation defects in aged midguts. (I, J) Treatment of young Drosophila with VLCFAs resulted in a decrease in SOX21A expression, while Bezafibrate treatment in old Drosophila led to an increase in SOX21A levels. (K, L) Enforced expression of either SOX21A or RAB7-CA in ISCs partially corrected the differentiation defects in ISCs in ACOX1 RNAi Drosophila, manifested by a reduction in the accumulation of preECs. (M, N) The overexpression of either SOX21A or RAB7-CA also ameliorated the differentiation deficiencies in ISC in Pex5 RNAi midguts. (O) The model of the current study. DAPI-stained nuclei (blue). Scale bars represent 10 µm (A, C, E, G, J, K, M). Error bars represent SDs. Student’s t tests, one-way ANOVA, Mann–Whitney test, and Kruskal–Wallis test, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, and NS (non-significant) represents p > 0.05. Underlying data and statistical analysis in S7 Data."
      }
    ]
  },
  {
    "id": "PMC12719848_multi",
    "image": [
      "images/PMC12719848-f1.png",
      "images/PMC12719848-f2.png",
      "images/PMC12719848-f3.png",
      "images/PMC12719848-f4.png",
      "images/PMC12719848-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"RING‐Type E3 Ligase OsRFPH2‐6 Ubiquitinates Nuclear Factor Y Subunit OsNF‐YA1 to Suppress Rice Immunity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. OsRFPH2‐6 negatively regulates rice blast resistance and chitin‐triggered immune responses. (a–c) OsRFPH2‐6‐OE lines exhibited attenuated blast resistance. Disease phenotype (a), lesion area (b) and relative in planta fungal growth (c) were analysed in representative OsRFPH2‐6‐OE and ZH11 leaves after inoculation with Magnaporthe oryzae. Bar = 0.2 cm. Leaf segments from 4‐week‐old OsRFPH2‐6‐OE and ZH11 plants were inoculated with 10 μL of spore suspension (5 × 105 spores/mL) of M. oryzae strain RB22, and disease phenotype was recorded at 5 days post‐inoculation. Leaf samples were collected for quantitative analysis of relative in planta fungal growth by quantitative PCR, with data shown as fold changes in M. oryzae MoPot2 levels relative to rice OsUbi. (d) Expression profiles of defence genes in OsRFPH2‐6‐OE and ZH11 plants with or without M. oryzae infection. Leaves of 3‐week‐old plants were sprayed with a spore suspension (2 × 105 spores/mL) of M. oryzae strain RB22 or an equal volume of 0.05% Tween 20 solution as a control. Leaf samples were collected at 48 h post‐inoculation. Rice 18S rRNA was used as an internal control for data normalisation. (e, f) Chitin‐triggered reactive oxygen species (ROS) burst (e) and expression of OsWRKY45 (f) in OsRFPH2‐6‐OE and ZH11 plants. Leaf discs from 3‐week‐old OsRFPH2‐6‐OE and ZH11 plants were treated with 100 μg/mL chitin or water as control. Chemiluminescent signals were immediately monitored. The results are presented as relative luminescence units (RLU) (e). Leaf samples were collected at the indicated time points after treatment for gene expression analysis. Rice 18S rRNA used as an internal control to normalise the data (f). RF26‐OE refers to OsRFPH2‐6‐OE. The experiments were independently conducted three times with similar results. Data are shown as mean ± SE from three independent experiments. ** in (b, c) represent significant differences at p < 0.01 (Student's t test), compared to ZH11, and different letters on the columns in (d, f) represent significant differences at the p < 0.05 level (one‐way ANOVA).\n\nFigure 2: Figure 2. OsRFPH2‐6 possesses E3 ligase activity that depends on conserved cysteines in the RING domain. (a) A structural diagram of OsRFPH2‐6, with RING and transmembrane domain (TM) indicated. Amino acid positions are presented above the diagram. (b) E3 ligase activity of OsRFPH2‐6. GST, glutathione S‐transferase; IB, immunoblot. (c) Functional importance of conserved cysteines in the RING domain of OsRFPH2‐6 for its E3 ligase activity. GST‐OsRFPH2‐6 and its cysteine‐to‐serine mutant variants (OsRFPH2‐6C101S, mutated at C101, OsRFPH2‐6C104S, mutated at C104, OsRFPH2‐6C120S, mutated at C120, OsRFPH2‐6C128S, mutated at C128, OsRFPH2‐6C140S, mutated at C140, and OsRFPH2‐6C143S, mutated at C143) were individually incubated with human E1, E2, and FLAG‐tagged ubiquitin at 30°C for 3 h. Ubiquitination and protein levels were analysed by immunoblotting with anti‐GST and anti‐FLAG antibodies. RF26 refers to OsRFPH2‐6. The experiments were independently conducted three times with similar results.\n\nFigure 3: Figure 3. OsRFPH2‐6 interacts with OsNF‐YA1. (a) Interactions of OsRFPH2‐6 with OsNF‐YA1 in yeast two‐hybrid (Y2H) assays. The indicated pairs of recombinant or empty pGBKT7 and pGADT7 plasmids were cotransformed into yeast strain Y2H Gold and grown on SD/−Trp/−Leu (DDO) and SD/−Trp/−Leu/−His/−Ade/X‐α‐gal/AbA (QDO/x‐α‐Gal) media at 30°C. The interaction was assessed based on the growth performance of yeast colonies at QDO/x‐α‐Gal medium. (b) Interactions of OsRFPH2‐6 with OsNF‐YA1 in luciferase complementation imaging assays. Agrobacteria carrying the indicated Nluc and Cluc recombinant plasmids were coinfiltrated into Nicotiana benthamiana leaves, and fluorescent signals were visualised 48 h post‐agroinfiltration. (c) Interaction of OsRFPH2‐6 with OsNF‐YA1 in glutathione S‐transferase pull‐down assays. GST‐OsRFPH2‐6 and GST protein were individually incubated with OsNF‐YA1‐HIS at 4°C for 3 h, followed by immunoprecipitation with GST resin. The immunoprecipitated proteins were detected by immunoblotting with anti‐GST and anti‐His antibodies. (d) Interactions of OsRFPH2‐6 with OsNF‐YA1 in bimolecular fluorescence complementation assays. Agrobacteria carrying indicated recombinant or empty p2YN and p2YC plasmids were coinfiltrated into N. benthamiana leaves expressing nucleus‐localised marker RFP‐H2B. YFP and RFP signals were visualised at 48 h post‐agroinfiltration. Bar = 20 μm. RF26 refers to OsRFPH2‐6; YA1 refers to OsNF‐YA1. The experiments were independently conducted three times with similar results.\n\nFigure 4: Figure 4. OsRFPH2‐6 ubiquitinates OsNF‐YA1 for degradation. (a) OsRFPH2‐6 ubiquitinates OsNF‐YA1 in in vitro ubiquitination assay. GST‐OsRFPH2‐6 or glutathione S‐transferase (GST) was incubated with OsNF‐YA1‐HIS in the presence of human E1, E2 and FLAG‐tagged ubiquitin. Ubiquitination and protein levels were analysed by immunoblotting using anti‐GST, anti‐His and anti‐FLAG antibodies. The red brackets indicate the ubiquitination bands of GST‐OsRFPH2‐6 and OsNF‐YA1‐HIS detected by anti‐GST and anti‐His antibodies, respectively. (b) OsRFPH2‐6‐GFP mediated the degradation of OsNF‐YA1‐HA in Nicotiana benthamiana leaves. OsRFPH2‐6‐GFP and OsNF‐YA1‐HA were transiently co‐expressed in N. benthamiana leaves, with or without treatment of 50 μM MG132 at 24 h post‐agroinfiltration. Total proteins were extracted at the indicated time points and analysed by immunoblotting with anti‐GFP, anti‐HA and anti‐actin antibodies. (c) OsRFPH2‐6 mediated the degradation of OsNF‐YA1‐HIS in cell‐free degradation assays. OsNF‐YA1 was incubated with total protein extracts from osrfph2‐6, OsRFPH2‐6‐OE and ZH11 plants, with or without 50 μM MG132 treatment. The protein levels of OsNF‐YA‐HIS were analysed by immunoblotting with anti‐His antibody. The band densities as grey values in (a, b and c) were calculated by using ImageJ software and normalised to the first lane values in the same protein. RF26 refers to OsRFPH2‐6; YA1 refers to OsNF‐YA1. The experiments were independently conducted three times with similar results.\n\nFigure 5: Figure 5. OsNF‐YA1 positively regulates rice immunity, blast resistance and chitin‐triggered immunity. (a–c) OsNF‐YA1 positively contributes to rice blast resistance. Disease phenotype (a), lesion area (b) and relative in planta fungal growth (c) in representative osnf‐ya1 and ZH11 leaves after inoculation with Magnaporthe oryzae . Bar = 0.2 cm. Leaf segments from 4‐week‐old osnf‐ya1 and ZH11 plants were inoculated with 10 μL spore suspension (5 × 105 spores/mL) of M. oryzae strain RB22. Disease phenotype was recorded at 5 days post‐inoculation, and leaf samples were collected for quantitative analysis of relative in planta fungal growth by quantitative PCR, shown as fold changes in M. oryzae MoPot2 levels with that of rice OsUbi. (d, e) Chitin‐triggered reactive oxygen species (ROS) burst (d) and the expression profile of OsWRKY45 (e) in osnf‐ya1 and ZH11 plants. Leaf discs from 3‐week‐old osnf‐ya1 and ZH11 plants were treated with 100 μg/mL chitin or water as control. Chemiluminescent signals were immediately monitored. Results are presented as relative luminescence units (RLU) (d). Leaf samples were collected at the indicated time points after treatment for gene expression analysis. Rice 18S rRNA used as an internal control to normalise the data (e). (f) MAPK activity in osnf‐ya1 and ZH11 plants with or without chitin treatment. Leaf fragments from 3‐week‐old plants were preincubated in double‐distilled water overnight, and then treated with 100 μg/mL chitin or double‐distilled water (mock). Total proteins were extracted at the indicated time points and detected by immunoblotting with antiphospho p44/p42‐ERK MAPK (anti‐pTEpY) and anti‐actin antibodies. ya1 refers to osnf‐ya1. The experiments were independently conducted three times with similar results. Data are shown as mean ± SE from three independent experiments. ** in (b, c) represent significant differences at p < 0.01 (Student's t test), compared to ZH11, and different letters on the columns in (e) represent significant differences at the p < 0.05 level (one‐way ANOVA)."
      }
    ]
  },
  {
    "id": "PMC12719848_multi_2",
    "image": [
      "images/PMC12719848-f6.png",
      "images/PMC12719848-f7.png",
      "images/PMC12719848-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"RING‐Type E3 Ligase OsRFPH2‐6 Ubiquitinates Nuclear Factor Y Subunit OsNF‐YA1 to Suppress Rice Immunity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Enriched GO terms of differentially expressed genes and heatmap of immune‐associated genes in osnf‐ya1 plants from RNA‐seq analysis. (a, b) Enriched GO terms for upregulated genes (a) and downregulated genes (b) in osnf‐ya1 plants compared with wild type ZH11 plants. (c, d) Heatmap visualisation of immune‐related genes derived from upregulated genes (c) and downregulated genes (d) in osnf‐ya1 plants compared with ZH11 plants.\n\nFigure 7: Figure 7. Expression profiles of selected immune‐associated genes from RNA‐seq analysis in osnf‐ya1 plants and wild type ZH11 plants with or without Magnaporthe oryzae infection. (a) Expression profiles of upregulated genes in osnf‐ya1 plants. (b) Expression changes of phenylpropanoid pathway‐related OsPAL5 and Os4CL1 in osnf‐ya1 plants. (c) Expression profiles of downregulated genes in osnf‐ya1 plants. Three‐week‐old plants were inoculated with a spore suspension (2 × 105 spores/mL) of M. oryzae strain RB22, or a 0.05% Tween 20 solution as mock control by foliar spraying. Leaf samples were collected at 48 h post‐inoculation for gene expression analysis. Rice 18S rRNA was used as an internal control to normalise the data. ya1 refers to osnf‐ya1. All experiments were independently conducted three times with similar results. Data are presented as mean ± SE from three independent experiments. Different letters indicate statistically significant differences at p < 0.05 (one‐way ANOVA).\n\nFigure 8: Figure 8. Proposed model for the ONAC083‐OsRFPH2‐6‐OsNF‐YA1 regulatory network in rice immunity. OsRFPH2‐6, an E3 ligase that negatively regulates rice immunity against Magnaporthe oryzae, is transcriptionally activated by ONAC083, a NAC transcription factor that also functions as a negative regulator of rice immunity to M. oryzae . Upon M. oryzae infection, ONAC083 expression is upregulated and subsequently activates OsRFPH2‐6 transcription by binding to the ACGCAA cis‐element in its promoter region. OsRFPH2‐6 then interacts with OsNF‐YA1, mediating its ubiquitination and subsequent degradation through the UPS pathway. This molecular cascade ultimately disrupts the positive regulatory role of OsNF‐YA1 in rice resistance to M. oryzae , thereby contributing to the negative regulation of rice immunity."
      }
    ]
  },
  {
    "id": "PMC12724674_multi",
    "image": [
      "images/PMC12724674-f1.png",
      "images/PMC12724674-f2.png",
      "images/PMC12724674-f3.png",
      "images/PMC12724674-f4.png",
      "images/PMC12724674-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"TRIM37 recognizes a bipartite degron to ubiquitinate centrosome substrates\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A) Western blot against HA-tagged ubiquitin from reconstituted ubiquitination reactions performed without or with TRIM37. B) Schematic of Cep192 domains indicating ubiquitinated residues identified by mass spectrometry. C) Graphic representation of beads used for immunoprecipitation assays. Green: GFP-Trap magnetic particles; blue: beads conjugated to TRIM37 antibody. D) Western blot showing TRIM37 binding to Cep192 constructs. Percentages below represent relative binding capacity normalized to full-length Cep192. E) Western blot against GFP showing Cep192 fragments that bind TRIM37. Percentages below represent binding capacity normalized to the Cep192 C-terminal fragment. F) Cep192 constructs expressed in DLD-1 cells. G) Western blot against GFP after pull-down of Cep192 constructs from DLD-1 cells. H) Western blot against HA-tagged ubiquitin from reconstituted ubiquitination reactions using the Cep192 constructs purified in panel G.\n\nFigure 2: Figure 2. A) Schematic of the construct degradation assay. GFP-Cep192 constructs localize to centrosomes and the cytoplasm after tetracycline-induced expression. After tetracycline washout, construct degradation is monitored; lighter color indicates higher protein abundance. B) Representative images showing degradation efficiency of each construct. C) Quantification of Cep192 foci per image (mean ± SEM; n ≥ 15 images per condition, 3 biological replicates) during expression (dark purple) and degradation (light purple) phases. P values from unpaired T-tests with Welch’s correction. D) Quantification of maximum fluorescence intensity of Cep192 foci (mean ± 95% CI; n > 90, 3 biological replicates) during expression (dark purple) and degradation (light purple) phases. P values from unpaired T-tests with Welch’s correction. E) Western blot against GFP showing total construct abundance under each condition. Tubulin detection was used as a loading control.\n\nFigure 3: Figure 3. A) Quantification of cell proliferation during expression of Cep192 constructs (mean ± 95% CI; n = 6 biological replicates). P values (day 6 viability) from one-way ANOVA followed by Dunnett’s multiple comparison test. B) Schematic showing the cell-synchronization timeline used before mitotic tracking. C) Representative images of cells in mitosis over time. Cells are outlined in white. Pie charts indicate the percentage of cells completing division within 110 min during imaging. D) Quantification of maximum fluorescence intensity of GFP-Cep192 constructs at mitotic centrosomes (median ± 95% CI; ≥ 50 centrosomes, 4 biological replicates). P values from Kruskal-Wallis test, followed by Dunn’s multiple comparison test.\n\nFigure 4: Figure 4. A) Diagram of EB1 constructs expressed in DLD-1 cells. B) Representative images showing EB1 constructs: (1) during tetracycline-induced expression, (2) after tetracycline withdrawal with siControl, and (3) after tetracycline withdrawal with siTRIM37. Cells are outlined in white. C) Quantification of cytoplasmic EB1-construct fluorescence under conditions described in (B) (median ± 95% CI; >35 cells, 2 biological replicates). P values from Kruskal-Wallis test, followed by Dunn’s multiple comparison test. D) Western blot against GFP showing total EB1-construct abundance under the conditions in (B).\n\nFigure 5: Figure 5. A) AlphaFold3 prediction of the IDR+ASH8 domain of Cep192. Side and top views shown. pTM = 0.68 for the whole domain; pTM = 0.86 for ASH8. B) Purified GFP-IDR+ASH8 was incubated with 30 nM TRIM37, then the complex was precipitated. The amount of TRIM37 remaining in the supernatant was measured to calculate the fraction of bound TRIM37 with each concentration of GFP-IDR+ASH8. Kd was determined from a one phase association fit (red line; R2 = 0.93). n = 2 biological replicates. Associated with Fig. S3B, C. C) Mass photometry of 20 nM GFP-IDR+ASH8. The data represent three biological replicates. D) DSSO crosslinking map of TRIM37 and IDR+ASH8. ASH8 is colored orange; intrinsically disordered regions are colored white. Cross-links: purple, intramolecular; green, intermolecular; red, intermolecular links between the same amino acid. n = 3 biological replicates, calculated FDR <1%. Associated with Fig. S3D. E) Model for how TRIM37 dimers recognize and ubiquitinate the C-terminus of Cep192."
      }
    ]
  },
  {
    "id": "PMC12731542_multi",
    "image": [
      "images/PMC12731542-f1.png",
      "images/PMC12731542-f2.png",
      "images/PMC12731542-f3.png",
      "images/PMC12731542-f4.png",
      "images/PMC12731542-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomes, PPARs, and Their Role in Macrophages\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Process of Peroxisome Biogenesis. There are three important stages that occur during the biogenesis of peroxisomes: the formation of the lipid membrane, the import of matrix proteins, and the subsequent enlargement of peroxisomes. The formation of the peroxisomal membrane begins with the fusion of pre-peroxisomal vesicles that originate from the mitochondria and the endoplasmic reticulum. Once budding takes place, peroxisomal membrane proteins are transported from free ribosomes. Matrix proteins synthesized on free ribosomes contain either peroxisomal targeting signals 1 or 2. Once these matrix proteins dock at the PEX13/PEX14 complex site, the peroxisomal targeting signals 1 and 2 are released. The process of peroxisome enlargement involves elongation, constriction, and fission. The resulting two asymmetric daughter peroxisomes then mature and become functional by importing additional matrix and membrane proteins. This process may lead to a re-entry into the membrane expansion phase of the cycle. Abbreviations: PEX (Peroxin), PMPs (Peroxisomal membrane proteins), PTS (Peroxisomal targeting signals), Mff (Mitochondrial fission factor), DLP1 (Dynamin-like protein 1), Fis1 (Mitochondrial fission protein 1). Created in BioRender. Wihadmadyatami, H. (2025) https://BioRender.com/dg41se9 (accessed on 10 December 2025).\n\nFigure 2: Figure 2. The Role of Peroxisomes. Peroxisomes are essential for fatty acid metabolism, especially in the initial breakdown of VLCFAs and BCFAs through α- and β-oxidation pathways. The shortened fatty acid chains are subsequently transferred to mitochondria for further oxidation and energy production. Additionally, peroxisomes are involved in the biosynthesis of plasmalogens and cholesterol, which are critical components for maintaining cellular membrane integrity and regulating signaling processes. In the regulation of lipid metabolism, peroxisomal ABCD transporters are critical for importing fatty acids into the peroxisome. Moreover, to maintain oxidative balance, peroxisomes generate antioxidative enzymes, such as Catalase, which plays a vital role in scavenging ROS and RNS. Abbreviations: FAR (Fatty acyl-CoA reductase), ABCD (ATP-binding cassette transporter subfamily D), VLCFA (Very Long Chain Fatty Acid), ATP (Adenosine triphosphate), CoASH (Coenzyme A), ACSL (Long-Chain Acyl-CoA Synthetase), PUFA (Polyunsaturated fatty acid), DHCA/THCA (Dihydroxycholestanoic acid/Trihydroxycholestanoic acid), AMARC (α-methylacyl-CoA racemase), PHYH (Phytanoyl-CoA Hydroxylase), AGPS (alkylglycerone phosphate synthase), DHAP (Dihydroxyacetone phosphate), GNPAT (Glyceronephosphate O-Acyltransferase), ACOX (Acyl-coenzyme A oxidase), MFP (MultiFunctional Protein), CAT (Catalase), PexRep (Peroxisomal Reductase Activating PPARγ), AGP (1-alkyl-2-lyso-sn-glycero-3-phosphate), LPA (Lysophosphatidic acid), HMG (Hydroxymethylglutaryl). Created in BioRender. Wihadmadyatami, H. (2025) https://BioRender.com/3vium8c (accessed on 10 December 2025).\n\nFigure 3: Figure 3. The Role of Peroxisomes and PPARs in Organ-Resident and Cultured Macrophages is Crucial for Disease Pathogenesis. Abbreviations: COPD (chronic obstructive pulmonary disease), X-ALD (X-linked adrenoleukodystrophy), HIV/AIDS (human immunodeficiency virus/Acquired Immune Deficiency Syndrome). Created in BioRender. Wihadmadyatami, H. (2025) https://BioRender.com/25pg3nj (accessed on 10 December 2025).\n\nFigure 4: Figure 4. The Role of Peroxisomes and PPARs in Macrophages. Abbreviations: PPARs (Peroxisome Proliferator-Activated Receptors), EPA (Eicosapentaenoic acid), DHA (Docosahexaenoic acid), ROS (Reactive Oxygen Species), RNS (Reactive Nitrogen Species). Created in BioRender. Wihadmadyatami, H. (2025) https://BioRender.com/5mrll4z (accessed on 10 December 2025).\n\nFigure 5: Figure 5. Role of Peroxisomes and PPARs in Anti-Inflammatory Macrophage. The activation of anti-inflammatory cytokines such as IL-10 can stimulate peroxisomes and PPARs, contributing to the resolution of inflammation in macrophages. IL-10 signaling in macrophages operates through the STAT3 transducer to activate PPARs, which in turn suppress NF-κB activity. Additionally, IL-10 signaling via STAT3 transducer is capable of directly inhibiting NF-κB activation. The suppression of NF-κB disrupts downstream signaling triggered by inflammatory stimuli such as LPS, IFN-γ, TNF-α, and PGE2, ultimately leading to reduced inflammatory responses. Furthermore, arachidonic acid is driven to produce increased levels of thromboxanes and PGD2, which serve as natural ligands for PPARs. The enhanced activation of PPARs ultimately promotes the transcription of genes involved in peroxisomal biogenesis, peroxisomal β-oxidation, and the production of peroxisomal antioxidative enzymes. This upregulation contributes to increased synthesis of DHA, which plays a role in supporting the resolution of inflammation. The elevated production of plasmalogens and cholesterol further strengthens cell membrane integrity, signaling, and antioxidant defenses. Efficient regulation of lipid metabolism by peroxisomes also helps prevent lipotoxicity. Moreover, the accumulation of antioxidative enzymes such as Catalase helps restore redox balance by reducing oxidative stress, thereby limiting lipid peroxidation. Abbreviations: IFN-γ (Interferon-γ), IFNGR (Interferon gamma Receptor), JAK-STAT (Janus Kinase-Signal Transducer and Activator of Transcription), LPS (Lipopolysaccharide), TLR4 (Toll-like receptor 4), MAPK (Mitogen-activated protein kinase), TNF-α (Tumor Necrosis Factor-α), TNFR1 (Tumor Necrosis Factor Receptor 1), NF-κB (Nuclear Factor kappa-light-chain-enhancer of activated B cells), PPARs (Peroxisome Proliferator-Activated Receptors), IL-10 (Interleukin-10), STAT3 (Signal Transducer and Activator of Transcription 3), COX2 (Cyclooxygenase-2), PGD2 (Prostaglandin D2), PGE2 (Prostaglandin E2), DHA (Docosahexaenoic acid), FAO (Fatty Acid Oxidation), ROS (Reactive Oxygen Species), RNS (Reactive Nitrogen Species). Created in BioRender. Wihadmadyatami, H. (2025) https://BioRender.com/n4kgirv (accessed on 10 December 2025)."
      }
    ]
  },
  {
    "id": "PMC12752160_multi",
    "image": [
      "images/PMC12752160-f1.png",
      "images/PMC12752160-f2.png",
      "images/PMC12752160-f3.png",
      "images/PMC12752160-f4.png",
      "images/PMC12752160-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MYB gene from Endocarpon pusillum regulates growth and development and enhances drought tolerance in creeping bentgrass (Agrostis stolonifera L.)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The bioinformatics analysis of EpMYB. Predicted domain of EpMYB protein (A), prediction of secondary structure of EpMYB protein (B), prediction of tertiary structure of EpMYB protein (C), and predicted signal peptide of EpMYB protein (D)\n\nFigure 2: Figure 2. Subcellular localization of EpMYB protein. Free YFP, control with empty vector. EpMYB-YFP, EpMYB-YFP fusion. The cell nucleus was stained by 4’, 6-diamidino-2-phenylindole (DAPI) to confirm the location of EpMYB protein in the nucleus. Bars = 25 μm\n\nFigure 3: Figure 3. Phenotypic characteristics and chlorophyll content of plants. A Wild-type (WT) plants and transgenic (TG) plants were grown in medium under the same conditions separately. B WT plants and TG plants were grown in soil (Nutrient soil: vermiculite: perlite = 1:1:1) separately and photographed after maturity. C The root of the representative WT and TG creeping bentgrass plants. The normal (D) and twisted leaf blades (E) of the representative WT and TG creeping bentgrass plants. F Phenotypes of a representative single tiller of creeping bentgrass plants from WT and TG lines. Statistical analysis of the differences in shoot fresh weight (G), root fresh weight (H), maximum leaf length (I), leaf number on a single tiller (J), Internode length (K), and chlorophyll content (L) between representative WT and TG plants. Data represent the average from three biological replicates. Data are means of three biological replicates ± standard deviation (SD). TG lines compared to WT, significant difference was indicated with asterisks (ns, *, **, *** or ****) at ns, P < 0.05, 0.01, 0.001 or 0.0001 by Student’s t-test\n\nFigure 4: Figure 4. Wax synthesis of the wild-type (WT) controls and EpMYB transgenic (TG) creeping bentgrass lines. Scanning electron microscope images of stomata of WT (A) and TG (B) leaves. C Relative expression of the wax synthesis gene MAH1 in WT and TG plants. MAH1, Midchain alkane hydroxylase. Data represent the average from four biological replicates. Data are means of three biological replicates ± standard deviation (SD). TG lines compared to WT, significant difference was indicated with asterisks (ns, *, **, *** or ****) at ns, P < 0.05, 0.01, 0.001 or 0.0001 by Student’s t-test\n\nFigure 5: Figure 5. Drought treatment of wild type (WT) and transgenic (TG) plants. Comparison of morphology of WT and TG plants under drought treatment at day 0 (A), day 19 (B). Fv/Fm (C), relative water content (D), and relative electrolytic leakage (E), were measured 0 and 19 days after drought treatment. Data represent the average from three biological replicates. Data are shown as means and the error bars indicate the standard deviation (± SD). TG lines compared to WT, significant difference was indicated with asterisks (ns, *, **, *** or ****) at ns, P < 0.05, 0.01, 0.001 or 0.0001 by Student’s t-test"
      }
    ]
  },
  {
    "id": "PMC12752160_multi_2",
    "image": [
      "images/PMC12752160-f6.png",
      "images/PMC12752160-f7.png",
      "images/PMC12752160-f8.png",
      "images/PMC12752160-f9.png",
      "images/PMC12752160-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MYB gene from Endocarpon pusillum regulates growth and development and enhances drought tolerance in creeping bentgrass (Agrostis stolonifera L.)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Physiological response to drought stress and molecular analysis of the wild-type (WT) controls and EpMYB transgenic (TG) creeping bentgrass lines. Physiological indexes of WT and TG plants were measured under drought treatment at day 0, day 10 and day 19, including peroxidase (POD) (A), Catalase (CAT) (B), malondialdehyde (MDA) (C), soluble protein (D). Data represent the average from three biological replicates. Data are shown as means and the error bars indicate the standard deviation (± SD). TG lines compared to WT, significant difference was indicated with asterisks (ns, *, **, *** or ****) at ns, P < 0.05, 0.01, 0.001 or 0.0001 by Student’s t-test\n\nFigure 7: Figure 7. Lignin of the wild-type (WT) controls and EpMYB transgenic (TG) creeping bentgrass lines. A Lignin content of the WT controls and TG plants. Data represent the average from three biological replicates. B Relative expression of the lignin synthesis gene HCT4 in WT and TG plants. HCT4, Hydroxycinnamoyltransferase 4. Data represent the average from four biological replicates. Data are shown as means and the error bars indicate the standard deviation (± SD). TG lines compared to WT, significant difference was indicated with asterisks (ns, *, **, *** or ****) at ns, P < 0.05, 0.01, 0.001 or 0.0001 by Student’s t-test\n\nFigure 8: Figure 8. Hormone content in the above-ground parts of wild type (WT) and transgenic (TG) plants. Auxin (IAA) content (A). Cytokinin isopentenyladenosine (IPA) content (B). Cytokinin trans-Zeatin-riboside (ZR) content (C). Gibberellin 3 (GA3) content (D). Brassinosteroid (BR) content (E). The unit is ng/g· FW. Data represent the average from three biological replicates. Data are shown as means and the error bars indicate the standard deviation (± SD). TG lines compared to WT, significant difference was indicated with asterisks (ns, *, **, *** or ****) at ns, P < 0.05, 0.01, 0.001 or 0.0001 by Student’s t-test\n\nFigure 9: Figure 9. Correlation plot and PCA scatter plot of 12 samples. A Correlation plot. B PCA scatter plot. The horizontal and vertical coordinates respectively represent the first and second principal components, and the numbers in parentheses indicate the contribution degrees of each principal component. The triangles represent the mean coordinates (center points) of each group, and the oval boxes indicate the confidence intervals. Different classification standards are distinguished by color. Group3, TG group. Group5, WT group. Group7, WT-D group. Group8, TG-D group. WT-D, Wild-type control after drought treatment; TG-D, The transgenic plants after drought treatment\n\nFigure 10: Figure 10. Global analysis of gene expression between wild type (WT) and transgenic (TG) plants. A The biological process analysis of Gene Ontology (GO) enrichment of the all annotated differentially expressed genes (DEGs) in TG-vs-WT group. B The cellular component analysis of GO enrichment of the all annotated DEGs in TG-vs-WT group. C The molecular function analysis of GO enrichment of the all annotated DEGs in TG-vs-WT group. TG-vs-WT, transgenic plants verse wild type plants. 20 most significant GO categories were selected according to the pvalue. D Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis of the annotated DEGs in TG-vs-WT group. TG-vs-WT, transgenic plants verse wild type plants. 20 most significant KEGG pathways were selected according to the qvalue"
      }
    ]
  },
  {
    "id": "PMC12752160_multi_3",
    "image": [
      "images/PMC12752160-f11.png",
      "images/PMC12752160-f12.png",
      "images/PMC12752160-f13.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"MYB gene from Endocarpon pusillum regulates growth and development and enhances drought tolerance in creeping bentgrass (Agrostis stolonifera L.)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Global analysis of gene expression between wild type (WT) and WT (Drought treatment). A The biological process analysis of Gene Ontology (GO) enrichment of the all annotated differentially expressed genes (DEGs) in WT (Drought treatment)-vs-WT group. B The cellular component analysis of GO enrichment of the all annotated DEGs in WT (Drought treatment)-vs-WT group. C The molecular function analysis of GO enrichment of the all annotated DEGs in WT (Drought treatment)-vs-WT group. WT (Drought treatment)-vs-WT, wild type plants (Drought treatment) verse wild type plants. 20 most significant GO categories were selected according to the pvalue. D Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis of the annotated DEGs in WT (Drought treatment)-vs-WT group. WT (Drought treatment)-vs-WT, wild type plants (Drought treatment) verse wild type plants. 20 most significant KEGG pathways were selected according to the qvalue\n\nFigure 12: Figure 12. Global analysis of gene expression between transgenic plant (TG) and TG (Drought treatment). A The biological process analysis of Gene Ontology (GO) enrichment of the all annotated differentially expressed genes (DEGs) in TG (Drought treatment)-vs-TG group. B The cellular component analysis of GO enrichment of the all annotated DEGs in TG (Drought treatment)-vs-TG group. C The molecular function analysis of GO enrichment of the all annotated DEGs in TG (Drought treatment)-vs-TG group. TG (Drought treatment)-vs-TG, transgenic plant (Drought treatment) verse transgenic plant. 20 most significant GO categories were selected according to the pvalue. D Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis of the annotated DEGs in TG (Drought treatment)-vs-TG group. TG (Drought treatment)-vs-TG, transgenic plant (Drought treatment) verse transgenic plant. 20 most significant KEGG pathways were selected according to the qvalue\n\nFigure 13: Figure 13. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway for differentially expressed genes (DEGs) in TG-vs-WT group. DEGs mapped to photosynthesis. TG-vs-WT, transgenic plants verse wild type plants. Red represents up-regulated gene expression. 7.1.1.6, cytochrome b6-f complex iron-sulfur subunit (petC). 1.18.1.2, ferredoxin–NADP + reductase (petH). 7.1.2.2, F-type H+/Na+-transporting ATPase subunit alpha (ATPF1A, atpA). PsbH, photosystem II PsbH protein. PsbO, photosystem II oxygen-evolving enhancer protein (1) PsbP, photosystem II oxygen-evolving enhancer protein (2) PsbQ, photosystem II oxygen-evolving enhancer protein (3) PsbS, photosystem II 22 kDa protein. PsbY, photosystem II PsbY protein. Psb27, photosystem II Psb27 protein. Psb28, photosystem II 13 kDa protein. PsaD, photosystem I subunit II. PsaF, photosystem I subunit III. PsaG, photosystem I subunit V. PsaH, photosystem I subunit VI. PsaK, photosystem I subunit X. PsaL, photosystem I subunit XI. PsaN, photosystem I subunit PsaN. PetC, cytochrome b6-f complex iron-sulfur subunit. PetE, plastocyanin. PetF, ferredoxin. PetH, ferredoxin–NADP + reductase. PetJ, cytochrome c6. Alpha, F-type H+/Na+-transporting ATPase subunit alpha. Delta, F-type H+-transporting ATPase subunit delta. A, F-type H+-transporting ATPase subunit a. B, F-type H+-transporting ATPase subunit b"
      }
    ]
  },
  {
    "id": "PMC12755880_multi",
    "image": [
      "images/PMC12755880-f1.png",
      "images/PMC12755880-f1-2.png",
      "images/PMC12755880-f2.png",
      "images/PMC12755880-f3.png",
      "images/PMC12755880-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Specific proteolysis mediated by a p97-directed proteolysis-targeting chimera (p97-PROTAC)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic representation of p97 presenting ubiquitinated proteins to the proteasome via a UBX domain-containing adaptor (top). The p97-PROTAC system, consisting of a UBX domain fused to a nanobody (Nb) that recruits substrates for p97-mediated segregation, unfolding, and proteasomal-mediated degradation (bottom). (B) p97-PROTAC (UBX-Nb(GFP)) recognizes GFP-tagged proteins at different cellular locations. HeLa cells were seeded on coverslips and co-transfected with UBX-Nb(GFP) and GFP-Coilin, GFP-Emerin, and GFP-ETV1. Cells were fixed and immunostained with anti-myc tag to verify the expression of UBX-Nb(GFP). Colocalization was evaluated using ImageJ/Fiji with the Coloc 2 plugin, obtaining Pearson correlation coefficient (R) values as follows: GFP-Emerin=0.95, GFP-Coilin=0.96, and GFP-ETV1=0.95. (C) Western blot analysis of GFP-Coilin degradation by transfection with p97-PROTAC (UBX-Nb(GFP)). (D) Quantification of C. (E) Western blot analysis of GFP-Emerin degradation by transfection with p97-PROTAC (UBX-Nb(GFP)). (F) Quantification of E. (G) Western blot analysis of GFP-ETV1 degradation by transfection with p97-PROTAC (UBX-Nb(GFP)). (H) Quantification of G, GFP-Coilin: 2 μg ‘p-value’ 0.0011 (**), 4 μg ‘p-value’ 0.0009 (***). GFP-Emerin: 2 μg ‘p-value’ 0.0130 (*), 4 μg ‘p-value’ 0.0059 (**). GFP-ETV1: 2 μg ‘p-value’ 0.0041 (**), 4 μg ‘p-value’ 0.0020 (**). Western blots were quantified and statistically analyzed using a Student’s t-test. p<0.05 compared to controls. n=3. Figure 1—source data 1.Raw Western blot images supporting GFP-Coilin, GFP-Emerin, and GFP-ETV1 degradation assays. Figure 1—source data 2.Annotated Western blot images indicating protein bands corresponding to GFP-Coilin, GFP-Emerin, and GFP-ETV1 degradation assays.\n\nFigure 1: Figure 1. (A) Amino acid sequence of human FAF1 UBX domain and synthetic p97 PROTAC chimera. (B–D) Histogram visualization of the colocalization of GFP-Coilin (B), GFP-Emerin (C), or GFP-ETV1 (D) and the Myc-tagged UBX-nanobody targeting GFP in HeLa cells. (E–G) HeLa cells were co-transfected with GFP-Coilin (E), GFP-ETV1 (F) or GFP-Emerin (G) with an empty vector or increasing concentrations of UBX-Nb (Neg.ctrl) vector. Protein degradation was analyzed by western blot. (H–I) Control experiment showing the localization of Myc-UBX-Nb(GFP) in HeLa cells co-transfected with free GFP (H) or empty vector (I). Figure 1—figure supplement 1—source data 1.Raw Western blots showing UBX-dependent degradation using an alternative nanobody as a control. Figure 1—figure supplement 1—source data 2.Annotated Western blots showing UBX-dependent degradation using an alternative nanobody as a control.\n\nFigure 2: Figure 2. (A) Strategy for inserting a yellow fluorescent protein (YFP) tag on the N-terminus of the 53BP1 gene in U2OS SEC-C cells using CRISPR/Cas9 D10A. (B) Selected knock-in (KI) YFP-53BP1 clones isolated via flow cytometry. Clones were confirmed via fluorescence microscopy (GE Deltavision Widefield). (C) Super-resolution images obtained with a Delta Vision OMX V4 structured illumination microscope (3D-SIM). (D) Immunofluorescence against 53BP1 (red) and colocalization with YFP-53BP1 in KI cells. Images were obtained using a Delta Vision OMX V4 structured illumination microscope (3D-SIM). (E) Recruitment of the p97-PROTAC UBX-Nb(GFP) (red) to YFP-53BP1 (green) within liquid-liquid phase separation structures. Data were obtained with a high-content CellDiscoverer 7. UBX-Nb(GFP) was detected using its myc-tag. (F) Western blot analysis of YFP-53BP1 degradation by UBX-Nb(GFP) transfection in the KI U2OS cells. (G) Quantification of F, ‘p-value’ 0.0071 (**). Western blots were quantified and statistically analyzed using a Student’s t-test. p<0.05 compared to controls. n=3. Figure 2—source data 1.Raw Western blots showing p97-PROTAC–mediated degradation of YFP-53BP1 in KI U2OS cells. Figure 2—source data 2.Annotated Western blots indicating YFP-53BP1 degradation in KI U2OS cells transfected with p97-PROTAC.\n\nFigure 3: Figure 3. Immunohistochemistry against p97 in brain tissue sections from nonhuman primates (Nhp) Macaca fascicularis, rat (Sprague-Dawley), and mouse (C57BL6/C). p97 expression was detected in substantia nigra pars compacta (SNpc), hippocampal, and cortical neurons. n=4.\n\nFigure 4: Figure 4. (A) Model representations of the FAF1 UBX domain (purple), UBX-Nb(GFP) (blue), GFP (green), and the p97 hexamer (light gray cartoon with semitransparent molecular surface representation). (B) A magnified view of the model shown in A. (C) GFP monomer was co-transfected with UBX-Nb (GFP) or empty vector in HeLa cells. Protein degradation was analyzed by western blot analysis. (D) Quantification of C, ‘p-value’ 0.0007 (***). (E) GFP monomer was co-transfected with UBX-Nb(GFP) or empty vector in HeLa cells, after 24 hr, the cells were incubated with DMSO or the proteasome inhibitor MG132 (25 µM final concentration) for 4 hr. Protein degradation was analyzed by western blot. (F) Quantification of E, ‘p-value’ DMSO treatment 0.0120 (*), ‘p-value’ MG132 treatment 0.7776 (ns). (G) p97 was silenced by transfection with VCP-siRNA in HeLa cells. Subsequently, the cells were transfected with GFP-Emerin and either the empty vector or UBX-Nb(GFP) vector. Protein degradation was analyzed by western blot analysis. (H) Quantification of GFP-Emerin in UBX-Nb(GFP) cells treated with either siNT control or a VCP-siRNA, ‘p-value’ 0.0114 (*). (I) Quantification of the UBX-Nb(GFP) (myc-tag) in UBX-Nb(GFP) cells treated with either siNT control or a VCP-siRNA, ‘p-value’ 0.0775 (ns). (J) HeLa cells co-transfected with GFP-Emerin and either empty vector or UBX-Nb(GFP); in addition, the cells were treated with the E1 ubiquitin inhibitor PYR-41 (50 µM) for 4 hr at 37°C. Subsequently, total proteins were extracted, and protein degradation was analyzed by western blot. (K) Quantification of J, ‘p-value’ DMSO treatment 0.0009 (***), ‘p-value’ PYR-41 treatment 0.0003 (***). (L) GFP-Emerin was co-transfected with UBX-Nb(GFP) or empty vector in HeLa cells, after 24 hr the cells were incubated with DMSO (as control) or the p97 inhibitor CB-5083 (4 µM final concentration) for 6 hr. Protein degradation was analyzed by western blot using total proteins. (M) Quantification of L, ‘p-value’ DMSO treatment 0.0071 (**), ‘p-value’ CB-5083 treatment 0.0139 (*). Western blots were quantified and statistically analyzed using a Student’s t-test. p<0.05 compared to controls. n=3. Figure 4—source data 1.Raw Western blots showing p97-PROTAC–mediated degradation using inhibitors and siRNA controls. Figure 4—source data 2.Annotated Western blots showing p97-PROTAC–mediated degradation under inhibitor and siRNA conditions."
      }
    ]
  },
  {
    "id": "PMC12755880_multi_2",
    "image": [
      "images/PMC12755880-f4-2.png",
      "images/PMC12755880-f5.png",
      "images/PMC12755880-f5-2.png",
      "images/PMC12755880-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Specific proteolysis mediated by a p97-directed proteolysis-targeting chimera (p97-PROTAC)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 4: Figure 4. (A) HeLa cells were co-transfected with a vector expressing anti-GFP nanobody fused to a myc-tag (Myc-Nb-anti-GFP) along with either an empty vector or increasing concentrations of p97-GFP. The degradation of Myc-Nb-anti-GFP was analyzed by western blot. (B) Quantification of panel H: 2 μg (p-value = 0.0410, *), 4 μg (p-value = 0.0063, **). (C) HeLa cells were incubated with different concentrations of PYR-41 (a cell-permeable irreversible inhibitor of ubiquitin-activating enzyme E1) for 4 hr. Subsequently, total cellular proteins were extracted, and western blot analyses were performed. Nitrocellulose membranes were incubated with the primary antibodies anti-p53 and anti-ubiquitin antibody. DMSO was used as a control. n=2. Figure 4—figure supplement 1—source data 1.Raw Western blots showing p97-dependent degradation and PYR41 treatment effects. Figure 4—figure supplement 1—source data 2.Annotated Western blots indicating protein bands for p97-dependent degradation and PYR41 treatment effects.\n\nFigure 5: Figure 5. HeLa cells were transiently co-transfected with HTT GFP-tagged plasmids containing either 23 CAG repeats (EGFP-HTTQ23-wild-type HTT), 74 CAG repeats (EGFP-HTTQ74: mutant HTT), or 24 CAG repeats (EGFP-HTTQ24). (A) Cells were co-transfected with GFP-HTTQ23 and increasing amounts of the p97 PROTAC UBX-Nb(GFP), degradation was determined by western blot analysis. (B) Quantification of A, 2 μg ‘p-value’ 0.0041 (**), 4 μg ‘p-value’ 0.0014 (**). (C) Immunofluorescence showing the recruitment of p97 PROTAC UBX-Nb(GFP) to GFP-HTTQ23. (D) HeLa cells were co-transfected with GFP-HTTQ74 and increasing amounts of the p97 PROTAC UBX-Nb(GFP), degradation was determined by western blot analysis. (E) Quantification of D, 2 μg ‘p-value’ 0.0016 (**), 4 μg ‘p-value’ 0.0003 (***). (F) Immunofluorescence to demonstrate the recruitment of p97 PROTAC UBX-Nb(GFP) to GFP-HTTQ74. Western blots were quantified and statistically analyzed using a Student’s t-test. p<0.05 compared to controls. n=3. Figure 5—source data 1.Raw Western blots showing p97-PROTAC–mediated degradation of GFP-HTTQ23 and GFP-HTTQ74. Figure 5—source data 2.Annotated Western blots indicating protein bands for p97-PROTAC–mediated degradation of GFP-HTTQ23 and GFP-HTTQ74.\n\nFigure 5: Figure 5. High-molecular-weight aggregates and protein degradation were analyzed by western blot. Western blots were quantified and statistically analyzed using a Student’s t-test. p<0.05 compared to controls. n=3. Figure 5—figure supplement 1—source data 1.Raw Western blots showing p97-PROTAC effects on GFP-HTTQ24 degradation and aggregate levels. Figure 5—figure supplement 1—source data 2.Annotated Western blots indicating protein bands for GFP-HTTQ24 degradation and aggregate analysis under p97-PROTAC treatment.\n\nFigure 6: Figure 6. (A) HeLa cells were co-transfected with a vector expressing αSynuclein mutant A53T fused to GFP (GFP-αSynuclein A53T) and empty or increasing concentrations of UBX-Nb(Syn87). A53T-GFP degradation was determined by western blot. (B) Quantification of A, 2 μg ‘p-value’ 0.0651 (ns), 4 μg ‘p-value’ 0.0020 (**). (C) Cells were co-transfected with a vector expressing untagged α-synuclein mutant A53T and an empty vector or increasing concentrations of UBX-Nb(Syn87). Untagged αSynuclein A53T degradation was determined by western blot using an anti αSynuclein antibody. (D) Quantification of C, 2 μg ‘p-value’ 0.0240 (*), 4 μg ‘p-value’ 0.0210 (*). (E) Quantification of α-synuclein aggregation via Thioflavin T (ThT) fluorescence. Non-transfected cells and cells transfected with GFP-tagged wild-type α-synuclein (pcDNA5 WT αSyn-GFP), either alone or co-transfected with the p97-based PROTACs containing nanobodies against GFP [UBX-Nb(GFP)] or α-synuclein [UBX-Nb(Syn87)], were analyzed for relative ThT fluorescence intensity normalized to total protein concentration (μg/μL). Bars represent mean ± SEM. Asterisks (*) indicate statistically significant differences compared to control (*p<0.05, Dunnett’s post hoc test); ‘ns’ indicates no significant difference. (F) Representative model of p97-PROTAC functioning in the degradation of proteins and protein aggregates. Western blots were quantified and statistically analyzed using a Student’s t-test. p<0.05 compared to controls. n=3. Figure 6—source data 1.Raw Western blots showing p97-PROTAC–mediated degradation of GFP-tagged and untagged α-synuclein A53T. Figure 6—source data 2.Annotated Western blots indicating protein bands for p97-PROTAC–mediated degradation of GFP-tagged and untagged α-synuclein A53T."
      }
    ]
  },
  {
    "id": "PMC12774698_multi",
    "image": [
      "images/PMC12774698-f1.png",
      "images/PMC12774698-f2.png",
      "images/PMC12774698-f3.png",
      "images/PMC12774698-f4.png",
      "images/PMC12774698-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Evolution of the lipidome uncovers early changes in adrenoleukodystrophy human cortical and spinal organoids\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Study workflow for cortical and spinal organoids derived from hiPSCs and characterization of organoids across maturation stages (A) Schematic representation of the experimental design. Cortical and spinal cord organoids were derived from human induced pluripotent stem cells (hiPSCs) from control (CTRL) and adrenoleukodystrophy (ALD) donors. Lipidomics was performed using liquid chromatography high-resolution accurate mass spectrometry (LC-HRAM-MS). Immunohistochemistry and electron microscopy were used for structural and cellular characterization. (B) Representative confocal immunofluorescence images of control hiPSC-derived cortical organoids (hCOs). At earlier stages, hCO generated distinct populations of cycling dorsal neural progenitors (SOX2, H3S10ph, and PAX6) that organized into ventricular-like zones, with an outer subventricular-zone-like area of TBR2+ intermediate progenitors, and an adjacent cortical-like plate of CTIP2+ deep layer and SATB2+ upper layer neurons (scale bars, 50 μm). (C and D) At later stages, hCO are composed of GFAP+ astrocytes, OLIG2+ oligodendrocyte precursor cells, and MBP+ myelinating oligodendrocytes (scale bars, 50 μm). (E) Representative electron microscopy images of day 200 hCO showing mushroom-shaped dendritic spines (asterisks), glycogen particles in astrocytes (triangles), and myelin-forming oligodendrocytic processes (right pointing arrowhead). (F) Representative confocal immunofluorescence images of ABCD1 present in MAP2+ neurons, GFAP+ astrocytes, and MBP+ oligodendrocytes at day 200 (scale bars, 50 μm). (G and H) Representative confocal immunofluorescence images of control hiPSC-derived spinal organoids (hSO). At earlier stages, hSO generated distinct PAX6+ dorsal and NKX6.1+ ventral progenitor zones. At later stages, hSO are composed of ISL1/2+ motor neurons, and glutamatergic VGLUT+ and GABAergic VGAT+ synaptic vesicles (scale bars, 100 μm). (I) Representative electron microscopy images of day 100 hSO show dendritic spines (asterisk), glycogen particles in astrocytes (triangles), and myelin-forming oligodendrocytic processes (arrowhead). (J) Representative confocal immunofluorescence images of ABCD1 present in MAP2+ neurons, GFAP+ astrocytes, and MBP+ oligodendrocytes at day 100 hSO (scale bars, 50 μm).\n\nFigure 2: Figure 2. Characterization of cortical organoids and lipidomic profiling across maturation stages (A) Principal component analysis (PCA) of lipidomic profiles shows distinct clustering of cortical organoids by maturation timepoint (color-coded) and individual lines (shapes). n = 3 lines, 4 timepoints, 3 samples per line. (B) Heatmap shows the Z-scores of lipid class abundance across four timepoints (days 50, 100, 150, and 200). Each lipid class displays dynamic changes in abundance during organoid maturation. (C) Log2 fold changes of lipid classes with 1, 2, and 3 acyl chains as a function of total acyl chain length across timepoints (days 100, 150, 200, relative to day 50), fitted with LOESS smoothing. (D) Log2 fold changes of lipid classes with 1, 2, and 3 acyl chains as a function of the total number of double bonds across timepoints (days 100, 150, 200, relative to day 50), fitted with LOESS smoothing.\n\nFigure 3: Figure 3. Characterization of spinal cord organoids and lipidomic profiling across maturation stages (A) Principal component analysis (PCA) of lipidomic profiles shows the distinct clustering of spinal cord organoids by maturation timepoint (color-coded) and individual lines (shapes). n = 3 lines, 2 timepoints, 3 samples per line. (B) Heatmap shows the Z-scores of lipid class abundance across four timepoints (days 50 and 100). Each lipid class displays dynamic changes in abundance during organoid maturation. (C) Log2 fold changes of lipid classes with 1, 2, and 3 acyl chains as a function of total acyl chain length at day 100, relative to day 50, fitted with LOESS smoothing. (D) Log2 fold changes of lipid classes with 1, 2, and 3 acyl chains as a function of the total number of double bonds at day 100 relative to day 50, fitted with LOESS smoothing.\n\nFigure 4: Figure 4. Lipidomic profiling reveals changes in lipid composition in ALD and control cortical organoids across maturation stages (A) Representative electron microscopy images of day 200 ALD hCO show dendritic spines (asterisks), glycogen particles in astrocytes (triangles), and myelin-forming oligodendrocytic processes (right pointing arrowhead). (B) Principal component analysis (PCA) of lipidomic profiles of cortical organoids across maturation stages (days 50, 100, 150, and 200) comparing ALD (triangles) and control (circles) samples. Points are color-coded by timepoint, illustrating clear clustering patterns based on maturation and disease status. Data represent median lipid profiles of 3 samples per line. n = 12 lines (9 ALD lines, 3 control), 4 timepoints. (C) Volcano plots illustrate Log2 fold change (Log2 FC) versus -Log10 (p-value) for lipid species at each timepoint (days 50, 100, 150, and 200) comparing ALD to controls. Each point represents one lipid species, color coded by lipid subclass. Statistical significance was determined using a linear mixed-effects model. (D) Boxplots show the abundance (log scale) of representative lipid species (CE(32:1), PC(54:3), PC(58:7), TG(74:7)) across timepoints for ALD (blue) and control (gray) organoids. Statistical significance for comparisons between ALD and control is indicated above the boxes at each time point. Statistical significance was determined using a linear mixed-effects model. Data represent median lipid profiles of 3 samples per line. n = 12 lines (9 ALD lines, 3 control), 4 timepoints. Boxes show the interquartile range (IQR) with the median; whiskers extend to 1.5 × IQR. ∗∗ FDR ≤0.01, ∗∗∗ FDR ≤0.001. FDR values for CE(32:1) were 8.95×10−4 (T50), 3.03×10−3 (T100), 5.15×10−3 (T150), and 1.21×10−4 (T200); for PC(54:3) 1.94×10−9 (T50), 2.04×10−8 (T100), 4.63×10−12 (T150), and 6.22×10−19 (T200); for PC(58:7) 2.09×10−5 (T50), 2.72×10−5 (T100), 3.56×10−9 (T150), and 5.28×10−9 (T200); and for TG(74:7) 4.62×10−4 (T50), 6.01×10−4 (T100), 5.93×10−3 (T150), and 3.16×10−4 (T200). (E) Line plots show Log2 fold change for lipid species with 1, 2, and 3 acyl chains as a function of acyl chain length, comparing ALD to controls. Trends are shown for days 50, 100, 150, and 200, fitted with LOESS smoothing. (F) Bubble plots illustrate the relationship between acyl chain length and the number of double bonds for cholesteryl esters (CEs), phosphatidylcholines (PCs), and triglycerides (TGs) at day 200, comparing ALD to controls. Bubble size corresponds to -Log10 (p-value) and color intensity indicates Log2 fold change. Statistical significance was determined using a linear mixed-effects model.\n\nFigure 5: Figure 5. Lipidomic profiling reveals changes in lipid composition in ALD and control spinal cord organoids across maturation stages (A) Principal component analysis (PCA) of lipidomic profiles of spinal cord organoids across maturation stages (days 50 and 100), comparing ALD (triangles) and control (circles) samples. Points are color-coded by timepoint, illustrating clear clustering patterns based on maturation and disease status. Data represent median lipid profiles of 3 samples per line (n = 2 timepoints, 9 ALD lines, 3 control lines). (B) Volcano plots illustrate Log2 fold change (Log2 FC) versus -Log10 (p-value) for lipid species at each timepoint (days 50 and 100), comparing ALD to controls. Each point represents a lipid species, color-coded by lipid subclass. Statistical significance was determined using a linear mixed-effects model. (C) Boxplots show the abundance (log scale) of representative lipid species (CE(35:1), PC(52:2), PC(54:3), TG(70:2), and TG(70:3)) across timepoints for ALD (red) and control (gray) organoids. Statistical significance for comparisons between ALD and control is indicated above the boxes at each time point. Statistical significance was determined using a linear mixed-effects model. Data represent median lipid profiles of 3 samples per line. n = 12 lines (9 ALD lines, 3 control). Boxes show the interquartile range (IQR) with the median; whiskers extend to 1.5 × IQR. ∗∗ FDR ≤0.01, ∗∗∗ FDR ≤0.001. FDR values for CE(35:1) were 4.58×10−6 (T50) and 9.19×10−6 (T100); for PC(52:2) 4.58×10−6 (T50) and 5.84×10−7 (T100); for PC(54:3) 1.40×10−4 (T50) and 4.10×10−5 (T100); for TG(70:2) 3.24×10−4 (T50) and 1.30×10−3 (T100); and for TG(70:3) 1.16×10−4 (T50) and 2.05×10−4 (T100). (D) Line plots show Log2 fold change for lipid species with 1, 2, and 3 acyl chains as a function of acyl chain length, comparing ALD to controls. Trends are shown for days 50 and 100, fitted with LOESS smoothing. (E) Bubble plots illustrate the relationship between acyl chain length and the number of double bonds for cholesteryl esters (CEs), phosphatidylcholines (PCs), and triglycerides (TGs) at day 100, comparing ALD to controls. Bubble size corresponds to -Log10 (p-value) and color intensity indicates Log2 fold change. Statistical significance was determined using a linear mixed-effects model."
      }
    ]
  },
  {
    "id": "PMC12774698_multi_2",
    "image": [
      "images/PMC12774698-f6.png",
      "images/PMC12774698-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Evolution of the lipidome uncovers early changes in adrenoleukodystrophy human cortical and spinal organoids\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Altered lipid metabolism in ALD cortical organoids (A) Line plots show the mean values ±SD for GM1[d] and SM4[d] across maturation timepoints (days 50, 100, 150, 200) in control (gray) and ALD (red) organoids. FDR values of the overall group difference across all timepoints for GM1[d] were 0.126 (p = 0.0167); for SM4[d] 0.0854 (p = 0.00444); and for SM4[t] 0.126 (p = 0.0168). Data represent median lipid profiles of 3 samples per line. n = 12 lines (9 ALD lines, 3 control), 4 timepoints. Statistical significance was determined using a linear mixed-effects model. (B) Heatmap of Z-scores for individual SM4 and GM1 lipid species across maturation stages in control and ALD hCO. Each row represents a lipid species, and each column represents a hiPSC line. Lipid species show distinct profiles between the ALD and control groups. Data represent median lipid profiles of 3 samples per line. n = 12 lines (9 ALD lines, 3 control), 4 timepoints. (C) Quantification of OLIG2+, O4+, and MBP+ cells at day 200 hCO. Quantification was performed in 3 whole tissue sections from 3 to 4 organoids per hiPSC line. p values were calculated using two-tailed nested t test. Data are represented as mean ± SD.\n\nFigure 7: Figure 7. Altered lipid metabolism in ALD spinal organoids (A) Line plots show mean values ±SD for lipid classes across two timepoints (days 50 and 100) in control (gray) and ALD (red) organoids. Lipid subclasses include 2-acyl-LPE, LPE, LPE[O], LPE[P], and PE[O + P]. FDR values of the overall group difference across all timepoints for 2-acyl LPE were 0.117 (p = 0.00675); for LPE 0.120 (p = 0.0152); for LPE[P] 0.193 (p = 0.0385); for LPE[O] 0.117 (p = 0.0124); and for PE[O + P] 0.0988 (p = 0.00359). Data represent median lipid profiles of 3 samples per line. n = 12 lines (9 ALD lines, 3 control), 2 timepoints. Statistical significance was determined using a linear mixed-effects model. (B) Heatmap of Z-scores for individual lipid species within lipid classes across samples from ALD and control hSO. Each row represents a lipid species, and each column represents an hiPSC line. ALD organoids show distinct lipidomic profiles compared to controls. Data represent median lipid profiles of 3 samples per line. n = 12 lines (9 ALD lines, 3 control), 2 timepoints."
      }
    ]
  },
  {
    "id": "PMC12775220_multi",
    "image": [
      "images/PMC12775220-f1.png",
      "images/PMC12775220-f2.png",
      "images/PMC12775220-f3.png",
      "images/PMC12775220-f4.png",
      "images/PMC12775220-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Local accumulation of very long-chain PUFA in plexiform layers associates with retinal dysfunction in a mouse model of peroxisomal ACBD5-deficiency\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Cellular alterations in the retina of Acbd5−/− mice. (A) Representative images of HE-stained sections from the retina of 3-month (3 m) and 12-month-old (12 m) Acbd5−/− mice and Acbd5+/+ controls. (B) ONL/INL ratio calculated from the HE-stained retinae (3 m: Acbd5+/+n = 6, Acbd5−/−n = 4; 12 m: Acbd5+/+n = 5, Acbd5−/−n = 5). (C, D) Average diameter of individual retinal layers in 3- and 12-month-old Acbd5−/− and Acbd5+/+ mice according to the HE stained sections. (E) IF images from ONL, PIS and POS showing nuclei (blue, TOPRO) and rhodopsin (green). (F) Length of POS identified by the rhodopsin signal (3 m: Acbd5+/+n = 6, Acbd5−/−n = 5; 12 m: Acbd5+/+n = 4, Acbd5−/−n = 7). (G) IF images showing regions from INL to POS; nuclei are visualized by TOPRO (blue), cone photoreceptor cells by antibodies against cone arrestin (green). (H) Retinal cell densities for cone photoreceptors identified by cone arrestin (ARR4) (3 m: Acbd5+/+ n = 6, Acbd5−/− n = 5; 12 m: Acbd5+/+ n = 5, Acbd5−/−n = 6). (I) Images of retinal ONL to GCL with nuclei stained by TOPRO (blue) and bipolar cells by an antibody against PKCα (protein kinase C alpha) (J) Retinal cell densities for bipolar cells identified by PKCα (3 m: Acbd5+/+n = 6, Acbd5−/−n = 5; 12 m: Acbd5+/+n = 4, Acbd5−/−n = 5). (K) IF of retinal ONL to GCL showing nuclei (blue, TOPRO) and ganglion cells (green, NeuN antibody). (L) Retinal cell densities for ganglion cells identified by NeuN (3 m: Acbd5+/+n = 6, Acbd5−/−n = 5; 12 m: Acbd5+/+n = 4, Acbd5−/−n = 5). Abbr.: ONL – outer nuclear layer, OPL - outer plexiform layer, INL – inner nuclear layer, IPL – inner plexiform layer, POS – photoreceptor outer segments, PIS – photoreceptor inner segments, GCL – ganglion cell layer; ns – not significant, * p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001\n\nFigure 2: Figure 2. Neuroinflammation in the retina of Acbd5−/− mice. (A) Representative IF images showing location and activation of microglia (IBA1, cyan), Müller cells and astrocytes (GFAP, magenta) in the retina of Acbd5−/− mice. (B) Colocalisation of Glut-Synth. (magenta) and GFAP (cyan) in radial Müller cell projections in the IPL of the Acbd5−/− mice. (C) Density of IBA1-positive microglia in all retinal layers and percentage of microglial cells in individual retinal layers (n = 5/genotype) from 3-month-old specimens. (D) Density of IBA1-positive microglia in all retinal layers and percentage of microglial cells in individual retinal layers (n = 5/genotype) from 12-month-old specimens. (E) Density of GFAP-positive astrocytes and Müller cells in the IPL, GCL and nerve fiber layer of the retina from 3-month-old mice. (F) Density of GFAP-positive astrocytes and Müller cells (MC) in the IPL, GCL and nerve fiber layer of the retina from 12-month-old mice. (G) Representative images of Müller cells projections into the IPL. Abbr.: ONL – outer nuclear layer, OPL – outer plexiform layer, IPL – inner plexiform layer, INL – inner nuclear layer, GCL – ganglion cell layer, N.opt. – Nervus opticus, Glut.Synth – glutamine synthetase; ns – not significant, * p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001\n\nFigure 3: Figure 3. Full-field ERG characterization of Acbd5+/+ and Acbd5−/−. (A) Average scotopic ERG traces following flash stimulation at 0 log(cd*s/m2) from either Acbd5+/+ and Acbd5−/−. (B) Quantification of a-wave and b-wave amplitudes elicited following flash stimulation at 0 log(cd*s/m2). (C) Representative ERGs from single-flash flash stimulation sequences from − 4 to 1.5 log(cd*s/m2) for scotopic (dark-adapted) conditions, and − 1.5 to 1.5 log(Cd*s/m2) for photopic (light-adapted) conditions. (D) Representative flicker flash sequences with increasing stimulation frequency from from 1 to 20 hz. (E) Quantification of a- and b-waves as indicated, following scotopic and photopic flash stimulation sequences as shown in (C). (F) Quantification of b-waves following flicker ERG stimulation sequence as shown in (D). For all traces, black indicates Acbd5+/+ and red indicates Acbd5−/− mice. Statistical analyses performed with (B) student’s unpaired t-test, and (E, F) two-way ANOVA with Sidak’s post-hoc test. * p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001\n\nFigure 4: Figure 4. Morphology of the retinal pigment epithelium (RPE) in retina flat-mount preparations from 3-month and 12-month-old Acbd5−/− and Acbd5+/+ mice (n = 10/genotype). (A) Representative IF images from 3-month-old specimens; cell borders are visualized by phalloidin (red), nuclei by TOPRO (blue); stars highlight binucleated, arrows multinucleated cells (> 2 nuclei). (B) Relative frequency distribution of the RPE cell size of 3-month-old mice. (C) Representative IF images from 12-month-old specimens; colors and labels as in (A). (D) Frequency distribution of the RPE cell size of 12-month-old mice. (E) Percentage of mono-/bi-/multinuclear cells in the RPE of 3- and 12-month-old Acbd5−/− and Acbd5+/+ mice. (F, G) IF images showing cone opsin (red) and rhodopsin (green) positive vesicles in RPE flat mounts, cells borders are highlighted by peroxisomes (antibody against PEX14, blue) positioned in close proximity to the cell membrane. (H) Quantification of cone opsin and rhodopsin vesicles in RPE flat mounts (3 m: Acbd5+/+n = 6, Acbd5−/−n = 6; 12 m: Acbd5+/+n = 6, Acbd5−/−n = 7). ns – not significant, * p < 0.05, ** p < 0.01, *** p < 0.001\n\nFigure 5: Figure 5. Subcellular organization of RPE cells from 12-month-old Acbd5−/− and Acbd5+/+. (A) Nile-Red-stained RPE flat-mount preparations showing 488 nm-exited fluorescence for neutral lipids (cyan) and 561 nm-exited fluorescence for phospholipids (magenta). Note that neutral lipids show residual fluorescence at 561 nm resulting partially in white spots in overlays; additionally, peroxisomes were identified by PEX14 antibodies (shown in blue). Examples for singular and accumulations of peroxisomes are indicated by arrowheads, lipid droplets are indicated by arrows. (B) Quantification of cellular lipid droplets marked in cyan in (A) (n = 5 per genotype). (C) EM images giving an overview of RPE cell morphology (Acbd5+/+n = 3, Acbd5−/−n = 4). (D) Quantification of the average height of the RPE cells from the Bruch membrane to the POS (nuclear regions excluded). (E) Magnifications from the deeply folded basal RPE cell membrane including the Bruch membrane. Abbr.: Mel -melanosome, Mi – mitochondrion, PO – peroxisome, BF – basal folds, Note, that the folds are less frequent and rather coarse in the Acbd5−/− RPE (F) Quantification of the diameter of individual folds in the basal cell membrane (Acbd5+/+n = 3, Acbd5−/−n = 4). ns – not significant, * p < 0.05, ** p < 0.01, *** p < 0.001"
      }
    ]
  },
  {
    "id": "PMC12775220_multi_2",
    "image": [
      "images/PMC12775220-f6.png",
      "images/PMC12775220-f7.png",
      "images/PMC12775220-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Local accumulation of very long-chain PUFA in plexiform layers associates with retinal dysfunction in a mouse model of peroxisomal ACBD5-deficiency\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Lipid composition of total retina homogenates from Acbd5−/− and Acbd5+/+ mice (n = 8 per genotype) determined by ESI-MS. (A) Comparison of the amounts of distinct ether/ester lipid classes: LPC [O + P] – alkyl-/alkenyl-lysophosphatidylcholines, PC [O + P] - alkyl-/alkenyl-phosphatidylcholines, PE [O + P] - PC [O + P] - alkyl-/alkenyl-phosphatidylethanolamines, PC – phosphatidylcholines, CE – cholesteryl esters. (B) Comparison of the fatty acid (FA) composition of selected lipid classes, circles in blue show lipid species elevated and circles in orange lipid species decreased in Acbd5−/− retinae, the circle size signifies the measure of significance of the alteration, the x-axis depicts the FA carbon chain length, the y-axis the number of double bonds/FA. (C) Direct comparison of selected (lyso-)phosphatidylcholines ((L-)PC) representative for the following phospholipid FA combinations: LPC(22:6): DHA, PC(38:6): DHA + palmitic acid, PC(40:7): DHA + oleic acid, PC(42:7) DHA + eicosenoic acid, PC(60:9); DHA + C38:3. ns – not significant, * p < 0.05, ** p < 0.01\n\nFigure 7: Figure 7. Distribution of selected PC species in sagittal sections of Acbd5−/− and Acbd5+/+ retinae determined by MALDI MS imaging (n = 5/genotype). (A) Overlay of m/z signal intensity distribution for PC(38:6) (green), PC(40:7) (magenta), PC(54:12) (blue), PC(62:9) (yellow). (B – E) Localization of the individual PC species among the retinal layers; to this end, distinct m/z signals representing PC(38:6) (m/z 828.55, [M + Na]+, mass error 1.45 ppm) (B), PC(40:7) (m/z 832.58, [M + H]+, mass error 3.0 ppm) (C), PC(54:12) (m/z 1040.71, [M + Na]+, mass error 1.06 ppm) (D), PC(60:10) (m/z 1106.85, [M + H]+, mass error 1.99 ppm) exemplary transverse retina sections were merged with the HE-stained consecutive section from the same specimen. Abbr.: SCL – sclera, PIS/POS – photoreceptor inner, outer segment, ONL – outer nuclear layer, INL – inner nuclear layer, IPL – inner plexiform layer\n\nFigure 8: Figure 8. Ribeye IF and electron microscopy analysis of the retina from 12-month-old Acbd5−/− and Acbd5+/+ mice. (A, B) Representative transverse retina sections from Acbd5+/+ and Acbd5−/− mice (n = 5/genotype) depicting ribbon synapses in green (Ribeye IF) and bipolar cells in magenta (PKCα IF); nuclei are shown in blue (TOPRO). (C-F) Quantification of ribbon synapse size and density in the OPL and IPL of the IF images. (G, H) General view of cross sections through the retina from Acbd5+/+, n = 3 (G) and Acbd5−/− mice, n = 3 (H); magnifications are derived from the OPL. (I, J) Overview of the OPL from Acbd5+/+ (G) and Acbd5−/− (H) retinae, ribbon synapses are highlighted by red arrowheads. (K) Typical photoreceptor ribbon synapses from Acbd5+/+ retinae, the presynaptic ribbon is highlighted by red arrowheads, horizontal cell terminals by stars, bipolar cell projections by a ”plus” and lysosomes with residual inclusions by red arrows. (L) Representative ribbon synapses in the Acbd5−/− OPL; extend ribbons without contact to postsynaptic structures as highlighted by the white arrowhead were more frequently observed in the ACBD5-deficient OPL. (M) Presynaptic ribbon retracted into the vicinity of the nucleus of a photoreceptor cell in an Acbd5−/− retina. (H-L) Quantification of the ribbon synapse frequency and morphology analyzed by EM. Abbr.: Mi – mitochondrion, Nu – nucleus, IPL – inner plexiform layer, INL – inner nuclear layer, OPL – outer plexiform layer, ONL – outer nuclear layer; ns – not significant, * p < 0.05, ** p < 0.01"
      }
    ]
  },
  {
    "id": "PMC12781578_multi",
    "image": [
      "images/PMC12781578-f1.png",
      "images/PMC12781578-f2.png",
      "images/PMC12781578-f3.png",
      "images/PMC12781578-f4.png",
      "images/PMC12781578-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Targeting TRIM25 as a therapeutic strategy to enhance ferroptosis in glioblastoma cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. ssGSEA and unbiased CRISPR-Cas9 screening reveal that VDAC2 is an essential driver of ferroptosis in GBM. A. Evaluation of overall enrichment scores for five programmed cell death (PCD) pathways in gliomas from the CGGA database using ssGSEA. B. Evaluation of overall enrichment scores for PCD pathways in gliomas from the TCGA database using ssGSEA. C. Schematic workflow of CRISPR-Cas9 library screening. D. Quality control images for library screening. E. Determination of IC50 values using a cell counting kit-8 (CCK-8) assay in erastin-resistant LN229 cells (induced by erastin treatment) and parental LN229 cells treated with gradient concentrations of erastin (n = 3). (F) Venn diagram illustrating the four overlapping genes shared between the two datasets. (G) Read counts of the four genes. (H) Correlations between VDAC2 expression levels and survival duration in glioma patients across four databases (CGGA, TCGA, Gravendeel, and Rembrandt). (I) Association of VDAC2 expression with glioma grade and stage in four databases (CGGA, TCGA, Gravendeel, and Rembrandt). (J) Distribution of high versus low VDAC2 expression in recurrent versus nonrecurrent patients from a 180-case clinical tissue microarray cohort. K. Representative immunohistochemical (IHC) staining images of VDAC2 and 4-HNE in nonrecurrent versus recurrent patient samples. Scale bar = 50 μm. L. Kaplan‒Meier survival curve for assessing the relationship between VDAC2 expression and survival prognosis in glioma patients. P values were calculated using two-tailed t tests (E) and the log-rank test, with adjustments for confounding factors via Cox regression (L). The data are presented as the means ± SDs\n\nFigure 2: Figure 2. VDAC2 induces ferroptosis via mitochondrial damage A. GO enrichment analysis of genes differentially expressed between VDAC2-overexpressing cells and parental cells (RNA-seq, n = 3). B. KEGG pathway enrichment analysis of differentially expressed genes in VDAC2-overexpressing versus parental cells. C. Heatmap of VDAC2 expression and ferroptosis-related genes in 6 clinical GBM samples. D. Pearson correlation analysis between VDAC2 and ACSL4/SLC7A11 expression in the TCGA database. E. Viability assessment of live and dead cells under different treatment conditions (n = 5). Scale bar = 20 μm. F. Flow cytometric quantification of oxidized versus nonoxidized lipid ratios (n = 5). G. Measurement of intracellular lipid ROS levels by flow cytometry (n = 5). H. Immunofluorescence imaging of lipid peroxidation using C11-BODIPY probe staining. Scale bar = 10 μm. I. Assessment of changes in the mitochondrial membrane potential (Δψm) via JC-1 probe staining. Scale bar = 10 μm. J. Visualization of mitochondrial lipid peroxidation using MitoPeDPP probe staining. K. Detection of mitochondrial ROS by MitoSOX probe staining. Scale bar = 10 μm. L. Transmission electron microscopy images of cells under different treatments (red arrows indicate mitochondria). M. Tumor volume measurements and H&E staining in orthotopic xenograft models (n = 8 animals per group). N. Quantitative analysis of tumor growth by fluorescence intensity and volume measurement (n = 8). O. Survival curves of nude mice bearing tumors derived from parental or VDAC2-overexpressing cells (n = 8 per group). P. Immunohistochemical (IHC) analysis and quantitative scoring of VDAC2 and 4-HNE expression in tumor tissues (n = 3). Scale bar = 50 μm. P values were calculated using two-tailed t tests (E, F, G, N and P) and the log-rank Mantel‒Cox test (O). The data are presented as the means ± SDs\n\nFigure 3: Figure 3. TRIM25 mediates ubiquitination-dependent degradation of the VDAC2 protein A. Silver staining image of Co-IP products separated by SDS‒PAGE. B. Mass spectrometry identification of potential VDAC2-interacting proteins. C. Analysis of the correlation between TRIM25 and VDAC2 protein expression in the TCGA database. D. Changes in VDAC2 expression levels in LN229 cells after infection with sgTRIM25 lentivirus (n = 3). E. Changes in VDAC2 expression levels at 0, 3, 6, and 9 h postlentivirus infection with synchronized CHX treatment (n = 3). F. Co-IP analysis of the interaction between endogenous TRIM25 and VDAC2 in LN229 cells. G. Immunofluorescence staining showing the interaction and colocalization of the TRIM25 and VDAC2 proteins in LN229 cells. Scale bar = 10 μm. H. Co-IP analysis of the interaction between TRIM25 and VDAC2 in HEK293T cells cotransfected with FLAG-tagged VDAC2 or MYC-tagged TRIM25 plasmids. I. Western blot showing VDAC2 expression in HEK293T cells transfected with the MYC-TRIM25 plasmid and treated with CQ (50 µM) or MG132 (4 µM) (n = 3). J. MOE analysis of TRIM25-VDAC2 protein interaction sites and binding affinity S-scores. K. Schematic diagram of TRIM25 protein truncation mutants. L. Western blot showing Co-IP products in LN229 cells transfected with full-length or truncated TRIM25. M. Western blot images of HEK293T cells transfected with different plasmids. N. Western blot images of polyubiquitin chains in HEK293T cells cotransfected with FLAG-VDAC2 and His-ubiquitin plasmids. O. Western blot showing ubiquitination degradation sites in HEK293T cells transfected with K48 ubiquitin site mutation plasmids. P values were calculated using two-tailed t tests (D, E and I). The data are presented as the means ± SDs\n\nFigure 4: Figure 4. TRIM25 knockout enhances ferroptosis sensitivity in LN229 cells in vitro and in vivo A. Correlations between TRIM25 expression levels and survival duration in glioma patients across the CGGA, TCGA, and Rembrandt databases. B. Representative immunohistochemical (IHC) staining images of TRIM25 and 4-HNE in recurrent versus nonrecurrent patients from a 180-case clinical tissue microarray cohort. Scale bar = 50 μm. C. Kaplan‒Meier survival analysis evaluating the prognostic significance of TRIM25 expression in glioma patients. D. GO enrichment analysis of differentially expressed genes between TRIM25-knockout and parental cells (RNA-seq, n = 3). E. Gene set enrichment analysis (GSEA) of the ferroptosis pathway. F. Viability assessment of live versus dead cells under different treatment conditions (n = 5). Scale bar = 20 μm.G. Flow cytometric measurement of intracellular lipid ROS levels (n = 5). H. Quantitative analysis of oxidized-to-nonoxidized-lipid ratios by flow cytometry (n = 5). I. Immunofluorescence visualization of lipid peroxidation using C11-BODIPY probe staining. Scale bar = 10 μm. J. Assessment of changes in the mitochondrial membrane potential (Δψm) via JC-1 probe staining. Scale bar = 20 μm. K. Detection of mitochondrial lipid peroxidation using MitoPeDPP probe staining. Scale bar = 10 μm. L. Measurement of mitochondrial ROS by MitoSOX probe staining. Scale bar = 10 μm. M. Tumor volume measurements and H&E staining in orthotopic xenograft models (n = 8 animals per group). N. Quantitative analysis of tumor growth by fluorescence intensity and volumetric measurements (n = 8). O. Survival curves of nude mice bearing tumors derived from parental cells, TRIM25 single-knockout cells, or TRIM25/VDAC2 double-knockout cells (n = 8 animals per group). P. IHC analysis and quantitative scoring of TRIM25, VDAC2, 4-HNE, and ACSL4 expression in tumor tissues (n = 3). Scale bar = 50 μm. P values were calculated using two-tailed t tests (F, G, H, N and P), the log-rank Mantel‒Cox test (O) and the log-rank test, with adjustments for confounding factors via Cox regression (C). The data are presented as the means ± SDs\n\nFigure 5: Figure 5. Construction and in vitro evaluation of ANPSS(sgTRIM25) A. Schematic of disulfide-crosslinked nanoparticles encapsulating Cas9/sgRNA complexes synthesized via in situ radical polymerization, followed by Angiopep-2 (Ang) functionalization to generate ANP-conjugated ANPSS(sgTRIM25). B. Dynamic light scattering (DLS) analysis showing the particle size distribution of ANPSS(sgTRIM25). C. Zeta potential measurement of ANPSS(sgTRIM25) nanoparticles (n = 3). D. Fluorescence spectra confirming sulfo-cyanine5.5 (Cy5.5) labeling of ANPSS (sgTRIM25). E. Transmission electron microscopy (TEM) images demonstrating morphological changes in ANPSS (sgTRIM25) in saline with/without GSH. F. Agarose gel electrophoresis showing TRIM25 cleavage patterns by T7 endonuclease I (T7E1) under different treatment conditions. G. Schematic illustration of the genome editing mechanism of ANPSS (sgTRIM25). H. Sanger sequencing analysis identifying precise TRIM25 gene editing sites following ANPSS (sgTRIM25) treatment. I. Immunofluorescence comparison of cellular targeting efficiency between NPSS(sgTRIM25) and ANPSS(sgTRIM25). Scale bar = 10 μm. J. Live/dead cell viability assay after ANPSS(sgTRIM25) treatment (n = 5). Scale bar = 20 μm. K. Flow cytometric quantification of intracellular lipid ROS levels (n = 5). L. Flow cytometric analysis of oxidized vs. nonoxidized lipid ratios (n = 5). M. Immunofluorescence visualization of lipid peroxidation via C11-BODIPY probe staining. Scale bar = 10 μm. N. Assessment of mitochondrial membrane potential (Δψm) changes using JC-1 probe staining. Scale bar = 10 μm. O. Mitochondrial lipid peroxidation was detected through MitoPeDPP probe staining. P. Measurement of mitochondrial reactive oxygen species via MitoSOX probe staining. P values were calculated using two-tailed t tests (J, K and L). The data are presented as the means ± SDs"
      }
    ]
  },
  {
    "id": "PMC12813174_multi",
    "image": [
      "images/PMC12813174-f1.png",
      "images/PMC12813174-f3.png",
      "images/PMC12813174-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Expansion of the genetic and phenotypic spectrum of hereditary spastic paraplegia caused by ABHD16A gene variants: an integrated analysis based on novel variants and literature review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Brain MRI. (a) Corpus callosum of the patient at 6 months of age. (b) Corpus callosum of the patient at 21 months of age. (c–e) Abnormal signal intensity in the periventricular region of the patient at 21 months of age. (f-g) Corpus callosum of a healthy age-matched control.\n\nFigure 3: Figure 3. Sanger sequencing results: sanger sequencing showed that the patient carried c.119delA (p. His40Leufs * 49) from her father and c.559_562del (p. Pro187Cysfs * 29) from her mother.\n\nFigure 4: Figure 4. Statistical analysis of clinical manifestations in patients with ABHD16A gene variants."
      }
    ]
  },
  {
    "id": "PMC12859765_multi",
    "image": [
      "images/PMC12859765-f1.png",
      "images/PMC12859765-f2.png",
      "images/PMC12859765-f3.png",
      "images/PMC12859765-f4.png",
      "images/PMC12859765-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Phosphatidylcholine with C26:0 moiety, a precursor of a diagnostic marker for X-ALD, is synthesized by LPLAT10/LPEAT2\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Identification of an acyltransferase involved in the synthesis of VLCFA-PL. A: Screening of GPATs and LPLATs involved in the synthesis of PC species with a VLCFA moiety. ABCD1-deficient HeLa cells were incubated with free C26:0 FFA for 24 h. The amounts of three PC species (PC 42:0, PC 44:1, and PC 44:2) with C26:0 moiety were analyzed by LC-MS/MS. B: The amounts of phospholipid species in ABCD1 and LPLAT10-DKO HeLa cells. C: The amounts of PC species in ABCD1 and LPLAT6-DKO and ABCD1, LPLAT6, and LPLAT10-TKO HeLa cells. D: The amounts of PC species in ABCD1 and LPLAT10-DKO HeLa cells transfected with the LPLAT10 or LPLAT6 gene. E: The amounts of PC 44:1 in ABCD1 and GPAT2- (#1 and 2) or ABCD1 and GPAT3-DKO HeLa cells (#1–3). Note that each of the PC, PE, and SM species was analyzed quantitatively in positive ion mode, followed by MS3 analysis to obtain structural insights, including into acyl moieties in each phospholipid (e.g., Supplemental Fig. S2). Data represent the mean ± SD; statistical analysis was performed using one-way ANOVA, followed by Tukey's post hoc test (B) or Dunnett's test (vs. ABCD1 KO in C and E or vs. mock in D). ∗P < 0.01, ∗∗P < 0.001.\n\nFigure 2: Figure 2. PC with C26:0 moiety was selectively altered in LPLAT10-KO fibroblasts from X-ALD patients. The amount of PC (A), PE (B), SM (C), TG (D), and CE (E) species with C26:0-moiety as well as PC 34:1 (F) in fibroblasts. Fibroblasts from X-ALD patients were infected with lentivirus-expressing guide RNA targeting the LPLAT10 gene. Each of the lipid species in the total lipid fractions was analyzed by LC-MS/MS. Note that each of the PC, PE, SM, and TG species was analyzed quantitatively in positive ion mode, followed by MS3 analysis to obtain structural insights including into acyl moieties in each phospholipid or TG (e.g., Supplemental Fig. S2). Data represent the mean ± SD; statistical analysis was performed using Student’s t-test. ∗∗P < 0.001.\n\nFigure 3: Figure 3. The amounts of LPC species in LPLAT10-KO cells. A: The amounts of LPC with a C18:1- or C26:0 moiety in ABCD1 and LPLAT10-DKO cells. B: The amounts of C18:1-LPC and C26:0-LPC in fibroblasts from two X-ALD patients (#1 and 2) infected with lentivirus-expressing guide RNA targeting the LPLAT10 gene. Data represent the mean ± SD; statistical analysis was performed using one-way ANOVA, followed by the Tukey's post hoc test (A) or Student’s t-test (B). ∗∗P < 0.001.\n\nFigure 4: Figure 4. Substrate selectivity of LPLAT10 in vitro. A: LPLAT activity toward C26:0-CoA and 2–16:0-d31-LPC as donor and acceptor substrates, respectively. Membrane fractions were obtained from human embryonic kidney 293 cells transfected with each LPLAT gene. B: LPLAT activity toward 1-16:0-d31-LPC or 2–16:0-d31-LPC as acceptor substrates. C: Kinetic analysis of the LPLAT activity of LPLAT10 toward C26:0-CoA and 1-16:0-d31-LPC or 2–16:0-d31-LPC was conducted to determine the value of the apparent Km (nM) and Vmax (nmol/min/mg). D: LPLAT activity toward saturated fatty acyl-CoA and C20:4-CoA as donor substrates. 2–16:0-d31-LPC was used as an acceptor substrate. E: LPLAT activity of LPLAT10 toward 1-17:0-LPLs or 2-17:0-LPL as acceptor substrates. Data represent the mean ± SD; statistical analysis was performed using one-way ANOVA, followed by the Dunnett's test (vs. mock) in A or Student’s t-test in B–E. ∗P < 0.01 and ∗∗P < 0.001.\n\nFigure 5: Figure 5. Spatial configuration of the choline group of PC in LPLAT10. A: Multiple sequence alignment of human LPLAT8–10 and docking simulations of LPLAT10 and C26:0-PC. The AGPAT motif 4 and loop domain are represented in a box, whereas the W-X-W motif is represented in a neon-green box. Conserved residues are highlighted in yellow. Spatial relationship between the choline group of PC 26:0/16:0 and two tryptophan residues (W242 and W244) in LPLAT10. Magenta (motif 1, residues 129–134); cyan (motif 3, residues 201–206); yellow-green (motif 4, residues 224–230); and neon-green (W-X-W motif, residues 242–244). The bound PC 26:0/16:0 is shown as orange sticks. B: Immunoblotting analysis of LPLAT10 mutant. The membrane fractions expressing the wild-type (WT) and LPLAT10 mutant (W244A) were analyzed by Western blotting with anti-FLAG antibody. C: LPLAT activity of LPLAT10 mutant (W244A). LPLAT activity was analyzed using 1-acyl or 2-acyl-LPC as acceptor substrates. Data represent the mean ± SD; statistical analysis was performed using one-way ANOVA, followed by the Dunnett's test (vs. mock). ∗P < 0.01. AGPAT, 1-acylglycerol-3-phosphate O-acyltransferase."
      }
    ]
  },
  {
    "id": "PMC12859765_multi_2",
    "image": [
      "images/PMC12859765-f6.png",
      "images/PMC12859765-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Phosphatidylcholine with C26:0 moiety, a precursor of a diagnostic marker for X-ALD, is synthesized by LPLAT10/LPEAT2\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Chemical synthesis of C26:0 FFA-d4. A: C26:0 FFA was converted to the corresponding 8-aminoquinoline amide. Deuterium incorporation was first achieved selectively at the β-position under palladium catalysis, followed by the introduction of two deuterium atoms at the α-position using potassium carbonate. Finally, the resulting tetradeuterated amide was converted in two steps to furnish C26:0 FFA-d4. B: The ion spectra of the C26:0 FFA-d4 obtained by a high-resolution mass spectrometer. ca., circa; eq, equivalent; y., yield.\n\nFigure 7: Figure 7. Metabolic analysis of C26:0 FFA-d4 in ABCD1 and LPLAT10-DKO HeLa cells. A: Schematic illustration of the possible metabolic pathway of exogenously administered C26:0 FFA-d4. Note that the C26:0-d4 moiety is subjected to hydrolysis by lipases, resulting in C26:0 FFA-d4. B–K: The amounts of C26:0 FFA-d4 (B) and lipid species with C26:0-d4 moiety (C–K) present within HeLa cells. Data represent the mean ± SD; statistical analysis was performed using one-way ANOVA, followed by the Dunnett’s test (vs. ABCD1 KO). ∗P < 0.01, ∗∗P < 0.001. ACAT, acyl-CoA:cholesterol acyltransferase; CerS, ceramide synthase; DG, diacylglycerol; DGAT, diacylglycerol O-acyltransferase; DH-Sph, dihydrosphingosine; FC, free cholesterol; GSL, glycosphingolipid; MG, monoacylglycerol; MOGAT, monoacylglycerol O-acyltransferase; PAP, phosphatidic acid phosphatase; PLA2, phospholipase A2; PLC, phospholipase C."
      }
    ]
  },
  {
    "id": "PMC12886174_multi",
    "image": [
      "images/PMC12886174-f1.png",
      "images/PMC12886174-f2.png",
      "images/PMC12886174-f3.png",
      "images/PMC12886174-f4.png",
      "images/PMC12886174-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Grey Zone Project: Risk‐Based Classification of ABCD1 Variants in X‐Linked Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Spectrum of ABCD1 variants submitted to ClinVar and identification of VUS in ALD newborn screening. As of October 1, 2025, a total of 2003 variants of the ABCD1 gene had been submitted to the ClinVar database (https://www.ncbi.nlm.nih.gov/clinvar). (A) Of these 1565 (78%) are missense variants; 199 (10%) are frameshifts; 118 (5.9%) are nonsense variants; 56 (2.8%) are splice site variants; 19 (0.9%) are deletions of one or more exons, and 46 (2.3%) are indel variants. (B) The 1565 missense variants are classified as follows: Benign (B, 61, 4%), likely benign (LB, 144, 9%), variant of uncertain significance (VUS, 725, 46%), likely pathogenic (LP, 317, 21%), and pathogenic (P, 318, 21%). (C) With the expansion of newborn screening in the United States since 2014, there has been a rapid increase in the number of VUS identified, with more than 45% classified as a VUS in 2025 (shown are unique missense variants in ABCD1). (D) A graphic presentation of the total number of missense variants reported in ALD NBS program publications from Minnesota [19], North Carolina [20], Pennsylvania [25], Illinois [24], Nebraska [23], California [22], and Taiwan [26] shows that a high percentage of VUSs are identified in ALD newborn screening.\n\nFigure 2: Figure 2. Reclassification of ABCD1 missense variants using curated evidence from the ABCD1 Variant Registry. (A) Original ClinVar classifications of 1565 ABCD1 missense variants. Variants are categorized as benign (B), likely benign (LB), variant of uncertain significance (VUS), likely pathogenic (LP), or pathogenic (P). (B) Reclassified variants using evidence‐based criteria from the ABCD1 Variant Registry. Curated classifications resolve discrepancies by integrating functional data (e.g., peroxisomal VLCFA beta‐oxidation assays, protein expression studies) and clinical case reports.\n\nFigure 3: Figure 3. Receiver operating characteristic (ROC) curve and distribution of LPC(26:0) levels in ALD patients. (A) Dot plot shows the levels of LPC(26:0) measured in DBS or plasma in patients with AI and/or CALD (n = 118), and in patients aged > 55 years without AI and CALD (n = 27). (B) The ROC curve shows the ability to differentiate between patients with and without adrenal insufficiency (AI) or cerebral ALD (CALD) based on LPC(26:0) levels. The area under the curve (AUC) is 0.87. A cutoff of 177 nmol/L was selected to achieve 95.0% sensitivity in identifying patients with AI or CALD.\n\nFigure 4: Figure 4. LPC(26:0) concentrations in dried blood spots (DBS) and plasma from control subjects stratified by age (< 100 days and ≥ 100 days). Dot plots of LPC(26:0) concentrations measured in DBS (red) and plasma (yellow) from healthy control subjects. Subjects were divided into two age groups: Younger than 100 days and 100 days or older. Horizontal lines represent the median value for each group. LPC(26:0) concentrations are significantly higher in DBS during the first 100 days of life, reflecting the physiologically elevated red blood cell counts and associated higher LPC(26:0) content in early infancy.\n\nFigure 5: Figure 5. The challenge of VUSs is not unique to ALD. (A) Pie charts showing missense variant classifications in ClinVar for 18 frequently referenced genes in clinical genetics that span diverse disease areas. Blue indicates conflicting classifications; dark green, benign; light green, likely benign; grey, VUS, orange, likely pathogenic; and dark red, pathogenic. The numbers below the pie charts indicate the number of missense variants submitted to ClinVar for each gene. (B) Growth of variant classifications in ClinVar is shown as absolute numbers for each class. (C) The same data is also shown as a percentage of the total classifications. Conflicting classifications are not included. Benign (B) and likely benign (LB) are grouped, as are likely pathogenic (LP) and pathogenic (P) classifications."
      }
    ]
  },
  {
    "id": "PMC12905269_multi",
    "image": [
      "images/PMC12905269-f1.png",
      "images/PMC12905269-f2.png",
      "images/PMC12905269-f3.png",
      "images/PMC12905269-f4.png",
      "images/PMC12905269-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Loss of CTLH component MAEA impairs DNA repair and replication and leads to developmental delay\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Overview of the E3 ubiquitin ligase CRISPR screen. (B) DrugZ analysis of (A). Black symbols denote positive control proteins, while red symbols denote CTLH complex members. Diamonds and circles denote significant and non-significant hits, respectively. (C) MAEA domain map displaying CRISPR-induced edits in MAEA KO and MAEA hypomorph U2OS cells. (D) Clonogenic survival assays in MAEA KO U2OS cells using camptothecin and olaparib. (E) Clonogenic survival assays in HAP1 cell lines using camptothecin and olaparib. (F) Clonogenic survival assays using etoposide in the indicated U2OS cell lines. (D–F) n = 3 independent experiments; error bars denote mean ± SEM. KO knockout, HM hypomorph. Source data are available online for this figure.\n\nFigure 2: Figure 2. (A) Cα trace representation of the MAEA/RMND5A/UBE2H complex crystal structure (PDBID: 8PJN). Altered residues are shown as CPK spheres colored by atom (C – cyan, O – red, N – blue, S – yellow). The environments of each mutant site are shown in the expansion insets. (B) Domain map of MAEA with C > S mutations and clinical variants labeled. Red text indicates cells were complemented with these MAEA variants and tested in subsequent assays. (C–F) Clonogenic survival assays in the indicated U2OS cell lines using camptothecin or olaparib, as indicated. Data in (C–F) are the combined results of three independent experiments. Bars denote mean ± SEM. *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001. 1S = eGFP-MAEA1S (C340S), 2S = eGFP-MAEA2S (C314S, C317S), 3S = eGFP-MAEA3S (C314S, C317S, and C340S). Source data are available online for this figure.\n\nFigure 3: Figure 3. (A) TLR assay in U2OS cells with the indicated siRNAs (n = 3). Statistics were generated by performing an ordinary one-way ANOVA comparing each siRNA to the siLuc control. siCtIP and siLuc data are from five independent experiments. siMAEA and siRMND5A data come from three independent experiments. (B, C) Immunofluorescence-based quantification (B) and representative images (C) of chromatinized RPA in S phase cells treated with DMSO (1 h) or camptothecin (1 μM, 1 h). (D, E) Quantification (D) and representative images (E) of BrdU in U2OS cells treated with DMSO (1 h) or camptothecin (1 μM 1 h). (F, G) Representative images (F) and quantification (G) of RAD51 foci in S phase U2OS cells treated with DMSO or camptothecin. All quantifications of foci are the combined results of three independent experiments. Extended fluorescent images from (C, E) can be found in Fig.EV3C,D. For (B–G), P values were generated using a two-tailed Kruskal–Wallis test. γ is a measure of effect size. Data represents three independent experiments. Bars denote mean ±95% CI. *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001; exact P values can be found in Appendix Table S1. Scale bars = 20μm. Source data are available online for this figure.\n\nFigure 4: Figure 4. (A–C) Clonogenic survival assays in WT and MAEA KO cells with HU (A), aphidicolin (B), and ATRi (C). (D, E) Quantification of chromatin-associated γH2AX and RPA signal in WT and MAEA KO cells upon HU (D) or ATRi (E) treatment for the indicated times. (F) Quantification of chromatin-associated γH2AX and RPA signal upon ATRi treatment in MAEA KO U2OS cells complemented with the indicated eGFP expression constructs. Representative images are shown in Fig. EV4F. (G) DNA fiber assay measuring replication fork progression in eGFP Only (MAEA−/−) and eGFP-MAEAWT cells following treatment with camptothecin. Clonogenic data (A–C) are from three independent experiments. Statistics were generated using an ordinary two-way ANOVA. Bars represent the mean ± SEM. DNA fiber data are the combined result of three independent experiments. P values were generated by performing a two-tailed Kruskal–Wallis test. γ is a measure of effect size. Bars represent the mean ± 95% CI. *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001; exact P values can be found in Appendix Table S1. Scatter plots represent two independent experiments. HU hydroxyurea, ATRi ATR inhibitor (AZD3768). Source data are available online for this figure.\n\nFigure 5: Figure 5. (A, B) Quantification of replication tract lengths (A) and spontaneous replication fork stalling (B) in MAEA KO U2OS cells complemented with the indicated eGFP expression constructs. (C, D) Quantification of HU-induced replication fork stalling (C) and fork restart after HU wash-out (D) in MAEA KO U2OS cells complemented with the indicated eGFP expression constructs. (E) Quantification of replication fork degradation after HU treatment in MAEA KO U2OS cells complemented with the indicated eGFP expression constructs. (F) Quantification of replication fork degradation in primary fibroblasts from Patients 1, 2, and 4 versus a WT control fibroblast cell line following treatment with HU. The data were the combined result of three independent experiments. P values were generated by performing a two-tailed Kruskal–Wallis test on scatter plots and an ordinary one-way ANOVA on histograms. γ is a measure of effect size. Bars represent the mean ± 95% CI. *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001; exact P values can be found in Appendix Table S1. HU hydroxyurea, KO knockout. Source data are available online for this figure."
      }
    ]
  },
  {
    "id": "PMC12905269_multi_2",
    "image": [
      "images/PMC12905269-f6.png",
      "images/PMC12905269-f7.png",
      "images/PMC12905269-f8.png",
      "images/PMC12905269-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Loss of CTLH component MAEA impairs DNA repair and replication and leads to developmental delay\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Immunoblot for MAEA in the indicated U2OS cell lines; n = 2 independent experiments. (B) TIDE analysis of the sgRNA target site in MAEA KO and MAEA HM cells. (C) Sanger trace analysis of the sgRNA target site in MAEA KO and HM cells. (D) Cell cycle analysis of MAEA KO and HM cells. (E, F) Representative images of untreated WT and MAEA-deficient U2OS (E) and HAP1 (F) cells. (G) Immunoblot for MAEA in U2OS following siRNA transfection; n = 3 independent experiments. (H, I) Representative images (H) and colony counts (I) of U2OS cells with or without siRNA-mediated MAEA depletion. (J) The average colony size of siRNA-transfected U2OS cells at 500 cells per well. (K) Total area coverage of U2OS colonies following siRNA transfection. (I–K) Bars represent the mean ± SEM. KO knockout, HM hypomorph. Source data are available online for this figure.\n\nFigure 7: Figure 7. (A) Aminode analysis (Chang et al, 2018) of MAEA, with C > S mutations annotated. The red line represents conservation across species. Species compared in the analysis are listed in the box. (B) Immunoblot assessing expression of eGFP-MAEA constructs; n = 2 independent experiments. Source data are available online for this figure.\n\nFigure 8: Figure 8. (A) Immunoblot against the indicated proteins with the indicated siRNAs; n = 3 independent experiments. (B) Quantification of BrdU immunofluorescence, after camptothecin treatment in the presence or absence of siRNA-mediated CtIP depletion. (C, D) Representative images from Fig. 3C,E expanded to include γH2AX staining, indicative of the S phase cells. (E) Immunoblot against RAD51 in WT and MAEA KO U2OS cells. (F) Immunoblot for indicated proteins in U2OS WT or MAEA KO cells. (E, F) are each n = 3 independent experiments. P values were generated by performing a two-tailed Kruskal–Wallis test. γ is a measure of effect size. The data were the combined results of two independent experiments. Bars denote mean ± 95% CI. *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001; exact P values can be found in Appendix Table S1. Scale bars = 20 μm. NT non-treated, KO knockout. Source data are available online for this figure.\n\nFigure 9: Figure 9. (A) Immunoblot for MAEA depletion in polyclonal SH-SY5Y cells following CRISPR-Cas9 editing; n = 3 independent experiments. (B) Quantification and (C) representative images of BrdU in SH-SY5Y cells treated with DMSO (1 h) or camptothecin (1 μΜ, 1 h). (D) Quantification and (E) representative images of RAD51 foci in S-phase SH-SY5Y cells treated with DMSO or camptothecin. Bars in (B, D) represent median and interquartile range. P values were generated by performing a two-tailed Kruskal–Wallis test. γ is a measure of effect size. The data represent three independent experiments. *P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001, ****P ≤ 0.0001; exact P values can be found in Appendix Table S1. Scale bars = 10 μm. For (B, C), outliers were removed using ROUT analysis (Q = 1%). (F) Representative images of Fig. 5F. Source data are available online for this figure."
      }
    ]
  },
  {
    "id": "PMC12927719_multi",
    "image": [
      "images/PMC12927719-f1.png",
      "images/PMC12927719-f2.png",
      "images/PMC12927719-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Prenatal Diagnosis and Genotype-Phenotype Correlation in 8q21.11 Microdeletion Syndrome: A Case Report\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The yellow arrow indicates the presence of increased nuchal translucency.\n\nFigure 2: Figure 2. Array comparative genomic hybridization (aCGH) result of the fetus showing a 5.07 Mb deletion at 8q21.11–q21.13 (chr8:77,491,659–82,561,762, GRCh37/hg19) encompassing 12 OMIM genes.\n\nFigure 3: Figure 3. Schematic representation of the 8q21.11 microdeletion region in the fetus, overlapping pathogenic or likely pathogenic deletions (red bars) reported in the DECIPHER database. The shared overlap involving the ZFHX4 gene (light blue vertical bar) is highlighted."
      }
    ]
  },
  {
    "id": "PMC12930096_multi",
    "image": [
      "images/PMC12930096-f1.png",
      "images/PMC12930096-f2.png",
      "images/PMC12930096-f3.png",
      "images/PMC12930096-f4.png",
      "images/PMC12930096-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mitochondrial‐derived peptides MOTS‐c and humanin attenuate dexamethasone‐induced atrophy in human skeletal muscle cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MOTS‐c and HNG mitigate dexamethasone‐induced myotube atrophy. Primary human skeletal muscle myotubes were treated with vehicle (Control), 10 μM S14G‐humanin (HNG), 10 μM mitochondrial open reading frame of the 12S rRNA‐c (MOTS‐c), 10 μM dexamethasone (DEXA), or co‐treated with DEXA and either HNG or MOTS‐c. (a) Representative immunofluorescence images of myotubes stained for desmin (green, Alexa Fluor 488) to visualize myotube structure, with nuclei counterstained with DAPI (blue), a red scale bar represents 100 μm. (b) Quantification of myotube area fraction, calculated as the percentage of the total image area positive for desmin staining. (c) Quantification of the fusion index, calculated as the percentage of nuclei within myotubes (containing ≥3 nuclei) relative to the total number of nuclei.\n\nFigure 2: Figure 2. mRNA levels of MURF1 (a), MAFbx (b), and myostatin (c). Primary human skeletal muscle myotubes were treated with vehicle (Control), 10 μM S14G‐humanin (HNG), 10 μM mitochondrial open reading frame of the 12S rRNA‐c (MOTS‐c), 10 μM dexamethasone (DEXA), or co‐treated with DEXA and either HNG or MOTS‐c. Data are presented as fold change relative to the control group and are shown as mean ± SD (N = 3). MAFbx, muscle atrophy F‐box; MURF1, muscle‐specific RING finger protein 1.\n\nFigure 3: Figure 3. mRNA levels of PGC1α (a) and TFAM (b). Primary human skeletal muscle myotubes were treated with vehicle (Control), 10 μM S14G‐humanin (HNG), 10 μM mitochondrial open reading frame of the 12S rRNA‐c (MOTS‐c), 10 μM dexamethasone (DEXA), or co‐treated with DEXA and either HNG or MOTS‐c. Data are presented as fold change relative to the control group and are shown as mean ± SD (N = 3). PGC1α, peroxisome proliferator‐activated receptor‐gamma coactivator‐1 alpha: TFAM, mitochondrial transcription factor A.\n\nFigure 4: Figure 4. Protein expression of mitochondrial electron transport chain complexes (ETC), Complex I (a), Complex II (b), Complex III (c), Complex IV (d) and Complex V (e), all normalized to eEF2. Primary human skeletal muscle myotubes were treated with vehicle (Control), 10 μM S14G‐humanin (HNG), 10 μM mitochondrial open reading frame of the 12S rRNA‐c (MOTS‐c), 10 μM dexamethasone (DEXA), or co‐treated with DEXA and either HNG or MOTS‐c. Results are presented as mean ± SD (N = 3).\n\nFigure 5: Figure 5. Protein expression of p‐Akt normalized to total Akt (a), p‐STAT3 normalized to total STAT3 (b), p‐NFκB normalized to total NFκB (c), p‐p38 normalized to total p38 (d), and caspase 3 normalized to eEF2 (e). Primary human skeletal muscle myotubes were treated with vehicle (Control), 10 μM S14G‐humanin (HNG), 10 μM mitochondrial open reading frame of the 12S rRNA‐c (MOTS‐c), 10 μM dexamethasone (DEXA), or co‐treated with DEXA and either HNG or MOTS‐c. Results are presented as mean ± SD (N = 3)."
      }
    ]
  },
  {
    "id": "PMC12933876_multi",
    "image": [
      "images/PMC12933876-f1.png",
      "images/PMC12933876-f2.png",
      "images/PMC12933876-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Comprehensive Clinical, Diagnostic, and In Silico Assessment of a Novel 1p36.33p36.32 Copy Number Variant\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clinical photographs, brain MRI and CT scan, and array‐CGH results of the patient with 1p36.33 duplication. Clinical photographs showing facial dysmorphism (A), surgically corrected right clubfoot (B), and widely spaced teeth (C). The axial brain CT scan shows left‐side ventriculomegaly without any calcification (D), and the T1 (E) and T2 (F, G, H) sequences of brain MRI show ventriculomegaly especially on the left side with a mild abnormality of cortical gyration on the frontal region. Array‐CGH results indicate a duplication at the 1p36.33p36.32 (GRCh37/hg19; chr1:834,101–3,070,509) (I); genomic coordinates elsewhere in the manuscript are reported on (GRCh38/hg38).\n\nFigure 2: Figure 2. Protein–protein interaction (PPI) network of the 27 protein‐coding genes within the duplicated region, constructed using STRING and visualised in Cytoscape. Nodes represent genes; edges represent predicted interactions. Hub genes identified by MCODE are highlighted in red.\n\nFigure 3: Figure 3. Phenolyzer‐based prioritisation of genes within the duplicated region using 13 patient‐specific phenotypes (HPO terms). Bars represent the Phenolyzer prioritisation scores for each gene. GNB1 received the highest score among all 89 candidate genes, suggesting its strong association with the observed clinical features. HI, Haploinsufficiency score; RVIS, Residual Variation Intolerance Score."
      }
    ]
  },
  {
    "id": "PMC12961334_multi",
    "image": [
      "images/PMC12961334-f1.png",
      "images/PMC12961334-f2.png",
      "images/PMC12961334-f3.png",
      "images/PMC12961334-f4.png",
      "images/PMC12961334-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"RNF90 promotes hepatic steatosis by degrading CPT1α to suppress fatty acid oxidation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. KLF5 mediates RNF90 expression upregulation in the liver of hepatic steatosis. A, representative H&E and Oil red O staining images of liver tissues from mice fed the indicated diets (n = 5). B–C, western blot (B) and quantitative analysis (C) of RNF90 and KLF5 protein expression in liver tissues from the mice described in (A) (n = 4). D, RT-qPCR analysis of RNF90 mRNA expression in mouse liver tissues (12 W NCD, HFD: n = 8; ob/ob: n = 6; 19 W NCD, HFHC: n = 10). E–H, RT-qPCR (E, G; n = 4) and western blot (F, H; n = 3) analyses of the indicated genes’ expressions in POA-treated HepG2 and AML12 cells at different time points. I, schematic of RNF90 gene promoter regions analysis via NCBI’s in silico tools. J, predicted conserved KLF5 binding sites via the JASPAR database. K–L, analysis of RNF90 mRNA (K; n = 4) and protein (L; n = 3) expression in HEK293T cells with KLF5 overexpression (leftpanel) and KLF5 knockdown (rightpanel). M, dual-luciferase reporter assay analysis of RNF90 promoter activity in KLF5-overexpressed (leftpanel) or KLF5-knockdown (rightpanel) HEK293T cells (n = 4). N, dual luciferase reporter assay for analyzing the effect of KLF5 on truncated RNF90 promoter mutants in HEK293T cells (n = 4). O, ChIP-PCR analysis of KLF5 enrichment at its potential binding sites in RNF90 promoter in POA-treated HepG2 cells (n = 3); schematic shows ChIP-PCR primer positions (black arrows). Data are presented as the mean ± SD, and statistical significance was analyzed by two-tailed t test (C, N, and O) and one-way ANOVA followed by Tukey’s post hoc test (D, E, G, K, and M). The exact p values are shown in each graph. ChIP-PCR, chromatin immunoprecipitation PCR; HFD, high-fat diet; HFHC, high-fat, high fructose and high-cholesterol; KLF5, Kruppel-like factor 5; NCBI, National Center for Biotechnology Information; NCD, normal chow diet; POA, a mixture of palmitic acid and oleic acid; RT-qPCR, quantitative real-time PCR.\n\nFigure 2: Figure 2. RNF90 aggravates hepatic steatosis in vitro. A, RT-qPCR (n = 4) and western blot (n = 3) analyses of RNF90 mRNA and protein expression in indicated HepG2 stable cell lines. B–C, Oil red O staining (B) and TG content measurement (C) in BSA- or POA-treated RNF90-modified HepG2 stable cell lines (n = 4). D–E, validation of RNF90 knockdown efficiency at the mRNA (D, n = 4) and protein levels (E, n = 3) in AML12 cells stably expressing shRNF90 or control shRNA. F–G, Oil red O staining (F) and TG content measurement (G) in BSA- or POA-treated AML12 stable cell lines with stable RNF90 knockdown (n = 4). H–I, RT-qPCR (H, n = 4) and western blot (I, n = 3) analyses of RNF90 mRNA and protein expression in HepG2 and AML12 cells stably overexpressing RNF90 wildtype or its E3 ligase-deficient mutant (RNF90-DM). J–K, Oil red O staining (J) and TG content detection (K) in BSA- or POA-treated HepG2/AML12 cells stably overexpressing RNF90 wildtype or RNF90-DM cells (n = 4). Data are presented as the mean ± SD, and statistical significance was analyzed by one-way ANOVA followed by Tukey’s post hoc test (A, C, D, G, H, and K). The exact p values are indicated in each graph. BSA, bovine serum albumin; POA, a mixture of palmitic acid and oleic acid; RT-qPCR, quantitative real-time PCR; shRNF90, shRNA targeting RNF90; TG, triglyceride.\n\nFigure 3: Figure 3. RNF90 interacts with CPT1α and promotes its K48-linked ubiquitination. A, mass spectral information of RNF90 and its interacting protein CPT1α from the RNF90-IP/MS assay. B, representative immunofluorescence staining images showing the subcellular localization of RNF90 and CPT1α protein in L02 cells. C, quantitative analysis of the colocalization between RNF90 and CPT1α in the indicated regions from panel B. D–E, co-IP analysis to detect the interaction between RNF90 and CPT1α proteins using exogenous-specific antibodies (D) and endogenous-specific antibodies (E) in HEK293T cells. F–G, measurement of CPT1α ubiquitination levels in HEK293T cells cotransfected with Myc-Ub, HA-CPT1α, and either Flag-tagged RNF90 wildtype or its E3 ligase deficiency mutant plasmids (F) or with Myc-Ub, HA-CPT1α, and RNF90 knockdown plasmids (G). H–I, analysis of the ubiquitination type of CPT1α catalyzed by RNF90 in HEK293T cells cotransfected with HA- CPT1α, Flag-RNF90, and the indicated Myc-Ub-K48 mutants (H) or Myc-Ub-K63 mutants (I). J, detection of the ubiquitination sites of CPT1α in HEK293T cells cotransfected with Myc-Ub, Flag-RNF90 and the indicated HA-CPT1α mutant plasmids. co-IP, co-immunoprecipitation; CPT1α, carnitine palmitoyltransferase 1α; HA, hemagglutinin.\n\nFigure 4: Figure 4. RNF90 regulates CPT1α stability in an E3 ligase activity-dependent manner. A, immunoblotting analysis of CPT1α protein expression in HEK293T cells cotransfected with HA-CPT1α and increasing concentrations of Flag-tagged RNF90 wildtype (RNF90-WT) or its E3 ligase-deficient mutant (RNF90-DM) plasmids. B–D, immunoblotting (B, C) and densitometric quantification (D) analyses showing the effect of RNF90-WT or RNF90-DM on CPT1α protein half-life by CHX chase assay. E, immunoblotting analysis of CPT1α protein expression in HEK293T cells cotransfected with increasing amounts of RNF90 plasmid and either HA-tagged CPT1α-WT or HA-tagged ubiquitination-deficient CPT1α mutant (CPT1α-K195R) plasmids. F–G, immunoblotting (F) and quantification (G) analyses of CPT1α-WT or CPT1α-K195R protein half-life as regulated by RNF90 in HEK293T cells. H–I, immunoblotting (H) and quantification (I) analyses of RNF90 knockdown on CPT1α protein half-life in CHX-treated HEK293T cells. J, immunoblotting analysis to delineate the degradation pathway of CPT1α protein in HEK293T cells transfected with the indicated plasmids, and subsequently treated with CHX alone or in combination with MG132, CQ, or NH4Cl prior to cell harvest. K, western blot analysis of CPT1α protein expression in POA-treated HepG2 and AML12 cells, including RNF90-WT/DM-overexpressing stable lines, RNF90-knockdown stable lines, and their respective control cells. L, measurement of cellular FAO activity in BSA- or POA-treated HepG2 cells with stable RNF90 overexpression or knockdown. Data are presented as the mean ± SD, and statistical significance was analyzed by two-tailed t test (D and G) and one-way ANOVA followed by Tukey’s post hoc test (I and L). The exact p values are indicated in each graph. BSA, bovine serum albumin; CHX, cycloheximide; CPT1α, carnitine palmitoyltransferase 1α; CQ, chloroquine; FAO, fatty acid oxidation; POA, a mixture of palmitic acid and oleic acid.\n\nFigure 5: Figure 5. Hepatic RNF90 deficiency alleviates diet-induced hepatic steatosis in mice by enhancing FAO. A–C, body weight (A), liver weight (B), liver weight-to-body weight ratio (C) in RNF90-HKO and RNF90-Flox mice at the indicated time points after feeding with NCD or HFD (n = 8). D–E, representative images of H&E staining and Oil red O staining (D), and quantitative analysis of Oil red O positive area (E) in liver tissues from RNF90-HKO and RNF90-Flox mice fed a NCD or HFD for 14 weeks (n = 5). F, measurement of hepatic TG, TC contents in RNF90-HKO and RNF90-Flox mice after 14 weeks of HFD feeding (n = 8). G–H, representative images of H&E and Oil red O staining (G), and quantitative analysis of Oil red O-stained positive area (H) in liver tissues from RNF90-HKO and RNF90-Flox mice fed a NCD or HFHC for 19 weeks (n = 5). I–J, detection of hepatic TG (I) and TC (J) contents in RNF90-HKO and RNF90-Flox mice after 19 weeks of HFHC feeding (n = 8). K, immunoblotting analysis of CPT1α protein expression in liver tissues from RNF90-HKO and RNF90-Flox mice fed a HFD for 14 weeks or HFHC for 19 weeks (n = 4). L, detection of FAO activity in liver tissues from RNF90-HKO and RNF90-Flox mice fed a HFD for 14 weeks (leftpanel) or HFHC for 19 weeks (rightpanel) (n = 8). M, RT-qPCR analysis of HMGCS2 mRNA expression in liver tissues from RNF90-HKO and RNF90-Flox mice fed a HFD or HFHC (n = 8). N–O, measurement of liver β-HB (N) and ATP (O) contents in RNF90-HKO and RNF90-Flox fed a HFD or HFHC (n = 8). Statistical significance was analyzed by two-tailed t test (E, F, H, I, J, and L–O) and one-way ANOVA followed by Tukey’s post hoc test (A–C). The exact p values are indicated in each graph. β-HB, β-hydroxybutyric acid; CPT1α, carnitine palmitoyltransferase 1α; FAO, fatty acid oxidation; HFD, high-fat diet; HFHC, high-fat, high fructose and high-cholesterol; HMGCS2, hydroxyl methyl glutaryl-CoA synthase 2; NCD, normal chow diet; RT-qPCR, quantitative real-time PCR; TG, triglyceride."
      }
    ]
  },
  {
    "id": "PMC12961334_multi_2",
    "image": [
      "images/PMC12961334-f6.png",
      "images/PMC12961334-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"RNF90 promotes hepatic steatosis by degrading CPT1α to suppress fatty acid oxidation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Hepatic RNF90 overexpression suppresses FAO and exacerbates hepatic lipid accumulation. A, representative EGFP fluorescence images of freshly isolated liver tissues from mice injected with AAV8 using a small animal imaging device. B–C, immunoblotting (B) and densitometric quantification (C) of RNF90, CPT1α protein expression in liver tissues from HFD- or HFHC-fed mice injected with AAV8. β-actin was used as control, and relative protein levels were quantified by normalizing target band intensities to β-actin using Image J software (n = 4). D–E, representative images of H&E staining and Oil red O staining (D), and quantitative analysis of Oil red O-stained positive area (E) in liver tissues from AAV8-injected mice fed a HFD (14 weeks) or HFHC (19 weeks) (n = 5). F–G, measurements of liver TG, TC contents (F), and FAO activity (G) in AAV8-injected mice fed a HFD (14 weeks) or HFHC (19 weeks) (n = 8). H, RT-qPCR analysis of HMGCS2 mRNA expression in liver tissues from HFD- or HFHC-fed mice injected with AAV8. I–J, measurement of liver β-HB (I) and ATP (J) contents in AAV8-injected mice fed a HFD (14 weeks) or HFHC (19 weeks) (n = 8). Statistical significance was analyzed by one-way ANOVA followed by Tukey’s post hoc test (D, F–J). The exact p values are indicated in each graph. β-HB, β-hydroxybutyric acid; AAV8, adeno-associated virus serotype 8; CPT1α, carnitine palmitoyltransferase 1α; EGFP, enhanced green fluorescent protein; FAO, fatty acid oxidation; HFD, high-fat diet; HFHC, high-fat, high fructose and high-cholesterol; HMGCS2, hydroxyl methyl glutaryl-CoA synthase 2; RT-qPCR, quantitative real-time PCR; TG, triglyceride.\n\nFigure 7: Figure 7. CPT1α is essential for RNF90-mediated regulation of FAO and steatosis in hepatocytes. A, HepG2 cells stably overexpressing Flag-tagged RNF90 were transfected with either HA-tagged CPT1α plasmid or empty control plasmid. At 12 h post transfection, cells were treated with POA for 24 h, then harvested for immunoblotting analysis of Flag-tagged RNF90 and HA-tagged CPT1α protein expression, with β-actin as the loading control. B, measurement of FAO activity in HepG2 cells treated as described in (A) (n = 4). C–D, representative Oil red O staining images, quantitative analysis of Oil red O-positive area (C), and TG content quantification (D) in HepG2 cells treated as described in (A) (n = 4). E, HepG2-shRNF90-3# cells were transfected with shCPT1α plasmid or empty control plasmid. After 12 h of transfection, cells were treated with POA for 24 h, then harvested for immunoblotting analysis of RNF90 and CPT1α protein expression, with β-actin as the loading control. F, measurement of FAO activity in HepG2 cells treated as described in (E) (n = 4). G–H, representative Oil red O staining images, quantitative analysis of Oil red O-positive area (G) and TG content quantification (H) in HepG2 cells treated as described in (E) (n = 4). I, schematic diagram illustrating the underlying molecular mechanism by which the KLF5/RNF90/CPT1α axis promotes hepatic steatosis by suppressing fatty acid oxidation. Data are presented as the mean ± SD, and statistical significance was analyzed by one-way ANOVA followed by Tukey’s post hoc test (B–D, F–H). The exact p values are indicated in each graph. CPT1α, carnitine palmitoyltransferase 1α; FAO, fatty acid oxidation; KLF5, Kruppel-like factor 5; POA, a mixture of palmitic acid and oleic acid; shRNF90, shRNA targeting RNF90; TG, triglyceride"
      }
    ]
  },
  {
    "id": "PMC12961535_multi",
    "image": [
      "images/PMC12961535-f1.png",
      "images/PMC12961535-f2.png",
      "images/PMC12961535-f3.png",
      "images/PMC12961535-f4.png",
      "images/PMC12961535-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Pioglitazone Ameliorates Mitochondrial Oxidative Stress and Inflammation via AMPK‐Dependent Inhibition of Mitochondrial Fission in Leigh Syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Ndufs4 KO induces mitochondrial ROS generation, inflammation, and aberrant mitochondrial dynamics in mNPCs. (A) Measurement of mitochondrial morphology and ROS level labelled by MitoTracker Green and MitoSox Red. Scar bar = 10 μm; for inset, scar bar = 2 μm. (B) QPCR analysis of COX‐2 mRNA level relative to Ndufs4 WT group. (C) QPCR analysis of the mRNA level of mitochondrial‐biogenesis‐related genes relative to Ndufs4 WT group. (D) Western blot analysis of Mfn‐2, Opa‐1, and Drp‐1 relative to Ndufs4 WT group. VDAC is taken as a loading control (i, ii). Data are presented as mean ± SEM of three independent experiments. *p < 0.05; **p < 0.01.\n\nFigure 2: Figure 2. Mdivi‐1 inhibition of Drp‐1 expression reduces mitochondrial ROS and inflammation in mNPCs. (A) Mitochondrial ROS level relative to Ndufs4 WT group 24 h after treatment. (B) QPCR analysis of COX‐2 mRNA level relative to Ndufs4 WT group 24 h after treatment. Data are presented as mean ± SEM of three independent experiments. *p < 0.05; **p < 0.01.\n\nFigure 3: Figure 3. Pioglitazone attenuates mitochondrial ROS generation, inflammation, and ameliorates mitochondrial dynamics in mNPCs. (A) Dose‐dependent inhibition of COX‐2 mRNA level by pioglitazone (PIO) and DMSO relative to Ndufs4 WT group 24 h after treatment. (B) Mitochondrial ROS level relative to Ndufs4 WT group 24 h after treatment. (C) (i) Western blot of Opa‐1, Mfn‐2, Drp‐1, and VDAC 24 h after treatment. (ii–iv) Quantification represents the level of Opa‐1, Mfn‐2, and Drp‐1 normalised to VDAC relative to Ndufs4 WT group. Data are presented as mean ± SEM of the three independent experiments. *p < 0.05; **p < 0.01; ns, not significant.\n\nFigure 4: Figure 4. AMPK activation mediates pioglitazone's rescue of aberrant mitochondrial dynamics in Ndufs4 KO mNPCs. (A) (i) Western blot of phospho‐AMPKα (Thr172) (pAMPKα) and AMPKα 24 h after treatment. (ii) Quantification represents the ratio of pAMPKα/AMPKα relative to Ndufs4 WT group. (B) (i) Western blot of Opa‐1, Mfn‐2, and Drp‐1 24 h after treatment (compound C‐1 μM). (ii–iv) Quantification represents the levels of Opa‐1, Mfn‐2, and Drp‐1 normalised to β‐Actin. (C) Measurement of mitochondrial ROS relative to Ndufs4 WT group 24 h after treatment. (D) QPCR analysis of COX‐2 mRNA level relative to Ndufs4 WT group 24 h after treatment. Data are presented as mean ± SEM of three independent experiments. *p < 0.05; **p < 0.01; ns, not significant; Comp C, compound C.\n\nFigure 5: Figure 5. Pioglitazone improves motor function and prolongs lifespan of Ndufs4 KO mice. (A) Schematic chart showing the timeline of animal neurobehavioral tests during D25 to D55. (B) Rotarod analysis for different groups at D30, D40, and D50 (n ≥ 6 for each group). (C) Ratio of non‐clasing/clasing between vehicle‐treated (i) and pioglitazone‐treated (ii) Ndufs4 KO mice (n = 15 for each group). (D) Kaplan–Meier survival curve (n = 9 for each group). Significance is assessed by the log rank test. (E) Comparison of body size between vehicle‐treated (KO + V) and pioglitazone‐treated (KO + P) Ndufs4 KO mice at D55. (F) Body weight monitoring of different groups of mice. Data are presented as mean ± SEM. *p < 0.05; **p < 0.01; ns, not significant."
      }
    ]
  },
  {
    "id": "PMC12961535_multi_2",
    "image": [
      "images/PMC12961535-f6.png",
      "images/PMC12961535-f7.png",
      "images/PMC12961535-f8.png",
      "images/PMC12961535-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Pioglitazone Ameliorates Mitochondrial Oxidative Stress and Inflammation via AMPK‐Dependent Inhibition of Mitochondrial Fission in Leigh Syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Pioglitazone alleviates neuroinflammation in the cerebellum of Ndufs4 KO mice. (A–D) Representative immunostaining for glia activation by Iba‐1 and GFAP in the cerebellum at D55 among different groups (n = 6 for each group). Scar bar = 500 μm. (E–H) High magnification of local area in the cerebellum. Scar bar = 200 μm. (I–L) Morphological change of microglia in the cerebellum. Scar bar = 50 μm.\n\nFigure 7: Figure 7. Pioglitazone enhances the mitochondrial fusion and increases MRC subunits expression. (A) EM of mitochondrial ultrastructure in mice brain (D55) among different groups at lower (i–iv) and higher (v–viii) magnification (n = 4 for each group). Scale bar = 500 nm; scale bar of the inset = 100 nm. (B) Western blot analysis of MRC subunits expression relative to Ndufs4 WT group. VDAC is taken as a loading control. Data are presented as mean ± SEM of three independent experiments. *p < 0.05; **p < 0.01; ns, not significant.\n\nFigure 8: Figure 8. Pioglitazone‐induced AMPK activation inhibits mitochondrial fission, ROS generation and inflammation in Ndufs4 KO mice. (A) Representative immunoblot and quantitative analysis of mitochondrial dynamics related proteins of Opa‐1, Drp‐1 and Mfn‐2 (n = 6 for each group) (i–iv). (B) Representative images and quantification of ROS generation relative to Ndufs4 WT group measured by DHE staining in cerebellum lobes (n ≥ 5 for each group). (C) (i) QPCR analysis of COX‐2 mRNA level relative to Ndufs4 WT group (n = 6 for each group). (ii) ELISA was performed to measure the inflammatory cytokine IL‐1β in brain tissue (n ≥ 3). (D) Representative immunoblot and quantitative analysis of pAMPKα expression. Quantification of pAMPKα was normalised to AMPKα (n = 6 for each group). Data are presented as mean ± SEM. *p < 0.05; **p < 0.01; ns, not significant. E. ATP detection in brain tissue (n ≥ 3).\n\nFigure 9: Figure 9. Schematic of the proposed mechanism that pioglitazone inhibits mitochondrial ROS and inflammation in LS. Pioglitazone suppresses mitochondrial excessive ROS generation and COX‐2 level through inhibition of Drp‐1 mediated mitochondrial fission in an AMPK‐dependent manner in LS."
      }
    ]
  },
  {
    "id": "PMC12962169_multi",
    "image": [
      "images/PMC12962169-f1.png",
      "images/PMC12962169-f2.png",
      "images/PMC12962169-f3.png",
      "images/PMC12962169-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Emerging biologic modalities for targeted protein degradation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Comparison of small-molecule and biologic degraders. Overview of key distinctions between biologic-based and small-molecule degraders.\n\nFigure 2: Figure 2. Overview of biologic degrader designs and strategies. A, multisubunit E3 ligases. Full-length or truncated multicomponent E3 ligases (e.g., SPOP, von Hippel–Lindau [VHL], CRBN, β-TrCP) can be fused to a target-binding ligand to recruit neosubstrates for degradation. B, single-subunit E3 ligases. E3 ligases such as NEDD4 or CHIP can be used in biologic degraders, in which truncated variants retain catalytic activity, whereas their substrate-recognition domains are replaced with target-binding modules. C, antibody ligands. Multidomain protein complexes that recognize specific antigens via their variable heavy and light chains. D, monobody ligands. Synthetic single-domain β-sandwich proteins derived from the fibronectin type III (FN3) domain, engineered for high affinity and specificity through loop diversification. E, nanobody ligands. Camelid-derived single-variable heavy-chain domains capable of binding deep or cryptic surface pockets on target proteins. F, designed ankyrin repeat proteins (DARPins). Human-derived, single-domain scaffolds composed of stacked ankyrin motifs that can be engineered for high-affinity or multispecific binding. CRBN, cereblon.\n\nFigure 3: Figure 3. TRIM-Away and TRIMbody-Away strategies for targeted protein degradation. A, TRIM-Away mechanism. TRIM21 recognizes the Fc domain of antibodies and directs degradation of both the antibody and its bound substrate. Exogenous introduction of antibodies against neosubstrates can induce TRIM21-dependent target degradation, a strategy termed “TRIM-Away.” B, TRIMbody-Away mechanism. Cells with low TRIM21 expression can be transfected with engineered TRIM21 variants wherein the Fc recognition domains are replaced with target-binding ligands (TRIMbodies) to direct target degradation. TRIM, tripartite motif.\n\nFigure 4: Figure 4. Peptide-based biologic degraders. A, peptide as E3 ligase recruiter. A peptide ligand is used to recruit the E3 ligase in the design of peptide-based PROTACs (p-PROTACs). B, peptide as POI recruiter. A peptide ligand derived from a target-binding motif engages the POI to promote its ubiquitination. C, peptide as bivalent recruiter. Two distinct peptide ligands are linked to simultaneously engage both the E3 ligase and the POI, eliminating the need for small-molecule components. D, degron-based degraders. A degron sequence fused to a target ligand is recognized by an E3 ligase upon POI binding, leading to ubiquitination and proteasomal degradation. E, HYDRACs (HYbrid DegRAding Copolymer). Polymer-linked assemblies of multiple peptide ligands for the E3 ligase and POI promote multivalent engagement and efficient target degradation. POI, protein of interest; PROTAC, proteolysis-targeting chimera."
      }
    ]
  },
  {
    "id": "PMC12994458_multi",
    "image": [
      "images/PMC12994458-f1.png",
      "images/PMC12994458-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Tumor-muscle communication in cancer-associated cachexia (Review)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Main cell signaling pathways involved in myofibrillar protein degradation in cancer-associated cachexia. BMP, bone morphogenetic protein; BMPR I/II, bone morphogenetic protein receptor type I/type II; SMAD1/5/8, mothers against decapentaplegic homologs 1, 5 and 8; SMAD4, mothers against decapentaplegic homolog 4; IL-1R1, interleukin-1 receptor type 1; MyD88, myeloid differentiation primary response protein 88; IRAK1/4, IL-1R-associated kinase 1/4; TRAF6, TNF receptor-associated factor 6; IKK, IκB kinase; IκB, inhibitor of κB; NF-κB, nuclear factor κ-light-chain-enhancer of activated B cells; TNF-α, tumor necrosis factor α; TNFR1, TNF receptor 1; TRADD, TNF receptor-associated death domain; RIP, receptor-interacting protein; TRAF5, TNF receptor-associated factor 5; TAB2/3, TAK1-binding protein 2/3; TAK1, transforming growth factor-β activated kinase 1; NEMO, NF-κB essential modulator; GP130, glycoprotein 130; JAK1/2, janus kinase 1/2; STAT3, signal transducer and activator of transcription 3; CXCR2, C-X-C chemokine receptor 2; GRB2, growth factor receptor-bound protein 2; SOS, son of sevenless; Ras, rat sarcoma viral oncogene homolog; Raf, rapidly accelerated fibrosarcoma kinase; MEK1/2, mitogen-activated protein kinase kinase 1/2; ERK1/2, extracellular signal-regulated kinase 1/2; ActRIIB, activin receptor type IIB; ALK4/ALK5, activin receptor-like kinase 4/5; Smad2/Smad3, mothers against decapentaplegic homologs 2/3; FOXO, forkhead box o; Akt, protein kinase B; mTOR, mechanistic target of rapamycin; MuRF1, muscle ring finger 1; Atrogin-1 (MAFbx), muscle atrophy F-box protein.\n\nFigure 2: Figure 2. Characteristics of tumor EVs in cachectic syndrome. EVs, extracellular vesicles. ATP, adenosine triphosphate; Atrogin-1 (MAFbx), muscle atrophy f-box protein; Bcl-2, B-cell lymphoma 2; Caspase 3, cysteine-aspartic protease 3; GDF-15, growth differentiation factor 15; HIF-1α, hypoxia-inducible factor 1α; HSP90, heat shock protein 90; IL-6, interleukin-6; LC3-II, microtubule-associated protein light chain 3-II; miR-21a-5p, microRNA-21a-5p; Mfn-2, Mitofusin-2; MuRF1, muscle ring finger protein 1; MyHC, myosin heavy chain; NF-κB, nuclear factor κ-light-chain-enhancer of activated B cells; PGC-1α, peroxisome proliferator-activated receptor gamma coactivator 1α; PHGDH, phosphoglycerate dehydrogenase; PPARGC1A (Ppargc1a), gene encoding PGC-1α; RAGE, receptor for advanced glycation end products; ROS, reactive oxygen species; RyR1, ryanodine receptor 1; SOD2, superoxide dismutase 2; STAT3/p-STAT3, signal transducer and activator of transcription 3 (phosphorylated); TLR4, toll-like receptor 4; TNF-α, tumor necrosis factor α; UBR2, ubiquitin protein ligase E3 component N-recognin 2."
      }
    ]
  },
  {
    "id": "PMC12998520_multi",
    "image": [
      "images/PMC12998520-f1-2.png",
      "images/PMC12998520-f2.png",
      "images/PMC12998520-f3-2.png",
      "images/PMC12998520-f4-2.png",
      "images/PMC12998520-f5-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. 10‐day‐old term newborn, intubated, ventilated. Pyridoxine (Vitamin B6)‐dependent developmental and epileptic encephalopathy (ALDH7A1). Epileptic spasms in clusters associated with diffuse periodic complexes alternating with generalized clonic seizures. No physiological EEG features.\n\nFigure 2: Figure 2. 1‐day‐old term newborn. Glycine encephalopathy (nonketotic hyperglycinemia). Discontinuous asynchronous background activity with immature features (delta brushes).\n\nFigure 3: Figure 3. 3‐month‐old infant. Awake state. Glycine encephalopathy (nonketotic hyperglycinemia). Hypsarrhythmia. Epileptic spasms (see Video 3).\n\nFigure 4: Figure 4. 6‐year‐old boy. Serine deficiency. (A) Diffuse spike‐and‐wave bursts predominating over frontal areas on slow background activity. (B and C) Atypical absence seizure with eyelid myoclonia (same seizure, in C at reduced sensitivity).\n\nFigure 5: Figure 5. 5‐day‐old term newborn. Sulfite oxidase deficiency. Discontinuous poor background activity without physiological figures. Frontal predominating delta‐beta complexes. Right centro‐temporal electrographic‐only seizure (see arrow)."
      }
    ]
  },
  {
    "id": "PMC12998520_multi_2",
    "image": [
      "images/PMC12998520-f6.png",
      "images/PMC12998520-f7.png",
      "images/PMC12998520-f8-2.png",
      "images/PMC12998520-f9.png",
      "images/PMC12998520-f10-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. 10‐day‐old term newborn. Urea cycle disorder. Right fronto‐central electrographic‐only seizure.\n\nFigure 7: Figure 7. 10‐day‐old term newborn. Urea cycle disorder. Status epilepticus of multifocal seizures. See DSA (density spectral array on right and left central electrodes) on the lower part (the narrow indicates the time of the EEG example) showing 9 h of the recording.\n\nFigure 8: Figure 8. 10‐day‐old term newborn. Urea cycle disorder. Discontinuous background activity (no sedative drugs), presence of physiological features at term (frontal sharp transients).\n\nFigure 9: Figure 9. 12‐day‐old term newborn. Urea cycle disorder. Discontinuous asynchronous background activity. Multifocal sharp discharges and fast activities.\n\nFigure 10: Figure 10. 7‐day‐old term newborn. Urea cycle disorder. Discontinuous asynchronous background activity. Left central sharp thêta activity."
      }
    ]
  },
  {
    "id": "PMC12998520_multi_3",
    "image": [
      "images/PMC12998520-f11.png",
      "images/PMC12998520-f12-2.png",
      "images/PMC12998520-f13-2.png",
      "images/PMC12998520-f14.png",
      "images/PMC12998520-f15-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. 15‐day‐old term newborn. Marple syrup urine disease. Comb‐like pattern. On the right side physiological features (frontal sharp transients).\n\nFigure 12: Figure 12. 11‐day‐old term newborn. Marple syrup urine disease. Bilateral comb‐like pattern.\n\nFigure 13: Figure 13. 11‐day‐old term newborn. Marple syrup urine disease. Bilateral comb‐like pattern.\n\nFigure 14: Figure 14. 5‐month‐old infant. Menkes disease. Left temporal seizure.\n\nFigure 15: Figure 15. 8‐month‐old infant. Menkes disease. Cluster of epileptic spasms."
      }
    ]
  },
  {
    "id": "PMC12998520_multi_4",
    "image": [
      "images/PMC12998520-f16.png",
      "images/PMC12998520-f17.png",
      "images/PMC12998520-f18.png",
      "images/PMC12998520-f19.png",
      "images/PMC12998520-f20-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 16: Figure 16. 13‐day‐old term newborn. Peroxisomal beta‐oxidation defect (HSD17B4). Lateralized periodic discharges (LPDs).\n\nFigure 17: Figure 17. 7‐year‐old patient. Glucose transporter 1 deficiency syndrome. Atypical absence seizure with incomplete loss of awareness without motor manifestations. EEG: Burst of high‐voltage generalized rhythmic 3 Hz spike waves preceded and followed by bi‐frontal slow spike waves.\n\nFigure 18: Figure 18. 12‐year‐old patient. Glucose transporter 1 deficiency syndrome. High‐voltage slow background activity with fronto‐central spikes/spike and waves (A) and generalized spike and waves associated with myoclonic seizures (B).\n\nFigure 19: Figure 19. 7‐month‐old infant. Mitochondrial disease (Alpers‐Huttenlocher disease; POLG1). Bilateral frontally predominant periodic discharges.\n\nFigure 20: Figure 20. 11‐year‐old boy. Stroke‐like episodes of unidentified etiology. Left fronto‐temporal predominating periodic discharges."
      }
    ]
  },
  {
    "id": "PMC12998520_multi_5",
    "image": [
      "images/PMC12998520-f21.png",
      "images/PMC12998520-f22.png",
      "images/PMC12998520-f23.png",
      "images/PMC12998520-f24.png",
      "images/PMC12998520-f25-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 21: Figure 21. 6‐month‐old infant. Stroke‐like episode. Etiology unrevealed. Right hemispheric lateralized periodic discharges.\n\nFigure 22: Figure 22. 3‐year‐old child. Mitochondrial disease. Bilateral occipital left predominating periodic complexes.\n\nFigure 23: Figure 23. 4‐week‐old infant. Mitochondrial disease. Pharmacoresistant bilateral clonic seizures with onset at age 2 weeks.\n\nFigure 24: Figure 24. 7‐year‐old infant. Mitochondrial disease. Right hemispheric lateralized periodic discharges.\n\nFigure 25: Figure 25. 6‐month‐old infant. Alpers‐Huttenlocher disease. Generalized posteriorly predominating rhythmic high‐amplitude delta waves with superimposed (poly)spikes."
      }
    ]
  },
  {
    "id": "PMC12998520_multi_6",
    "image": [
      "images/PMC12998520-f26.png",
      "images/PMC12998520-f27-2.png",
      "images/PMC12998520-f28.png",
      "images/PMC12998520-f29-2.png",
      "images/PMC12998520-f30-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 26: Figure 26. 13‐month‐old child. ALG1‐CDG. Left: Awake; right: Sleep. Abundant bilateral posterior predominating spikes and spike and waves, no hypsarrhythmia.\n\nFigure 27: Figure 27. 10‐week‐old infant. CLN1. Vanishing EEG.\n\nFigure 28: Figure 28. 3‐year‐old child. CLN2. Photoparoxysmal flash‐per‐flash response at 1 Hz.\n\nFigure 29: Figure 29. 4‐year‐old child. CLN2. Photoparoxysmal flash‐per‐flash response at 1 Hz.\n\nFigure 30: Figure 30. 3‐year‐old child. CLN2. Photoparoxysmal flash‐per‐flash response at 2 Hz with brief interruptions."
      }
    ]
  },
  {
    "id": "PMC12998520_multi_7",
    "image": [
      "images/PMC12998520-f31-2.png",
      "images/PMC12998520-f32.png",
      "images/PMC12998520-f33-2.png",
      "images/PMC12998520-f34-2.png",
      "images/PMC12998520-f35-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 31: Figure 31. CLN2. Different aspects of flash‐per‐flash response at slow frequencies at 1 and 2 Hz in 3 patients aged 2 to 4 years.\n\nFigure 32: Figure 32. 7‐year‐old child. CLN6. Photoparoxysmal flash‐per‐flash response at 1 and 2.\n\nFigure 33: Figure 33. 4‐year‐old child. CLN2. Photoparoxysmal flash‐per‐flash response at 1 Hz associated with myoclonic jerks.\n\nFigure 34: Figure 34. 5‐year‐old child. CLN2. Photoparoxysmal flash‐per‐flash response triggered only when the child looks at the center of the lamp.\n\nFigure 35: Figure 35. 3‐year‐old child. CLN2. Photoparoxysmal response at middle frequencies (7, 13, and 17 Hz)."
      }
    ]
  },
  {
    "id": "PMC12998520_multi_8",
    "image": [
      "images/PMC12998520-f36-2.png",
      "images/PMC12998520-f37-2.png",
      "images/PMC12998520-f38-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Seizures and electroencephalographic findings in inborn errors of metabolism: Clues to differential diagnosis in the neonatal period, infancy, childhood and adolescence, and review of the literature\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 36: Figure 36. 7‐year‐old child. CLN6. Photoparoxysmal response at middle frequencies (6 and 10 Hz).\n\nFigure 37: Figure 37. 14‐year‐old patient. Lafora disease. Diffuse slowing of background activity. Generalized spike‐and‐wave bursts accompanied by myoclonic jerks. On EMG leads see myoclonia without EEG correlate.\n\nFigure 38: Figure 38. 14‐year‐old patient. Lafora disease. Diffuse slowing of background activity. Generalized spike‐and‐wave bursts and polyspikes activated by photic stimulation at middle frequencies."
      }
    ]
  },
  {
    "id": "PMC13017199_multi",
    "image": [
      "images/PMC13017199-f1.png",
      "images/PMC13017199-f2.png",
      "images/PMC13017199-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Neurofilament light chain as a prognostic marker in cerebral adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Neurofilament light chain analysis. Onset of cerebral adrenoleukodystrophy most often originates in the splenium of the corpus callosum. As axons are damaged, neurofilament light chain (NfL) is released into the cerebrospinal fluid and plasma. Single-Molecule Array (SiMoA) technology can reliably detect small amounts of NfL in plasma. Figure created in BioRender. Pierpont, R. (2025) https://BioRender.com/jrtqk9v\n\nFigure 2: Figure 2. Relationship of baseline plasma neurofilament light chain (NfL) levels in boys with cerebral adrenoleukodystrophy to their neurocognitive status at 1 year following haematopoietic stem cell transplantation (HSCT). The boxes delineate the interquartile range for each group with a line at the median and whiskers indicating the range. To enable better visualization of individual data points, NfL values were plotted along a log-transformed scale.\n\nFigure 3: Figure 3. Scatter plots display associations between plasma neurofilament light chain (NfL) concentrations prior to haematopoietic stem cell transplantation (HSCT) and scores across six domains of neurocognitive function at 1-year post-HSCT."
      }
    ]
  },
  {
    "id": "PMC13021563_multi",
    "image": [
      "images/PMC13021563-f1.png",
      "images/PMC13021563-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Enhanced oxidative stress resilience in C. elegans acox-1.1 mutants through CTL-3 and proteasomal regulation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Characterization of a CTL-3-dependent oxidative stress adaptive response in acox-1.1(ok2257) mutants. (A) Survival analysis under basal and PQ-induced oxidative stress conditions demonstrates that acox-1.1(ok2257) mutants exhibit increased resistance to PQ-induced mortality compared to wild-type worms, indicating enhanced oxidative stress tolerance. (B) Mean lifespan. (C) Measurement of intracellular ROS levels reveals a significant increase in acox-1.1(ok2257) mutants relative to wild-type worms, suggesting elevated oxidative stress due to acox-1.1 deficiency. (D) Quantitative RT-PCR analysis of catalase gene expression shows that ctl-3, but not ctl-1 or ctl-2, is selectively upregulated in acox-1(ok2257) mutants, indicating specific activation of a CTL-3-mediated ROS scavenging pathway. Data represent means ± SD from two biological replicates. (E) CTL-3 is required for oxidative stress resistance in acox-1.1(ok2257) mutants. RNAi-mediated knockdown of ctl-3 abolishes the enhanced survival of acox-1.1(ok2257) mutants under 1 mM PQ treatment. (F) Quantification of acox-1.1 mRNA levels shows a marked reduction under mild chronic oxidative stress conditions (1 mM PQ), reflecting the impaired peroxisomal β-oxidation cycle. (G) Expression analysis of oxidative stress-responsive genes (gcs-1, ptps-1, gst-4, and mtl-1) following 1 mM PQ treatment indicates a significant upregulation of mtl-1 in acox-1.1(ok2257) mutants compared to wild-type worms. Data represent means ± SD from three biological replicates.\n\nFigure 2: Figure 2. Proteostasis alterations and a proposed adaptive model in acox-1.1(ok2257) mutants. (A) Representative 2D electrophoresis gel images comparing protein extracts from mixed-stage wild-type and acox-1.1(ok2257) mutant worms. (B) Enlarged views of differentially expressed protein spots are indicated, with PAS-5 showing a decrease and CCO-2 showing a notable increase in acox-1.1(ok2257). (C) Western blot analysis of ubiquitinated proteins (Ub) in wild-type and acox-1.1(ok2257) mutants under basal conditions and following oxidative stress conditions (1 mM PQ). Upon PQ treatment, ubiquitin-conjugated protein levels are markedly reduced in acox-1.1(ok2257) mutants, indicating an oxidative stress-dependent alteration in ubiquitination dynamics. (The original Western blot images are included in Supplementary Figure S2). (D) Relative ubiquitin intensity. Quantification was performed using ImageJ software. (E) Proposed model illustrating an adaptive response to oxidative stress in acox-1.1(ok2257) mutants, highlighting the interplay between elevated ROS, reduced proteasome activity via PAS-5 downregulation, and elevated ROS-mediated regulatory machineries (upregulation of CTL-3). Reduced PAS-5 levels may impair proteasome integrity, thereby contributing to an adaptive oxidative stress-resistant state."
      }
    ]
  },
  {
    "id": "PMC13026078_multi",
    "image": [
      "images/PMC13026078-f1.png",
      "images/PMC13026078-f2.png",
      "images/PMC13026078-f3.png",
      "images/PMC13026078-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Novel Missense Variants in TRIM37 Associated with Mulibrey Nanism and Complex Congenital Heart Disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The TRIM family organization at the N-terminal including a TRIM motif or RBCC (Ring-B-box-Coiled-coil) domain, and the variable C-terminal domain sub-classified into nine subgroups (class I-IX). TRIM37 is a member of class VIII. Adopted from Meroni (2020) [8].\n\nFigure 2: Figure 2. Representative brain MRI showing progressive periventricular leukomalacia (PVL). T1 images from scan at 2 months of age (A and B) showing areas of hyperintensity suggesting early PVL marked with white arrows. T1 image from follow up scan at 5 months of age showing ventricular enlargement compared to prior and ex vacuo of the periventricular white matter as evidence of late stage PVL.\n\nFigure 3: Figure 3. Representative echocardiography images of proband showing multiple cardiac malformations. (A) 5-chamber view showing VSD and posterior malaligned conal septum (asterisk); (B) Parasternal short axis view showing VSD (asterisk); (C) Color Doppler interrogation of the ductus arteriosis (PDA) showing origin at the main pulmonary artery (MPA) and ductal arch with unobstructed right to left flow to the distal aorta (Distal Ao). (D) Suprasternal notch view of aortic arch (Ao) demonstrating interruption without communication with the descending aorta (DAO).\n\nFigure 6: Figure 6. (A) Schematic diagram showing the exons, their corresponding domains, and position of the novel missense variants in the TRIM37 gene in our proband. (B) Schematic diagram showing the domains of the TRIM37 protein and the positions of the corresponding amino acid substitutions due to the novel missense variants detected in our proband."
      }
    ]
  },
  {
    "id": "PMC13035816_multi",
    "image": [
      "images/PMC13035816-f1.png",
      "images/PMC13035816-f2.png",
      "images/PMC13035816-f3.png",
      "images/PMC13035816-f4.png",
      "images/PMC13035816-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"RNF128 regulates the adaptive metabolic response to fasting by modulating PPARα function\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A Wild-type and RING finger protein 128 knockout mice (8–10 weeks old) are either fed normally or fasted for 24 h, and weight loss is measured (n = 5 per group). B–G Analysis of serum glucose, triglyceride, cholesterol, aspartate aminotransferase, alanine aminotransferase, and serum β-hydroxybutyrate in the indicated groups following either ad libitum feeding or a 24-h fasting period (n = 6 per group). Data are presented as the mean ± standard deviation. One-way analysis of variance using the Newman–Keuls post hoc test or Student’s t-test is used to assess the statistical significance. *P < 0.05; **P < 0.01; and ***P < 0.001.\n\nFigure 2: Figure 2. A Body weight loss in adeno-associated virus serotype 8-vector and adeno-associated virus serotype 8-RING finger protein 128 mice after 24 h of fasting (n = 5 per group). B–G Alterations in serum glucose, triglyceride, cholesterol, aspartate aminotransferase, alanine aminotransferase, and β-hydroxybutyrate levels obtained from indicated groups after fasting for 24 h (n = 5 per group). Data are presented as the mean ± standard deviation. One-way analysis of variance using the Newman–Keuls post hoc test or Student’s t-test is used to assess the statistical significance. *P < 0.05; **P < 0.01; and ***P < 0.001.\n\nFigure 3: Figure 3. A Serum fibroblast growth factor 21 (FGF21) concentrations are measured in the indicated groups after ad libitum feeding or 24-h fasting (n = 6 per group). B Immunoblots of peroxisome proliferator-activated receptor alpha and FGF21 in the liver of mice subjected to ad libitum feeding or 24-h fasting. C, D The mRNA expressions of FGF21, peroxisomal acyl-coenzyme A oxidase 1, carnitine palmitoyltransferase 1, acyl-coA dehydrogenase long chain, acyl-coA dehydrogenase medium chain, 3-hydroxy-3-methylglutaryl-coA synthase 2, and 3-hydroxybutyrate dehydrogenase in indicated samples were analyzed using quantitative reverse transcription PCR. E Serum FGF21 concentrations of adeno-associated virus serotype 8-vector and adeno-associated virus serotype 8-RING finger protein 128 mice after 24-h fasting (n = 6 per group). F Immunoblots of peroxisome proliferator-activated receptor alpha and FGF21 in indicated samples. G, H The mRNA expressions of FGF21, peroxisomal acyl-coenzyme A oxidase 1, carnitine palmitoyltransferase 1, acyl-coA dehydrogenase long chain, acyl-coA dehydrogenase medium chain, 3-hydroxy-3-methylglutaryl-coA synthase 2, and 3-hydroxybutyrate dehydrogenase in indicated samples are analyzed using quantitative reverse transcription polymerase chain reaction. Data are presented as the mean ± standard deviation. One-way analysis of variance using the Newman–Keuls post hoc test or Student’s t-test is used to assess the statistical significance. **P < 0.01 and ***P < 0.001.\n\nFigure 4: Figure 4. A Immunoblots of RNF128, proliferator-activated receptor alpha, and fibroblast growth factor 21 (FGF21) in AML12/shluc and AML12/shRNF128 cell lines after treatment with or without fasted medium (containing 1 g/l glucose and 0.5% fetal bovine serum). B The mRNA expressions of FGF21 in the indicated samples. C Immunoblots of RNF128, proliferator-activated receptor alpha, and FGF21 in HepG2/shluc and HepG2/shRNF128 cell lines subjected to fasted medium. D The mRNA expressions of FGF21 in fasted HepG2/shluc and HepG2/shRNF128 cell lines. The mRNA expressions of peroxisomal acyl-coenzyme A oxidase 1, carnitine palmitoyltransferase 1, acyl-coA dehydrogenase long chain, acyl-coA dehydrogenase medium chain, 3-hydroxy-3-methylglutaryl-coA synthase 2, and 3-hydroxybutyrate dehydrogenase (E) in AML12/shluc and AML12/shRNF128 or F in HepG2/shluc and HepG2/shRNF128 cell lines subjected to a fasted medium for 24 h. Data are presented as the mean ± standard deviation. One-way analysis of variance using the Newman–Keuls post hoc test or Student’s t-test is used to assess the statistical significance. **P < 0.01 and ***P < 0.001.\n\nFigure 5: Figure 5. A Immunoblots of RING finger protein 128 (RNF128), proliferator-activated receptor alpha, and fibroblast growth factor 21 (FGF21) in AML12/vector and AML12/RNF128 cell lines after treatment with or without fasted medium. B The mRNA expressions of FGF21 in indicated samples. C Immunoblots of RNF128, proliferator-activated receptor alpha, and FGF21 in HepG2/vector and HepG2/RNF128 cell lines with fasted medium. D The mRNA expressions of FGF21 in fasted HepG2/vector and HepG2/RNF128 cell lines. The mRNA expressions of peroxisomal acyl-coenzyme A oxidase 1, carnitine palmitoyltransferase 1, acyl-coA dehydrogenase long chain, acyl-coA dehydrogenase medium chain, 3-hydroxy-3-methylglutaryl-coA synthase 2, and 3-hydroxybutyrate dehydrogenase (E) in AML12/vector and AML12/RNF128 or F in HepG2/vector and HepG2/RNF128 cell lines subjected to fasted medium for 24 h. Data are presented as the mean ± standard deviation. One-way analysis of variance using the Newman–Keuls post hoc test or Student’s t-test is used to assess the statistical significance. **P < 0.01 and ***P < 0.001."
      }
    ]
  },
  {
    "id": "PMC13035816_multi_2",
    "image": [
      "images/PMC13035816-f6.png",
      "images/PMC13035816-f7.png",
      "images/PMC13035816-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"RNF128 regulates the adaptive metabolic response to fasting by modulating PPARα function\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A, B HepG2/vector and HepG2/RNF128 cells are treated with cycloheximide (100 g/mL) and harvested at the indicated times. Cell lysates are subjected to immunoblotting with the indicated antibodies. C, D Endogenous RNF128 interacts with endogenous PPARα. Extracts from AML-12 cells are prepared, immunoprecipitated with anti-RNF128, anti-PPARα, or rabbit anti-immunoglobulin G antibodies, and analyzed using anti-RNF128 and anti-PPARα antibodies. E HEK293 cells are transiently transfected with HA-PPARα, RNF128-GFP, RNF1281–228-GFP, and RNF128205–428-GFP after 48 h. Lysates are harvested and subjected to immunoprecipitation with GFP antibody and analyzed by immunoblotting with the indicated antibody. F HEK293 cells are transiently transfected with Flag-RNF128, HA-PPARα, HA-PPARα1–278, and HA-PPARα279–468 after 48 h. Lysates are harvested and subjected to immunoprecipitation with HA antibody and analyzed by immunoblotting with the indicated antibody. Data are presented as the mean ± standard deviation. One-way analysis of variance using the Newman–Keuls post hoc test or Student’s t-test is used to assess the statistical significance. ***P < 0.001.\n\nFigure 7: Figure 7. A–C HEK293 cells are transiently transfected with hemagglutinin-ubiquitin (wild-type), hemagglutinin-ubiquitin (K48), hemagglutinin-ubiquitin (K63), Flag-PPARα, and RNF128 after 48 h. Lysates are harvested and subjected to immunoprecipitation with Flag antibody and analyzed for ubiquitylation by immunoblotting with the indicated antibody. D, E Lysates from HepG2 stable cell lines with RNF128 overexpression or silencing are immunoprecipitated with PPARα antibody and analyzed for ubiquitylation by immunoblotting with the specified antibody.\n\nFigure 8: Figure 8. A Immunoblot analysis of RING finger protein 128, proliferator-activated receptor alpha, and fibroblast growth factor 21 (FGF21) expression in indicated stable cell lines treated with fasted medium. B, C The mRNA expressions of FGF21, peroxisomal acyl-coenzyme A oxidase 1, carnitine palmitoyltransferase 1, acyl-coA dehydrogenase long chain, acyl-coA dehydrogenase medium chain, 3-hydroxy-3-methylglutaryl-coA synthase 2, and 3-hydroxybutyrate dehydrogenase in indicated samples. D Immunoblots of RING finger protein 128, proliferator-activated receptor alpha, and FGF21 in indicated stable cell lines subjected to fasted medium. E, F The mRNA expressions of FGF21, peroxisomal acyl-coenzyme A oxidase 1, carnitine palmitoyltransferase 1, acyl-coA dehydrogenase long chain, acyl-coA dehydrogenase medium chain, 3-hydroxy-3-methylglutaryl-coA synthase 2, and 3-hydroxybutyrate dehydrogenase in indicated samples. G The working model of RNF128 in the regulation of the adaptive metabolic response to fasting. The figure is created using elements from BioRender.com. Data are presented as the mean ± standard deviation. One-way analysis of variance using the Newman–Keuls post hoc test or Student’s t-test is used to assess the statistical significance. ***P < 0.001."
      }
    ]
  },
  {
    "id": "PMC13083169_multi",
    "image": [
      "images/PMC13083169-f1.png",
      "images/PMC13083169-f2.png",
      "images/PMC13083169-f3.png",
      "images/PMC13083169-f4.png",
      "images/PMC13083169-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Decoding RNF20: an epigenetic modifier and beyond\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. RNF20 domain structure feature and conservation in genetic models. (A) Schematic diagram of human RNF20 and RNF40 protein. Human RNF20 and RNF40 are composed of 975 and 1001 amino acids (aa), respectively, consisting of an N-terminal helical domain, a coiled-coil region and a C-terminal RING domain. (B) Phylogenetic analysis of RNF20 protein and protein domain architecture in different genetic models. Amino acid identity of overall sequence and RING domain between human RNF20 and RNF20 proteins from other species in National Center for Biotechnology Information (NCBI) database are indicated. RNF20 Protein sequence reference number in NCBI: Homo sapiens (NP_062538.5); Mus musculus (NP_001156735.1); Xenopus tropicalis (XP_002941911.2); Drosophila melanogaster (NP_647989.2); Saccharomyces cerevisiae (NP_010209.1).\n\nFigure 2: Figure 2. Cellular control of RNF20 activity at different levels. (A) Schematic diagram of post-transcriptional regulations on RNF20 by miR-let-7b-5p or ATG5. (B) Model of post-translational modifications or upstream regulations targeting RNF20. (C) Control of RNF20 activity by its co-regulators such as WAC. See details in the context.\n\nFigure 3: Figure 3. RNF20 functions in cardiac and neurodevelopment. (A–D) Roles of RNF20 in cardiac development. (E–H) Roles of RNF20 in neurodevelopment. CM: cardiomyocyte; EC: endothelial cells; NPC: neural precursor cell.\n\nFigure 4: Figure 4. Molecular modes of action of RNF20 in health and diseases. (A) RNF20 functions as an epigenetic regulator by monoubiquitinating histone H2B (at K120 in mammalian cells) and exerts effects on other histone modifications, chromatin accessibility, Pol II-mediated transcription, genomic stability and mRNA processing, thus influencing biological processes in different cellular contexts such as cell-fate, cell cycle, apoptosis and signaling transduction. Green single-headed arrow indicates activities triggered by RNF20 via H2Bub1. Blue dashed arrow indicates activities whether RNF20 functions through H2Bub1 or not is still not very clear or independent of H2Bub1 in some cases. (B) RNF20 acts as an E3 ligase of non-histone proteins, by monoubiquitination or polyubiquitination. (C) RNF20 functions by interacting with cofactors (for example: Rad51 and TPM3) via an E3-ligase independent manner in different contexts. (D) RNF20 regulates physiological and pathological processes by modulating signaling pathways.\n\nFigure 5: Figure 5. Misregulation of RNF20 results in cancers and congenital heart disease in humans. (A) RNF20 is associated with tumor initiation and progression of multiple cancers. The downstream effectors of RNF20 are listed. Factors regulated by RNF20 via mono- or poly-ubiquitination are shown in green boxes. Factors with its level or activity regulated by RNF20 by other pathways or unknown are shown in blue boxes. (B) RNF20 mutation has been found in patients with congenital heart disease (CHD). Reported CHD associated RNF20 mutation (p.Gln83*) is highlighted."
      }
    ]
  },
  {
    "id": "PMC1472686_multi",
    "image": [
      "images/PMC1472686-f1.png",
      "images/PMC1472686-f2.png",
      "images/PMC1472686-f3.png",
      "images/PMC1472686-f4.png",
      "images/PMC1472686-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Origin and evolution of the peroxisomal proteome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A: Maximum likelihood phylogenetic tree of the CDC48 orthologous group and its paralogs, including PEX1 and PEX6. The crenarchaeon Pyrobaculum aerophilum and euryarchaeon Archaeoglobus fulgidus sequences cluster together, consistent with an ancient eukaryotic origin of this protein family rather than an origin from a horizontal transfer, and they are used as outgroup. PEX1/6, as well as SEC18 and RIX7 appear to have evolved from CDC48, the central protein of the ERAD pathway B: Maximum likelihood phylogenetic tree of the Npy1p orthologous group and its mitochondrial paralogs. This protein family has a single origin in the alpha-proteobacteria. Bootstrap support over 100 replicates of the maximum likelihood tree is shown in all partitions. C: Pie chart showing the relative distribution of peroxisomal proteins according to their phylogenetic origin in yeast (left) and rat (right). Proteins that do have prokaryotic homologs but for which no reliable tree can de constructed, e.g. due to short stretches of homology, are considered \"unresolved\". For a complete list of the proteins and their origins, see the supplemental material, for their phylogenies see [44].\n\nFigure 2: Figure 2. ERAD and peroxisomal protein import homology. A) Schematic representation of the ERAD (top) and the Pex5 recycling (bottom) pathways. Proteins involved are represented by ovals and rectangles, only those commented in the text are named. Homologous relationships between proteins from the pathways are indicated in color. B) Homology between proteins of the ERAD pathway and proteins involved in protein import to the Peroxisome. Domain organization of the proteins was predicted with SMART [45]. Independent from that, homology between the proteins was determined by profile-to-profile searches using hhsearch [46], based on alignments of orthologous groups of the various proteins. Note that the SEL1 repeat is homologous to the TPR repeat. The location of the two CDC48 N-terminal domains (CDC48_N and CDC48_2) in Pex1 is based on PSI-Blast [47] searches starting with CDC48 proteins and on the structure published for the N-terminal domains of PEX1 [48].\n\nFigure 3: Figure 3. The retargeting of proteins to the peroxisome during evolution. The dashed lines indicate the ancestral cellular location of a peroxisomal protein, the continuous line their current (peroxisomal) location. Some proteins are derived from the alpha-proteobacterial ancestor of the mitochondria, their proteins have been retargeted to the peroxisome concomitant with the transfer of their genes to the nucleus (red, scenario I). Also proteins without a (detectable) alpha-proteobacterial ancestry have been retargeted from the mitochondria (blue, scenario II). Finally, a class of proteins have been retargeted from other compartments of the cell like the Endoplasmic Reticulum (cyan, scenario III).\n\nFigure 4: Figure 4. The N-terminal region of the multiple sequence alignment of several fungal members of the Cit1/2p orthologous group. Amino acids around the signal-peptide cleavage-sites, as predicted by Mitoprot are marked with a rectangle (white arrow indicates the position in the alignment) they correspond to YS (YA in C. tropicalis) that is missing in Cit2p. No mitochondrial localization nor a cleavage-site is predicted for Cit2p consistent with its peroxisomal location.\n\nFigure 5: Figure 5. Evolution of the peroxisomal proteome. Biochemical pathways reconstructed according to KEGG and annotations of peroxisomal proteins. For details on the reconstruction of ancestral states see supplemental material. Color code: yellow, eukaryotic origin; green, alpha-proteobacterial origin; red, actinomycetales origin; blue, cyanobacterial origin; white, origin unresolved. Note that the ancestral eukaryotic peroxisomal proteome reconstruction depends on the topology of the eukaryotic tree. If an alternative topology is considered, placing kinetoplastida and viridiplantae together [49], and the plant peroxisomal proteome is taken from the Araperox database [31], then the reconstructed ancestral eukaryotic peroxisomal proteome would be much larger, including all proteins present in the opisthokont proteome except for ANT1, IDP3, FOX3, PEX13 and PEX19."
      }
    ]
  },
  {
    "id": "PMC1681483_multi",
    "image": [
      "images/PMC1681483-f1.png",
      "images/PMC1681483-f2.png",
      "images/PMC1681483-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Expression and functional profiling reveal distinct gene classes involved in fatty acid metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clear zone assays. (A) Digital photograph of clear zones on an oleate plate after cell material was removed from the agar surface by rinsing with running water. (B, C) Greyscale images of myristate plate number 128 scanned on a flatbed scanner with transmitted light before and after removal of cell material, respectively. The locations of previously characterized and novel mutants of fatty acid metabolism are boxed in red and green, respectively. A strain resistant to cell removal is boxed in yellow.\n\nFigure 2: Figure 2. Physical interactions among peroxisomal proteins and proteins of the expression and fitness data sets are shown in (A) and (B), respectively. Red and green circles represent proteins exclusive to the expression and fitness data sets, respectively, and yellow circles represent proteins common to both data sets. Edges representing two-hybrid and affinity precipitation protein–protein interaction data are red and black, respectively. Interactions between proteins and metabolites (diamonds) are shown as blue edges.\n\nFigure 3: Figure 3. Pie graphs comparing GO slim terms of genes in the fitness and expression data sets. Terms for cellular component (A) and biological process (B) that are represented in the data sets are depicted as slices, the sizes of which are proportional to the term's frequency in the data set. Pies start at 0° with significantly over-represented terms (in a clockwise order of decreasing significance) and end with under-represented terms. Colours represent binomial distribution probability P-values for over-represented terms (see key in panel B), which reflect the statistical significance of enrichments."
      }
    ]
  },
  {
    "id": "PMC2147047_multi",
    "image": [
      "images/PMC2147047-f2.png",
      "images/PMC2147047-f3.png",
      "images/PMC2147047-f4.png",
      "images/PMC2147047-f5.png",
      "images/PMC2147047-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Shotgun Lipidomics Identifies a Paired Rule for the Presence of Isomeric Ether Phospholipid Molecular Species\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. Bovine heart lipids were extracted by a modified Bligh and Dyer procedure [21] and the PtdEtn fraction was separated by using HPLC with a cation-exchange column as previously described [23]. Analyses of PtdEtn molecular species were performed in the negative-ion mode by using an LTQ-Orbitrap mass spectrometer equipped with a Nanomate device as described under “MATERIALS AND METHODS”.\n\nFigure 3: Figure 3. Product ion ESI/MS analyses of PtdEtn molecular species in isolated bovine heart ethanolamine glycerophospholipids at m/z 772.5 (Panel A) and 774.5 (Panel B) were performed by using an LTQ-Orbitrap mass spectrometer. Analyses were conducted using a peak width setting of 1 Th by selection of the molecular ion in the linear ion trap (LTQ), collision activation in the C-trap with a normalized collision energy of 55% and gas pressure of 1 mTorr, and analysis of the resultant product ions in the Orbitrap.\n\nFigure 4: Figure 4. Product ion ESI/MS analysis of deprotonated 18∶0-20∶4 plasmenylethanolamine at m/z 750.54 was performed on an LTQ-Orbitrap mass spectrometer with a C-trap using an ion selective window of 1 Th by LTQ. Collision activation in C-trap was carried out with normalized collision energy of 55% and gas pressure of 1 mT. The resultant fragment ions were analyzed in the Orbitrap. The arrow indicates the absence of the 18:0 FA carboxylate in the spectrum after amplifying the position greater than1,000 fold.\n\nFigure 5: Figure 5. Bovine heart PtdEtn solution was treated with LiOMe leading to the cleavage of the FA ester bonds in the PtdEtn pool as previously described [26]. The resultant lysoPtdEtn mixture containing an ether aliphatic chain at the sn-1 position of glycerol was recovered using a modified procedure of Bligh and Dyer [21]. The mass spectrum in panel A was acquired in the negative-ion mode by using a QqQ mass spectrometer directly from the lysoPtdEtn solution that was diluted to less than 50 pmol of total lipids/µl. The mass spectrum in panel B was acquired in the negative-ion mode directly from a diluted lysoPtdEtn solution after addition of Fmoc chloride as previously described [16]. The mass spectrum in panel C was acquired in the negative-ion mode as that of spectrum B but in the neutral loss mode. The neutral loss scanning was conducted through coordinately scanning the first and third quadrupoles with a mass difference of 222.2 u (i.e., loss of a Fmoc) while the collisional activation was performed in the second quadrupole at collision energy of 32 eV. “IS” denotes internal standard. Panel D shows the comparison of ether aliphatic chain profiles in bovine heart PtdEtn determined by using different approaches: (1) direct quantitation of the resultant ether lysoPtdEtn molecular species from alkaline hydrolysis of PtdEtn (closed column) through a two-step quantitation procedure [5] from spectra A and C and (2) calculated composition (open column) derived from individual PtdEtn molecular species listed in Table 1.\n\nFigure 6: Figure 6. Mouse cerebellar lipid extracts were prepared by a modified Bligh and Dyer procedure [21]. Spectrum A was acquired in the negative-ion mode by using a QqQ mass spectrometer directly from a lipid extract that was diluted to less than 50 pmol of total lipids/µl after addition of approximately 25 pmol LiOH/µl to the lipid solution. Spectrum B was taken in the negative-ion mode after the diluted lipid solution used in spectrum A was treated with acid vapor and a small amount of LiOH (approximately 25 pmol LiOH/µl) was added to the infused solution. Spectrum C was acquired in the negative-ion mode as that of spectrum A but in the precursor-ion mode. The tandem mass spectrometry of precursor-ion scanning of 196 Th (i.e., phosphoethanolamine) was conducted through scanning the first quadrupole in the interested mass range and monitoring the third quadruple with the ion at m/z 196 while collision activation was performed in the second quadrupole at collision energy of 50 eV. Spectrum D was acquired in the negative-ion mode directly from a diluted mouse cerebellum lipid extract after addition of Fmoc chloride as previously described [16]. Spectrum E was acquired in the negative-ion mode as that of spectrum D but in the neutral loss mode. Tandem mass spectrometry of neutral loss scanning was conducted through coordinately scanning the first and third quadrupoles with a mass difference of 222.2 u (i.e., loss of a Fmoc) while collisional activation was performed in the second quadrupole at collision energy of 32 eV. “IS” denotes internal standard. All mass spectral traces are displayed after normalization to the base peak in each individual spectrum. All spectra are displayed after being normalized to the base peak in individual spectrum."
      }
    ]
  },
  {
    "id": "PMC2147047_multi_2",
    "image": [
      "images/PMC2147047-f7.png",
      "images/PMC2147047-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Shotgun Lipidomics Identifies a Paired Rule for the Presence of Isomeric Ether Phospholipid Molecular Species\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. The profiles of both aliphatic chains (open column in Panel A) and fatty acyl chains (closed column in Panel A) of bovine heart ether-linked ethanolamine glycerophospholipids (PtdEtn) were derived from individual molecular species listed in Table 1. The fatty acyl chain composition of bovine heart diacyl PtdEtn (Panel B) was also calculated from the identified individual molecular species as listed in Table 1. The profile of acyl-CoA in bovine heart (Panel C) was re-plotted from previously published data [28].\n\nFigure 8: Figure 8. The enzymes that may be involved in non-selective utilization of acyl CoA pool are highlighted with broken-lined frames. ** CDP-ethanolamine: 1-O-alkyl-2-acyl-sn-glycerol ethanolamine phosphotransferase."
      }
    ]
  },
  {
    "id": "PMC2171887_multi",
    "image": [
      "images/PMC2171887-f1.png",
      "images/PMC2171887-f2.png",
      "images/PMC2171887-f3.png",
      "images/PMC2171887-f4.png",
      "images/PMC2171887-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Phenylbutyrate up-regulates the adrenoleukodystrophy-related gene as a nonclassical peroxisome proliferator\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Expression of the Abcd2 and Aox genes is up-regulated by PBA in liver. (A) RNA samples from liver and brain of a control rat and from a rat treated per os with PBA (dose ×1.5) for 9 wk were analyzed by RT-PCR in duplicates. (B) RNA was extracted from liver of control rats (n = 10) and rats treated with PBA (dose ×1) for 6–7 wk (n = 6) or PBA (dose ×1.5) for 6–9 wk (n = 4). Samples were individually analyzed twice by RT-PCR. The intensities for Abcd2 and Aox mRNA were quantified by digital imaging and normalized using glyceraldehyde-phosphate dehydrogenase (Gapdh) intensities. Data (means ± SD) are presented as fold induction in relation to the values for control rats (taken equal to 1 and not depicted in the figure). (C) 2 mg sodium ciprofibrate (Cipro) or 20 mg PBA in 100 μl of water was injected into the cerebral fourth ventricle (100 μl/h). Control rats received equiosmolar amounts of NaCl. RNA was extracted from the whole brain and analyzed individually by Northern blotting (n = 4 for each group of rats).\n\nFigure 2: Figure 2. PBA induces peroxisome proliferation in liver. (A–D) Peroxisomes were stained for catalase activity. Liver of a control rat (A) and a rat treated per os with PBA (dose ×1.5) for 6 wk (B). Note peroxisome clusters and a phi-shaped peroxisome (arrowhead) in B. (C) Nearly touching peroxisomes suggesting a fission or budding process (Roels, 1991) in liver of a rat treated with PBA (dose ×1) for 6 wk. (D) Four phi-shaped peroxisomes in liver of a rat treated as in C. Unstained nucleoids are clearly visible in several peroxisomes. (E) Immunogold localization of AOX in a phi-shaped peroxisome, adjacent to an unlabeled mitochondrion, in liver of a rat treated as in C. Bars: (A, B, D, and E) 1 μm; (C) 100 nm.\n\nFigure 3: Figure 3. PBA modifies peroxisome distribution in ependymal cells of the fourth ventricle. Peroxisomes were stained for catalase activity. Peroxisomes in cells of a control rat (A) or a rat treated per os with dose ×1 of PBA for 6 wk (B). Peroxisomes are small and few when compared with liver (Fig. 2). Peroxisome clusters as shown in B were more frequently observed in treated animals. Cilium is seen in A. Bars, 200 nm.\n\nFigure 4: Figure 4. Peroxisomal genes are inducible by PBA and butyrate in hepatocytes. Rat primary hepatocytes were cultured in the presence of different concentrations of PBA, butyrate, and ciprofibrate for 72 h. Total RNA was analyzed by RT-PCR for Abcd2 and Aox expression. Results are presented as fold induction in relation to the control values for cells cultured in the absence of drug. Control data, taken equal to 1, are not reported in the figure. Data represent means ± SD of two independent experiments.\n\nFigure 5: Figure 5. Abcd2 is inducible by PBA and butyrate in glial cells. Differentiated CG-4 oligodendrocytes, pure primary astrocytes, and mixed primary cultures of oligodendrocytes and astrocytes were treated with different concentrations of PBA (A) and butyrate (B) for 72 h. Gene expression was analyzed by RT-PCR. Results are means ± SD of three independent experiments and presented as in Fig. 4."
      }
    ]
  },
  {
    "id": "PMC2171887_multi_2",
    "image": [
      "images/PMC2171887-f6.png",
      "images/PMC2171887-f7.png",
      "images/PMC2171887-f8.png",
      "images/PMC2171887-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Phenylbutyrate up-regulates the adrenoleukodystrophy-related gene as a nonclassical peroxisome proliferator\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. PBA causes Abcd2 induction and peroxisome proliferation in PPARα −/− cells. Fibroblasts (A) and hepatocytes (B) were prepared from fetal and adult liver, respectively, of PPARα +/+ and PPARα −/− mice and exposed to PBA or fenofibrate (Feno) for 72 h. Gene expression was analyzed by RT-PCR. Data are means ± SD of two to five independent experiments and presented as in Fig. 4. Untreated (C) or 2.5 mM PBA-treated (D) hepatocytes from PPARα −/− mice were examined for the number of peroxisomes by LM after anti-catalase protein A–gold immunolabeling with silver enhancement. Bars, 20 μm.\n\nFigure 7: Figure 7. TSA, a potent HDAC inhibitor, induces Abcd2 expression. Rat primary hepatocytes were treated with different doses of TSA and for different times. Abcd2 expression was analyzed by RT-PCR. Results from three independent experiments are presented as fold induction of the control values (equal to 1) for untreated cells.\n\nFigure 8: Figure 8. The GC and CCAAT boxes control basal expression and allow full induction of the basic Abcd2 promoter by PBA and butyrate. COS-7 cells were cotransfected with constructs containing normal or mutated Abcd2 promoter upstream of the luciferase reporter gene and pCMV-βGal to allow normalization of the luciferase activity. Mutations of the GC and CCAAT boxes and deletions are indicated in the schematic diagram. The cells were cultured with or without different doses of PBA or butyrate. (A) Analysis of the dose-dependent effect of PBA and butyrate. (B) Analysis of the role of the GC boxes. (C) Analysis of the role of the CCAAT box and of 5′UTR sequence. In each experiment, results are presented in relation to the luciferase activity of untreated p277-transfected cells taken equal to 1. Fold induction showing the effect of the treatment for each construct is indicated. Data are shown as means ± SD of three to six independent experiments performed in triplicate wells.\n\nFigure 9: Figure 9. Sp1/Sp3 and NF-Y bind to the GC1 and CCAAT boxes and HDAC1 is recruited through the GC1 box. (A) EMSA was performed using the 32P-labeled GC1 or CCAAT oligonucleotides with 10 μg of nuclear extracts (NE) from rat liver. Competition experiments were performed with a 50-fold molar excess of unlabeled oligonucleotides. Supershifts were performed using specific antibodies or serum for control. Retarded complexes are indicated. (B) DAPA was performed with the same nuclear extracts using the biotinylated normal or mutated GC1 oligonucleotide. Complexed proteins were resolved by SDS-PAGE and revealed by Western blot using an anti-HDAC1 antibody."
      }
    ]
  },
  {
    "id": "PMC2198940_multi",
    "image": [
      "images/PMC2198940-f1.png",
      "images/PMC2198940-f2.png",
      "images/PMC2198940-f3.png",
      "images/PMC2198940-f4.png",
      "images/PMC2198940-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Genome-Wide and Functional Annotation of Human E3 Ubiquitin Ligases Identifies MULAN, a Mitochondrial E3 that Regulates the Organelle's Dynamics and Signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A) Left 2 panels: Mitochondrial perinuclear clustering (a consequence of defective trafficking) results from siRNA-mediated knockdown of KIF5B, but not of KIF11. HeLa cells were transfected with the indicated siRNAs and mitochondria were visualized with MitoTracker Red. Right 2 panels: A cell-based imaging screen of E3 cDNA and shDNA genome-wide collections led to the identification of MULAN, a RING finger protein whose ectopic expression resulted in mitochondrial perinuclear clustering and fragmentation. For the screen, HeLa cells were co-transfected with mitochondrial-targeted RFP (MT-RFP) and with the E3 collections. “Control E3” refers to a random E3 cDNA which did not affect mitochondrial dynamics in the screen. B) Mitochondrial perinuclear clustering in response to MULAN ectopic expression apparently does not result from disruption of the microtubule network. HeLa cells were co-transfected with MT-RFP and either vector control or MULAN wild type cDNA. Cells were immuno-stained with anti-α-tubulin antibody to visualize the microtubule network. Green, tubulin staining; red, mitochondria. C) MULAN's schematic domain structure. Amino acid numbers indicated below. TMD, transmembrane domain. RNF, RING finger. D) MULAN's RNF has in vitro E3 activity. Reactions utilized GST fusions with the MULAN or c-Cbl RNFs as E3s. Activity was dependent on an intact RNF, since it was not detected in reactions using the MULAN C339A RNF mutant. c-Cbl's RNF was used as a positive control. Negative controls were reactions lacking an E3 (No E3) or reactions added to SDS sample buffer at t = 0 (unreacted). E) MULAN's RNF is required for the regulation of mitochondrial dynamics. NIH3T3 cells were transfected with vector, wild type MULAN cDNA or RNF-mutant cDNAs, together with MT-RFP. Cells were fixed at 24 h post-transfection and the fraction of RFP-positive cells exhibiting perinuclear-clustered mitochondria was scored (% trafficking defect). Data represent the average of at least 350 cells per condition, from 3–5 random 20× fields. Results are representative of several experiments.\n\nFigure 2: Figure 2. A) Blue bars: MULAN mRNA knockdown. RNA was extracted from HeLa cells 48 h after transfection with siRNA oligos targeting two different MULAN sequences, or with a negative control siRNA (siScrambled). Knockdown efficiency was determined by quantitative real-time RT-PCR. Results were normalized to the level of the 36B4 mRNA, which was amplified in the same multiplex reaction, as an internal control. Purple bars: MULAN knockdown leads to mitochondrial perinuclear clustering. HeLa cells were transfected with the indicated siRNAs on day 1, followed by MT-RFP on day 2. Cells were fixed on day 3 and the percentage of RFP-positive cells with perinuclear-clustered mitochondria was scored. B) The microtubule network is apparently intact in MULAN-knockdown cells. As in “A”, except that cells were fixed and stained with anti-α-tubulin antibody for analysis (green). C) Both MULAN ectopic expression and endogenous knockdown indicate its role in mitochondrial dynamics. For ectopic expression, HeLa cells were transfected with vector or MULAN wild type cDNA together with MT-RFP. Cells were fixed for analysis 24 h post-transfection. For siRNA-mediated knockdown, cells were transfected with siScrambled or siMULAN1 on day 1 and with MT-RFP on day 2. Cells were fixed on day 3. Mitochondrial fragmentation and clustering were quantitated under 100× field. At least 100 cells were counted per condition and data represent average of three independent transfections.\n\nFigure 3: Figure 3. A) MULAN colocalizes with MT-RFP/MT-GFP. NIH3T3 cells were transfected with Flag-tagged MULAN or untagged MULAN 1-301, together with MT-RFP (top panels) or MT-GFP (bottom panels), followed by immunostaining with antibody against Flag (top; green) or MULAN (bottom; red). B) Left panel: MULAN-Flag co-sediments with the mitochondrial protein, Tom20, in sucrose gradient. 293 cells transfected with MULAN-Flag were subfractionated by sucrose gradient. MULAN-Flag, the MOM protein Tom20, and Golgin 97 in each fraction were detected by western blot. Right panel: endogenous MULAN co-fractionates with mitochondria in sucrose gradient. 293F cells were Dounce-homogenized and centrifuged at 750×g to pellet nuclei and unbroken cells. The post-nuclear supernatant was centrifuged at 12,500×g to obtain the heavy membrane (HM) and the cytosolic/light membrane (LM) fractions. The HM fraction was subjected to sucrose gradient to further purify mitochondria. Equal protein amounts (40 µg) were fractionated by SDS-PAGE and blotted with anti-MULAN antibody to detect endogenous MULAN. Cytochrome c, Golgin 97, EEA1 and tubulin were used as markers for mitochondria, Golgi, endosomes and cytosol, respectively. Calreticulin and Sec61 were both used as ER markers. C) Immuno-electron microscopy of MULAN. COS7 cells transfected or not with MULAN-Flag were fixed and stained with anti-Flag antibody followed by gold-conjugated secondary antibody for immuno-EM analysis. Left panel: BSA only (no primary antibody) control; inset: mitochondrion from an untransfected cell. Right panel: mitochondria expressing MULAN-Flag. Scale bars are indicated. D) MULAN's predicted transmembrane domains (TMDs) mediate localization to mitochondria. NIH3T3 cells were co-transfected with Flag-tagged MULAN deletion mutants (green) and MT-RFP (red). Deletion of TMD1 (MULAN Δ2-29; top row) or of TMD2 (MULAN Δ242-259; middle row) led to partial mislocalization of MULAN. The combined deletion of both TMDs led to complete mislocalization of MULAN to the cytosol (MULAN Δ2-29+Δ242-259; bottom row). E) MULAN is a mitochondrial outer membrane (MOM) protein. Mitochondria from 293 cells transfected with MULAN-Flag were purified by sucrose gradient. Intact mitochondria were treated with trypsin for the indicated time, in the presence or absence of Triton X-100. The MULAN C-terminus was readily susceptible to trypsin digestion in intact mitochondria, indicating that it sits in the MOM facing the cytosol. Controls are the MOM protein, Tom20, and the intermembrane space protein, Smac. Smac only becomes sensitive to trypsin upon lysis of mitochondria with 0.5% Triton X-100 (lower panel). F) Topological model for MULAN on the MOM, indicating its transmembrane domains (red) and RNF (green). The cytosolic-exposed RNF can have access to the remaining components of the Ub system.\n\nFigure 4: Figure 4. NIH3T3 cells were transfected with wild type or mitochondrial localization-defective MULAN mutants, together with MT-RFP. C339A is the RING finger-mutant control. Cells were fixed 24 h post-transfection and the percentage of RFP-positive cells with perinuclear-clustered mitochondria was determined.\n\nFigure 5: Figure 5. A) Full-length human MULAN cDNA was used as a probe for hybridization to northern-blot of RNA from multiple human tissues. A single 2.4Kb band was detected for MULAN mRNA, in various tissues. B) RT-PCR of MULAN mRNA showed higher expression in mouse and rat adult primary cardiomyocytes (ACM) and in the mouse HL-1 cardiomyocyte cell line, compared to mouse NIH-3T3 cells and to the rat skeletal muscle-like cell line H9c2. 18S rRNA and Cyclophilin B were used as controls."
      }
    ]
  },
  {
    "id": "PMC2213590_multi",
    "image": [
      "images/PMC2213590-f1.png",
      "images/PMC2213590-f2.png",
      "images/PMC2213590-f3.png",
      "images/PMC2213590-f4.png",
      "images/PMC2213590-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Making two organelles from one: Woronin body biogenesis by peroxisomal protein sorting\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. wsc mutants are defective in WB maturation and inheritance. (A) HEX assemblies move in concert with peroxisomes in wild-type hyphae (Video 1, available at http://www.jcb.org/cgi/content/full/jcb.200705049/DC1) but move randomly in the matrix of wsc mutant peroxisomes (Video 2). The peroxisome matrix is revealed by peroxisome-targeted GFP, and HEX assemblies are observed as characteristic refractive structures by light microscopy. Arrows point to peroxisomes containing HEX assemblies. Bar, 1 μm. A schematic of results obtained from time-lapse microscopy is presented below. The double-headed arrow indicates random motion of the HEX assembly. (B) HEX assemblies accumulate in the apical cell of the wsc mutant and are not observed in subapical compartments. Representative apical and subapical compartments of wild-type and wsc mutant hyphae viewed by light microscopy are shown. Arrows point to HEX assembly. Bar, 10 μm. (C) The top shows a quantification of HEX assembly distribution in wild-type and mutant hyphae. The bottom shows the distribution of nuclei at similar positions in the hypha. Standard deviation is indicated with error bars.\n\nFigure 2: Figure 2. Positional cloning, phylogenetic analysis, and alignment of WSC-related sequences. (A) The schematic shows a set of markers on the left arm of chromosome three. The recombination frequency between wsc and these markers is indicated at the top. Cosmids (a–h) encompassing contig 40 were assessed for their ability to complement the wsc mutant. Complementing cosmids (e and f) are drawn as solid lines and noncomplementing cosmids are drawn as dotted lines. Transformation with DNA fragments containing individual candidate genes identified NCU 07842.2 as wsc. (B) Alignment of WSC and selected homologous proteins. Regions predicted to encode membrane-spanning domains are highlighted in yellow (score > 500) and pink (score < 500). Identical (*), strongly conserved (:), and weakly conserved (.) residues are identified beneath the alignment. The arginine residue that is mutated in some individuals afflicted with MDDS is shaded with black. (C) Phylogenetic tree showing the relationship between WSC and homologous sequences. The tree was constructed using MrBayes3.1.2. The scale bar indicates 0.1 substitutions. Proteins that have been shown to reside in the peroxisome are shown in green and those known to target to mitochondria are shown in blue. WSC and close relatives in the Euascomycetes are labeled in red. AT, Arabidopsis thaliana; AF, Aspergillus fumigatus; AN, Aspergillus nidulans; AO, Aspergillus oryzae; CA, Candida albicans; CC, Coprinus cinereus; DD, Dictyostelium discoideum; DM, Drosophila melanogaster; GZ, Gibberella zea; HC, Histoplasma capsulatum; HS, Homo sapiens; KL, Kluyveromyces lactis; MG, Magnaporthe grisea; NC, Neurospora crassa; OS, Oryzae sativa; SC, Saccharomyces cerevisiae; SP, Schizosaccharomyces pombe; SS, Sclerotina sclerotinium; UM, Ustilago maydis; YL, Yarrowia lipolytica; XT, Xenopus tropicalis.\n\nFigure 3: Figure 3. WSC is localized to nascent and mature WBs, and effect of deletion of dynamin-related proteins and FIS1. (A) WSC localizes over HEX assemblies in nascent WBs and surrounds HEX assemblies in mature WBs. WSC–GFP and RFP-PTS1 were coexpressed and localized in apical and subapical compartments by laser-scanning confocal microscopy. Bar, 10 μm. Magnified views of the region are indicated by a black square and shown at the right. Arrowheads point to refractive HEX assemblies. (B) WSC–GFP is concentrated over HEX assemblies in nascent WBs. Individual images of a single nascent WB are shown on the left and GFP and RFP fluorescence intensity are shown on the right across the indicated line. A black bar in the graph indicates the position of the HEX assembly, which can be seen in the DIC image. The line in the merge panel is 5.25 μm. (C) Effect of deletion of fis1, vps1, and dnm1 on WB assembly. DIC images show refractive HEX assemblies at the cell cortex (arrowheads) and RFP-PTS1 reveals the peroxisomal matrix. Bar, 10 μm. Bottom shows peroxisomes in the apical compartment, where Δdnm1 and Δfis1 present abnormal tubular peroxisomes. Bar, 1 μm. Radial growth for the indicated strains is shown in μm/min.\n\nFigure 4: Figure 4. Biochemical characterization of WB-associated WSC. (A) HEX and WSC cofractionate. Organelles were separated on a 17–60% Nycodenz gradient and fractions were probed for various organellar markers. The graph shows the shape of the gradient and total protein distribution across the gradient. Anti-HEX and anti-HA reveal HEX and WSC and antithiolase provides a marker of the peroxisome matrix. The inner mitochondrial membrane protein porin reveals the distribution of mitochondria. (B) WSC is insoluble in Triton X-100. (left) 16 KgP was resuspended in buffer containing the indicated additions and then fractionated into pellet (P) and supernatant (S) fractions by centrifugation at 100,000 g for 45 min. Porin provides a control of an integral membrane protein. (right) An extract obtained from the WSC–GFP–expressing strain received the indicated treatments and was then examined by epifluorescence (WSC–GFP) and bright field (differential interference contrast) microscopy. Bar, 2 μm.\n\nFigure 5: Figure 5. HEX controls WSC localization and the development of large peroxisomes. (A) The localization of WSC–GFP was examined in the presence (wt) and absence (Δhex) of HEX. In wild-type hyphae, WSC is enriched in the WB membrane and is mostly excluded from abundant cytosolic peroxisomes. In the absence of hex, WSC is localized to small cytosolic peroxisomes. Bar, 10 μm. Magnified views of the region are indicated by a black square and shown below. (B) WSC cofractionates with thiolase in the absence of HEX. An organellar fraction was obtained from the hex deletion strain expressing WSC-HA and separated by density gradient centrifugation. The bottom (B) and top (T) of the gradient are indicated. (C) The detergent insolubility of WSC depends on HEX. An organellar fraction from wild-type and hex deletion strains was treated as indicated and fractionated into pellet (P) and supernatant (S) fractions by centrifugation at 100,000 g for 45 min. (D) Large apical peroxisomes are no longer observed in the hex deletion strain. GFP-PTS1–expressing wild-type and hex deletion strains were examined by laser-scanning confocal microscopy and peroxisome size was estimated using morphometric analysis as described in Materials and methods. Peroxisome size is plotted against mean GFP intensity (arbitrary units), which provides an estimate of GFP-PTS1 density in the peroxisome matrix. The inset panels show a representative image of the indicated strains as well as a Western blot showing that both strains express equal levels of GFP-PTS1."
      }
    ]
  },
  {
    "id": "PMC2213590_multi_2",
    "image": [
      "images/PMC2213590-f6.png",
      "images/PMC2213590-f7.png",
      "images/PMC2213590-f8.png",
      "images/PMC2213590-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Making two organelles from one: Woronin body biogenesis by peroxisomal protein sorting\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. WSC overproduction promotes cortical association in the absence of HEX. (A) WSC can target peroxisomes to the cell cortex in the absence of hex. WSC–GFP was overproduced from the strong hex promoter (WSC op). Bar, 10 μm. Magnified views of the region are indicated by a black square and shown below. (B) Overproduced WSC–GFP cofractionates with thiolase. Fractionation was done as described for Fig. 4 A. The bottom (B) and top (T) of the gradient are indicated. (C) WSC is in oligomers. WSC-HA and WSC–GFP were coexpressed or WSC–GFP was expressed alone in the wsc deletion strain. Detergent extracts from these strains were precipitated with anti-HA, and Western blotting with anti-GFP reveals the degree of WSC–GFP coprecipitation. WSC–GFP alone provides a control for the specificity of anti-HA precipitation. (D) Peroxisomes from the hex deletion (Δhex) overproducing WSC–GFP contain detergent-insoluble WSC–GFP–enriched membrane domains. An organellar fraction from the indicated strain was examined by epifluorescence microscopy in the absence (buffer) and presence (1% TX-100) of detergent. Bar, 1 μm. (E) Detergent-insoluble WSC–GFP complexes sediment to densities higher than the peroxisomes in which they form (compare with B). The organellar fraction was treated with 1% Triton X-100 and separated as described in Fig. 6 B. Porin and thiolase provide controls for detergent extraction and, in a separate experiment, PEX14-GFP reveals the behavior of another PMP (bottom). The bottom and top of the gradient are indicated. (F) The WSC complex promotes BiFC. The indicated constructs were coexpressed in the wsc mutant background and the resulting strain was examined for YFP fluorescence. Arrows point to mature WBs. Bar, 10 μm.\n\nFigure 7: Figure 7. WSC forms detergent-resistant complexes in the yeast peroxisome and also inhibits peroxisome biogenesis. (A) Yeast were transformed with an RFP-PTS1–expressing plasmid to reveal peroxisomes and then transformed with an empty plasmid (−WSC) or a WSC–GFP–expressing plasmid (+WSC). Bar, 5 μm. (B) The effect of WSC on peroxisome numbers was quantified by counting punctate signal from RFP-PTS1 in the indicated strains. 64 cells were counted for each strain. (C) WSC–GFP forms detergent-insoluble complexes in yeast. Examination of peroxisomes by fluorescence microscopy in the absence (buffer) and presence (1% TX-100) of detergent was conducted as described in Fig. 6 D. Bar, 1 μm. Panels presented in this figure were enlarged using the scaling function in Photoshop software. (D) Fractionation by density gradient centrifugation of extracts prepared from WSC–GFP–expressing yeast was done as described in Fig. 6 E in the absence (top) and presence (TX-100) of detergent. The bottom (B) and top (T) of the gradient are indicated.\n\nFigure 8: Figure 8. MDDS-causing point mutations abolish WSC function and complex assembly. (A) The wsc deletion mutant was complemented with the indicated version of wsc–gfp and the distribution of HEX assemblies was quantified in apical and subapical compartments. Standard deviation is shown. These mutants do not dramatically alter steady-state levels of protein as revealed by a Western blot of extracts from the indicated strains (inset). (B) Capping is abolished by the R102W mutation. The indicated versions of WSC–GFP were localized using laser-scanning confocal microscopy. RFP-PTS1 reveals the peroxisome matrix. Arrow points to weak capping occasionally observed in the R102W mutant. Bar, 5 μm. (C) Evidence that WSC and HEX physically interact and effect of the R102W mutation on this interaction. Detergent extracts were prepared from strains expressing WSC-HA or WSC-R102W-HA from the native wsc promoter and anti-HA antibodies were used to precipitate WSC. Anti-HEX antibodies reveal the degree of HEX coprecipitation. (D) The R102W mutation affects WSC–WSC interaction. Extracts obtained from strains expressing the indicated versions of WSC were examined for WSC coprecipitation as described in Fig. 6 C. (E) Aberrant WSC–WSC complexes in the R102W mutant. Extracts were prepared from the indicated strains, treated with detergent, and separated by density gradient centrifugation, as in Fig. 6 E, using buffer H or buffer N.\n\nFigure 9: Figure 9. Model of WB biogenesis. HEX self-assembles (double-headed arrow) in the peroxisome matrix and is recruited to the matrix face of the peroxisome membrane by interaction with WSC. A combination of WSC–WSC and HEX–WSC interactions concentrate WSC in the membrane and promote the production of asymmetrical nascent WBs. WSC complexes can then trigger cortical association, which allows partitioning of the nascent WB and allows segregation of the newly formed organelle into subapical compartments."
      }
    ]
  },
  {
    "id": "PMC2329825_multi",
    "image": [
      "images/PMC2329825-f1.png",
      "images/PMC2329825-f2.png",
      "images/PMC2329825-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"E6-associated protein (E6-AP) is a dual function coactivator of steroid hormone receptors\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) The genomic structure of the coding region of E6-AP. The 10 exons that were reported in the first E6-AP gene structure study are indicated by closed boxes in green and numbered E1 to E10. The exons upstream of exon 1 are indicated by closed boxes in pink and are numbered U1 to U4. The three translation initiation sites (ATG) are shown. (B) A set of five E6-AP mRNAs with their potential protein isoforms (isoforms I, II, and III) that differ at their extreme amino-termini. 3’-region of exon 3 and exons 4-10 encode the hect domain. The E6-binding site is encoded within exon 3, and the active site cysteine is encoded within exon 10 (adapted from (Yamamoto et al., 1997)).\n\nFigure 2: Figure 2. E6-AP possesses five well-characterized functional domains: (i) a hect domain, (ii) an E6 binding domain, (iii) a p53 binding domain, (iv) two nuclear receptor interaction domains and (v) an activation domain, which have been represented with the amino acid numbers they correspond to. The three LXXLL motifs (NR box) are shown dispersed throughout the protein. Two of these motifs are located in the amino terminus and the third one is located within the carboxy terminus of the protein.\n\nFigure 3: Figure 3. Step 1: In the absence of hormone, the NRs are in their inactive form, bound to chaperone proteins. In the presence of hormone, the NRs undergo conformational changes that result in the release of chaperones, which facilitate receptor dimerization and their recruitment to the promoter. Step 2: The negative regulators are cleared of the promoter via the ubiquitin proteasome pathway, followed by recruitment of coactivator complexes, general transcription factors (GTFs) and RNA polymerase II (Pol II) to the target gene promoter (Perissi et al., 2004). Some of the coactivators recruited to the promoter include ubiquitin proteasome enzymes like E6-AP and UBCH7 (Verma et al., 2004). Step 3: The preinitiation complex disassembles and the RNA Pol II escapes from the promoter, leading to transcriptional elongation. Step 4: Then the ubiquitin proteasome pathway degrades the nuclear receptor-transcription complex. According to this model, the active transcription depends on continuous reloading and degradation of the nuclear receptor-transcription complex, thus the ubiquitin-proteasome-dependent degradation and receptor-dependent transactivation are linked."
      }
    ]
  },
  {
    "id": "PMC2605849_multi",
    "image": [
      "images/PMC2605849-f1.png",
      "images/PMC2605849-f2.png",
      "images/PMC2605849-f3.png",
      "images/PMC2605849-f4.png",
      "images/PMC2605849-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of Peroxisome Proliferator-Activated Receptors by E6-Associated Protein\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. E6-AP inhibits the transcriptional activity of PPARα, PPARβ, and PPARγ. 293T cells were transfected with plasmids expressing 4X-ACO-Luciferase, pRLCMV, PPARα, PPARβ or PPARγ, and E6-AP. Cells were lysed and luciferase activity was corrected for transfection efficiency and protein. Asterisks indicate a significant difference in luciferase values when compared to the 0 ratio group. (*P < .05 with statistical analysis using ANOVA). The graphs are representative of 3 independent experiments.\n\nFigure 2: Figure 2. E6-AP expression results in decreased mRNA levels of PPARα target genes. FaO cells were transfected with empty vector or plasmid expressing E6-AP, followed by treatment with 0.1% DMSO or 50 μM Wy-14,643 for 6 hours. Total RNA was isolated from the cells and real-time PCR was performed on reverse transcribed RNA. Asterisks indicate a significant difference when compared to the corresponding control group. (*P < .05 with statistical analysis using ANOVA). The graphs represent mean values obtained from 2 independent experiments.\n\nFigure 3: Figure 3. E6-AP interacts with PPARα. 293T cells were transfected with plasmids expressing pFR-Luciferase, pRLCMV, pVP16-PPARα, pM-E6-AP. Cells were lysed and luciferase activity was corrected for transfection efficiency and protein. Asterisks indicate a significant difference in Wy-14,643 induction when compared to the corresponding DMSO group. (*P < .05 with statistical analysis using ANOVA). The graph is representative of 2 independent experiments.\n\nFigure 4: Figure 4. E3 ubiquitin ligase activity of E6-AP is required for regulating PPARα transactivation. (a) 293T cells were transfected with plasmids expressing 4X-ACO-Luciferase, pRLCMV, PPARα, E6-AP, or E6-AP-C833S that is defective in ubiquitin ligase function. (b) Cells were treated with 0.1% DMSO or 5 μM MG132 for 6 hours. Cells were lysed and luciferase activity was corrected for transfection efficiency and protein. Asterisks indicate a significant difference when compared to the corresponding 0 ratio group. (*P < .05 with statistical analysis using ANOVA). The graph is representative of 3 independent experiments.\n\nFigure 5: Figure 5. E6-AP is induced by clofibrate in a PPARα-dependent manner. Wildtype and PPARα null mice were treated with control vehicle or clofibrate for 2 weeks. Groups of five mice were used for each treatment. (a) Total RNA was isolated from liver and mRNA levels were measured using real-time PCR. (b) Protein isolated from liver was analyzed for E6AP expression by western blot. The graph (lower panel) depicts mean (n = 5) band intensity. Asterisks indicate a significant increase in clofibrate induction when compared to the PPARα null group. (*P < .05 with statistical analysis using ANOVA)."
      }
    ]
  },
  {
    "id": "PMC2733298_multi",
    "image": [
      "images/PMC2733298-f1.png",
      "images/PMC2733298-f2.png",
      "images/PMC2733298-f3.png",
      "images/PMC2733298-f4.png",
      "images/PMC2733298-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Leptin Administration Favors Muscle Mass Accretion by Decreasing FoxO3a and Increasing PGC-1α in ob/ob Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Gastrocnemius (GAS), extensor digitorum longus (EDL) and soleus (SOL) muscle weights of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice (n = 9–10 per group). *P<0.05, **P<0.01 and ***P<0.001. (B) Cross-sectional area (CSA) of GAS, EDL and SOL muscle fibers of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice (approximately 100 fibers/muscle from 3 mice/group). **P<0.001 and ***P<0.0001. (C) Representative histological sections of hematoxylin-eosin-stained GAS, EDL and SOL muscles of wild type and ob/ob mice. Scale bars = 200 µm. Results are presented as mean±SEM. G: genotype, T: treatment.\n\nFigure 2: Figure 2. (A) Representative Western blot analyses of forkhead box class O (FoxO3a) and phospho-FoxO3a proteins of gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice are shown. β-actin was used as a loading control (n = 8 per group). (B) Representative Western blot analyses of Akt activity evidenced by phosphorylated-Akt and Akt proteins ratio of gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice (n = 8 per group). (C) Representative Western blot analyses of AMP-activated protein kinase (AMPK) activity evidenced by phosphorylated-AMPK and AMPK proteins ratio of gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice are shown (n = 5 per group). (D) Representative Western blot analyses of AMP- (PGC-1α) of gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice are shown. β-actin was used as a loading control (n = 8 per group). Data are expressed as mean±SEM. G: genotype, T: treatment.\n\nFigure 3: Figure 3. (A) Representative Western blot analyses of muscle atrophy F box (MAFbx) and muscle RING finger 1 (MuRF1) proteins of gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice are shown. β-actin was used as a loading control (n = 8 per group). *P<0.05. (B) Immunostaining for MAFbx and MuRF1 proteins was assessed by optic microscopy. Representative images are shown for gastrocnemius muscle. Scale bars = 50 µm. Data are presented as mean±SEM. G: genotype, T: treatment.\n\nFigure 4: Figure 4. (A) Representative Western blot analyses of myostatin protein of gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice are shown. β-actin was used as a loading control (n = 2–6 per group). The myostatin band was detected only in 2 samples of wild type groups.*P<0.05. (B) Representative Western blot analyses of proliferating cell nuclear antigen (PCNA), cyclin D1 and cyclin-dependent kinase inhibitor 1B (Cdkn1b/p27Kip1) proteins of gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice are shown. β-actin was used as a loading control (n = 8 per group). *P<0.05, **P<0.01 and ***P<0.001. Data are expressed as mean±SEM. G: genotype, T: treatment.\n\nFigure 5: Figure 5. (A) Immunohistochemical staining for dystrophin and PCNA of gastrocnemious muscle of wild type and ob/ob mice (n = 3 per group). Scale bar = 50 µm. (B) Immunohistochemical staining and relative stained nuclei number for PCNA evaluated among 500 cells in gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice (n = 3 per group). Scale bar = 50 µm. **P<0.01. (C) Immunohistochemical staining and relative stained nuclei number for cyclin D1 evaluated among 500 cells in gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice (n = 3 per group). Scale bar = 50 µm. (D) Immunohistochemical staining and relative stained nuclei number for p27Kip1 evaluated among 500 cells in gastrocnemius muscle of PBS (open), pair-fed (gray) and leptin-treated (closed) wild type and ob/ob mice (n = 3 per group). Scale bar = 50 µm. *P<0.05 and **P<0.01. Data are expressed as mean±SEM. G: genotype, T: treatment."
      }
    ]
  },
  {
    "id": "PMC2949860_multi",
    "image": [
      "images/PMC2949860-f1.png",
      "images/PMC2949860-f2.png",
      "images/PMC2949860-f3.png",
      "images/PMC2949860-f4.png",
      "images/PMC2949860-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Δ4-desaturation pathway for DHA biosynthesis is operative in the human species: Differences between normal controls and children with the Zellweger syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Microscopic images of human immortalized lymphocytes transfected with the Δ4-desaturase vector. Human B lymphoblastoid cells from one of the control cases, transiently transfected with the pIRES2EGFP-FlagΔ4 vector on day 3 after electroporation. Upper (A) and lower (B) panels show the cells under bright field and fluorescence microscopy, respectively.\n\nFigure 2: Figure 2. Gas-chromatographic differences of the main omega-3 PUFAs between the normal and the Zellweger-syndrome child. Omega-3 VLPUFA peaks directly scanned from the gas chromatograms in one control and one ZS patient. It can be seen that, before adding the Δ4-desaturase construct (A), DHA is higher than ω3DPA (22:5ω3) in the normal child, while it is lower than ω3DPA in the patient with Zellweger's syndrome (ratio 22:6ω3/22:5ω3 < 1.0) When adding the enzyme (B), this ratio increases clearly, especially in the ZS patient.\n\nFigure 3: Figure 3. Omega-3 individual effects of transfection with Δ4-desaturase on controls and children with the Zellweger syndrome. This figure shows the significant increases of the 22:6ω3/22:5ω3 ratio in all the children transfected with the Δ4-desaturase plasmid. As can be seen, the ratio increases clearly in all the cases. However, the slope is higher in the ZS patients, whose ratio is lower from the start and surpasses the normal in some patients. The greater variability in the ZS patients is due to their clinical and biological heterogeneity. Yet, the statistical significance of paired t-tests is extremely high in all cases (p < 0.0001)\n\nFigure 4: Figure 4. Omega-6 individual effects of transfection with Δ4-desaturase on controls and children with the Zellweger syndrome. This figure shows the significant increases in the 22:5ω6/22:4ω6 ratio in all the children transfected with the Δ4-desaturase vector. As can be seen, the ratio increases clearly in all the cases (p value lower than 0.0001 by paired t-tests). Again, the slope is higher in the ZS patients, who start with lower ratios than the controls. Here too, the ZS patients show a greater variability in the ratio, although the statistical significance remains extremely high.\n\nFigure 5: Figure 5. Omega-3 effects of transfection with Δ4-desaturase on grouped controls and patients with the Zellweger syndrome. The number of times that the 22:6ω3/22:5ω3 ratio increased when the Δ4-desaturase construct was transfected, in normal children and in ZS patients, is displayed here. For that, a new index was obtained by dividing the 22:6ω3/22:5ω3 ratio with the added Δ4-desaturase by the same ratio obtained when transfecting the empty vector [(22:6ω3/22:5ω3)+Δ4/(22:6ω3/22:5ω3) empty]. Bars are mean values ± SEM. Despite the effect of grouping patients and controls by unpaired t-tests, the statistical significance was still extremely high (p = 0.0002)."
      }
    ]
  },
  {
    "id": "PMC3082194_multi",
    "image": [
      "images/PMC3082194-f1.png",
      "images/PMC3082194-f2.png",
      "images/PMC3082194-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome assembly: matrix and membrane protein biogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The import of peroxisomal matrix proteins. The process may be divided into distinct steps (white numbers in closed black circles). Bold numbers indicate corresponding Pex proteins. The steps are: (1) Receptor–cargo interaction in the cytosol (PTS2 pathway is not depicted). (2) Receptor–cargo docking at the peroxisomal membrane with the docking subcomplex, inducing the assembly of the translocon. (3) Translocation of the receptor–cargo complex across the membrane followed by the dissociation of the receptor–cargo complex; i.e., cargo release. (4) Export of cargo-free receptors from the peroxisome matrix to the membrane. (5a) Monoubiquitination of the receptor on a cysteine by Pex4 and Pex2 (for receptor recycling) or (5b) polyubiquitination of the receptor on a lysine by Ubc4/5 and Pex10/12 (for degradation by the RADAR pathway). (6a) Receptor recycling from the peroxisome membrane back to the cytosol by the action of the AAA ATPases (Pex1 and Pex6) and ATP hydrolysis, or (6b) degradation of a receptor that is blocked from recycling via the RADAR pathway involving the proteasome. (7) Deubiquitination of the receptor before the next round of import. The squiggly line on Pex5 denotes its disordered N-terminal segment.\n\nFigure 2: Figure 2. Contribution of the ER to peroxisome biogenesis. Most, if not all, PMPs are first imported into the ER through the Sec61/SSH1 translocon or the GET3 complex (left inset), are sorted into a pre-peroxisomal compartment, and bud out in a Pex3/Pex19-dependent manner to form pre-peroxisomal vesicles (right inset). These vesicles can form mature peroxisomes after fusion, dependent on Pex1/Pex6 (Titorenko and Rachubinski, 1998) and matrix protein import (de novo pathway). The de novo pathway repopulates cells with peroxisomes in the biogenesis mutants (e.g., pex3Δ/pex19Δ) lacking the organelle when corresponding genes are reintroduced (Elgersma et al., 1997; Fang et al., 2004; Tam et al., 2005; Hoepfner et al., 2005; Motley and Hettema, 2007; Motley et al., 2008; Perry et al., 2009; van der Zand et al., 2010). Alternatively, the pre-peroxisomal vesicles fuse with divided peroxisomes generated from preexisting mature peroxisomes. Peroxisome division requires Pex11 and a specific set of DRPs. In plants, retrograde trafficking from peroxisomes to the ER has been described (McCartney et al., 2005).\n\nFigure 3: Figure 3. Alternative roles of Pex19 in the insertion of PMPs into the peroxisomal membrane. The role of Pex19 in peroxisome biogenesis and import of various PMPs has been clearly established in yeast and mammals, but its mechanism of action is still a matter of debate (Snyder et al., 1999; Sacksteder et al., 2000). Previous studies implicated Pex3 and Pex19 in the posttranslational insertion of PMPs. Pex19 serving as a chaperone binds and stabilizes newly synthesized mPTS-containing PMPs in the cytoplasm, and transports them to peroxisomes by docking to Pex3 present in the peroxisomal membrane (Muntau et al., 2003; Fang et al., 2004; Jones et al., 2004; Matsuzono and Fujiki, 2006; Matsuzono et al., 2006). However, subsequent studies in yeast show the requirement of Pex19 for the exit of most, if not all PMPs, including Pex3, from the ER (Fig. 2 B; Hoepfner et al., 2005; Lam et al., 2010; van der Zand et al., 2010; unpublished data). In the light of the Pex19-independent insertion of most PMPs into the ER and the role of Pex19 in mediating the budding of pre-peroxisomal vesicles, the role of Pex19 in the posttranslational import of PMPs is questionable for all PMPs that go to peroxisomes via the ER."
      }
    ]
  },
  {
    "id": "PMC3168371_multi",
    "image": [
      "images/PMC3168371-f1.png",
      "images/PMC3168371-f2.png",
      "images/PMC3168371-f3.png",
      "images/PMC3168371-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal alterations in Alzheimer’s disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Accumulation of VLCFA in cortical areas of human brains associated with progressive AD neuropathology. a The content of long and very long-chain fatty acids in five different cortical regions, indicated below the graphs, was determined by GC–MS (n = 10/group). Relative amounts of the fatty acids C16:0, C18:0, C22:0, C24:0 and C26:0 are depicted as ratio to the total fatty acid (TFA) content (×1,000). The mean values of each AD severity group are connected across brain regions by the line pattern indicated above the graphs. The AD-related neuropathology was defined according to Braak staging of the contralateral hemisphere. Tissue abbreviations: PS parasubiculum, TEC trans-entorhinal cortex, GF gyrus frontalis, GP gyrus precentralis, CB cerebellar cortex. The mean level of VLCFA (C24:0 and C26:0 combined) in gyrus frontalis is depicted as ratio to total fatty acids for the three Braak stage groups (b) and of C22:0 (c) and VLCFA (d) in relation to NFT and plaques. The increase in VLCFA in stage V–VI when compared with stage I–II was statistically significant (corr. p = 0.044). When NFT were present, both C22:0 (c left) and VLCFA (d left) were significantly increased (p = 0.013 and 0.003, respectively). Also when the cases were grouped according to plaques, the levels of C22:0 (c right) and VLCFA (d right) were elevated when plaques were present, but to a lesser extent (p = 0.030 and 0.165, respectively). Thus, the increase in VLCFA was more strongly associated with NFT than with plaques. Error bars indicate SEM; *p < 0.05 and **p < 0.01; corr., corrected for multiple testing (Tukey’s post hoc test)\n\nFigure 2: Figure 2. Plasmalogens are reduced in gyrus frontalis with AD pathology. a Schematic structure of plasmalogen. b, c The relative levels of total ethanolamine plasmalogens (PlsEtn) in gyrus frontalis medius were determined by GC–MS and expressed as ratio to the total fatty acid (TFA) content (×1,000). Reduced levels were observed when the samples were grouped either by Braak staging of neuropathology (b corr. p = 0.027) or by the presence or absence of NFT (c left; p = 0.004) or plaques (c right; p = 0.300). d Individual plasmalogen sub-species were determined by nano-ESI–MS and depicted as percentage of the mean level of the same plasmalogen species in samples without NFT. The four main species (striped) account together for 58.5% of total plasmalogen. e The level of plasmalogen species grouped according to the degree of saturation of the fatty acid at the sn-2 position and the presence or absence of NFT. The difference between the 6.1% increase in plasmalogens with saturated (sat) or monounsaturated (MUFA) fatty acids at sn-2 compared with the 7.7% decrease in those with polyunsaturated fatty acids (PUFA) is statistically significant (p = 0.019) The number (n) of cases in each group are indicated below the graphs. Error bars indicate SEM; *p < 0.05 and **p < 0.01; corr., corrected for multiple testing (Tukey’s post hoc test)\n\nFigure 3: Figure 3. Increased peroxisome density in the soma of neurons in gyrus frontalis is associated with NFT. a The peroxisome density in the cell body of at least 24 neurons (each represented by a circle) in gyrus frontalis from each of the 30 cases in the cohort was determined by morphometry after immunohistochemical staining for PMP70 and plotted as pixel/mm2. The total number of analyzed neurons/Braak group is indicated at the bottom of the panel. b The increase in mean peroxisome volume density was statistically significant in tissues containing NFT (p = 0.018) but not in the group with plaques only (p = 0.123). The observation that the increase was more strongly associated with NFT than with plaques was statistically significant (p = 0.001). The number (n) of cases in each group is indicated below the graphs. Error bars indicate SEM; *p < 0.05\n\nFigure 4: Figure 4. Peroxisomes but not mitochondria are absent from neuronal processes featuring pre-tangles. Representative images of confocal double-immunofluorescence using AT8 antibody to detect phospho-tau (pre-tangle marker) and either PMP70-positive peroxisomes (a, c, e) or SOD2-positive mitochondria (b, d, f) in entorhinal cortex of an AD patient with Braak stage IV. a , b In the absence of phosphorylated tau, numerous peroxisomes (a) and mitochondria (b) are present in the neuronal processes. When phosphorylated tau is present, peroxisomes are only visible in the soma (arrow), but not in the neuronal process (c arrowheads pointing upwards), but normal amounts of mitochondria are present (d). Note the abundance of peroxisomes in a neighboring neuron, in which no phospho-tau is detected (c arrowheads pointing downwards). e, f In neurons filled with NFT, no peroxisomes and only sporadic mitochondria were detected in the soma. Size bar 10 μm"
      }
    ]
  },
  {
    "id": "PMC3177427_multi",
    "image": [
      "images/PMC3177427-f1.png",
      "images/PMC3177427-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Diffusion-weighted Magnetic Resonance Imaging in the Early Diagnosis of Neonatal Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Neonatal adrenoleukodystrophy: (a) the axial T2-weighted MR image is normal; (b) the diffusion-weighted image (b = 1000 sec/mm2) reveals high-signal changes in the splenium of the corpus callosum, and occipital lobes (black arrows); (c) the ADC map reveals that the ADC values of the involved regions is low (0.69 × 10–3 mm2/sec), compared to the frontal regions (1.24 × 10–3 mm2/s).\n\nFigure 2: Figure 2. A healthy 4-day-old boy. ADC map: normal parechymal values. ADC measurements are shown by region of interest (ROI) evaluations. Large ROI evaluations from different regions in the parenchyma reveal normal ADC values: 1.82 and 1.23 × 10–3 mm2/sec."
      }
    ]
  },
  {
    "id": "PMC3178599_multi",
    "image": [
      "images/PMC3178599-f1.png",
      "images/PMC3178599-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Genomic Profiling Identifies Novel Mutations and SNPs in ABCD1 Gene: A Molecular, Biochemical and Clinical Analysis of X-ALD Cases in India\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The upper left panel depicts all the mutations and SNPs that are localized in the schematic molecular structure of ALDP in the present study. The lower left panel shows the four novel mutations (a) c.1903_04insCCA/Val635delinsAlaMet (TGG in antisense strand with reverse primer), (b) c.1979G>A/Arg660Gln, (c) c.1993_95delinsGAG/Lys665delinsGlu and (d) c.1673T>C/Ile558Thr. The right panel shows the three novel SNPs (a) 476C/T (His30His), (b) 1950G/A (Ala650Ala) and (c) -32C/T in IVS9.\n\nFigure 2: Figure 2. (a) Top Panel shows the western blot of the patients ALDP level (except patient number P05) in total PBMCs lysate examined with mouse anti-ALDP monoclonal antibody as explained in material and method. Lane 1 and 10 (Control by symbol “C”), Lane 2 (P01, ccALD, V635delins A & M), Lane 3 (P02, ccALD, R660Q), Lane 4 (P03, ccALD, R622fs), Lane 5 (P04, ccALD, G266R), Lane 6 (P06, ccALD, E302K), Lane 7 (P07, ccALD, R401Q), Lane 8 (P08, ccALD, K665delinsE), Lane 9 (P09, AdolCALD, G266R), Lane 11 (P10, AdolCALD, S606P), Lane 12 (P11, AdolCALD, R622fs), Lane 13 (P12, ACALD, E609K), Lane 14 (P13, ACALD, I558T), Lane 15 (P14, AMN, A646fs), Lane 16 (P15, AMN, G266R), Lane 17 (P16, asymptomatic female, R591W) and Lane 18 (P17, asymptomatic female,). The lower panel shows the GAPDH as the loading control for each lane. (b) Densometric quantification of the ALDP in X-ALD patients normalized to GAPDH. The number along the x-axis indicated the patient serial number and symbol “C” represents healthy control."
      }
    ]
  },
  {
    "id": "PMC3180231_multi",
    "image": [
      "images/PMC3180231-f1.png",
      "images/PMC3180231-f2.png",
      "images/PMC3180231-f3.png",
      "images/PMC3180231-f4.png",
      "images/PMC3180231-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A Drosophila model for the Zellweger spectrum of peroxisome biogenesis disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxins and their putative homologs in Drosophila. The putative Drosophila homologs of known peroxins that we identified in silico are presented. The main function in peroxisome biogenesis of each known peroxin is given. The PBD in which a PEX gene has been implicated is indicated in brackets. Pairwise alignment is made between the human or yeast peroxin (upper) and the putative Drosophila homolog (lower) using the SIM alignment algorithm (http://ca.expasy.org/tools/sim-prot.html) and visualized using Lalnview (http://pbil.univ-lyon1.fr/software/lalnview.html). The extent of amino acid similarity between regions of two aligned proteins is given by the Heat map at bottom. Hs, Homo sapiens; Yl, Yarrowia lipolytica; Dmel, Drosophila melanogaster.\n\nFigure 2: Figure 2. Peroxisomes are absent or exhibit altered morphology in S2 cells treated with dsRNA to putative Pex genes. (A) S2 cells constitutively expressing the fluorescent peroxisomal reporter protein GFP-SKL (Kural et al., 2005) were treated with dsRNA to the indicated putative Pex genes, mock-treated (MT) or treated with dsRNA targeting Dredd, which has no known role in peroxisome biogenesis or peroxisome function. GFP-SKL in S2 cells targets to punctae that are characteristic of peroxisomes. Mock-treated cells and cells treated with dsRNA targeting Dredd exhibited punctae in the same pattern as control cells (UT). Cells treated with dsRNAs to different Pex genes exhibited mislocalization of the GFP-SKL peroxisomal reporter to the cytosol and/or altered peroxisomal size and number. Cells treated with dsRNA to Pex7 or Pex20 exhibited punctate peroxisomes that were essentially like those of wild-type cells, because PEX7 and PEX20 affect the targeting only of peroxisomal proteins containing a PTS2 and not of those containing PTS1, such as GFP-SKL. (B) Quantitative description of peroxisome morphologies in S2 cells treated with dsRNA to putative Pex genes. Images were scored for numbers of punctate bodies, the average volume of these punctate bodies and the intensity of fluorescent signal from these punctate bodies.\n\nFigure 3: Figure 3. Detection of Pex1 transcripts by RT-PCR and of Pex1 protein by immunoblotting. (A) The specific bands corresponding to the expression levels of Pex1 and the gene Rpl32, encoding a ubiquitously expressed ribosomal protein and used as a loading control, are indicated by arrows. Heterozygous l(3)70Da animals are indicated by ‘/+’. The mRNA isolated from l(3)70DaS4648 homozygotes produced no Pex1-specific band, whereas l(3)70Da1 homozygous animals showed a severe reduction in this band compared with the Rpl32 loading control. Similarly, the level of Pex1 transcript was reduced in the dsRNA-treated S2 cells compared with untreated, mock-treated or S2 cells treated with a dsRNA that targets the Dredd gene, which is involved in the immune response. For each set of primers, specific amounts of the wild-type RT-reaction were analyzed to confirm that 2.5 μl of experimental sample yielded a product within the linear range of amplification by the subsequent PCR. (B) Pex1 protein is reduced specifically in cells treated with dsRNA to the Pex1 transcript. Lysates of untreated S2 cells, mock-treated S2 cells, S2 cells treated with dsRNA to Pex1 mRNA and S2 cells treated with dsRNA to Pex7 mRNA were separated by SDS-PAGE and subjected to immunoblotting with anti-Pex1 protein antibodies. Reduced levels of Pex1 protein are observed only in the lane containing lysate of S2 cells treated with dsRNA to Pex1 mRNA. A protein detected nonspecifically by the antibodies to Pex1 protein serves as a control for protein loading. Numbers at left represent the migrations of molecular mass standards in kDa.\n\nFigure 4: Figure 4. Pex1s4868 homozygous larvae exhibit defects in growth. Each data point represents the average size in mm2 of 20 randomly selected Pex1s4868 homozygous (green), Pex1s4868 heterozygous (purple) and wild-type (blue) larvae. On day 4, the mean area, which represents growth, of Pex1s4868 homozygous larvae is significantly reduced, as compared with wild-type and heterozygous larvae (P<0.0001). Wild-type and heterozygous larvae did not show any statistically significant difference in growth. Error bars indicate standard deviation.\n\nFigure 5: Figure 5. Pex1s4868 homozygous flies have a reduced lifespan. Survival curve of Pex1s4868 homozygous (green), Pex1s4868 heterozygous (red) and wild-type (blue) flies. All Pex1s4868 homozygous flies died by day 6 (pupariation). Wild-type and heterozygous larvae pupated on day 6. Error bars indicate standard deviation."
      }
    ]
  },
  {
    "id": "PMC3180231_multi_2",
    "image": [
      "images/PMC3180231-f6.png",
      "images/PMC3180231-f7.png",
      "images/PMC3180231-f8.png",
      "images/PMC3180231-f9.png",
      "images/PMC3180231-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A Drosophila model for the Zellweger spectrum of peroxisome biogenesis disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Pex1s4868 homozygous larvae are smaller in size than wild-type and heterozygous larvae, and fail to show coordinated movement towards food. (A) A histogram reporting the percentage of larvae that reach food in a fixed period of 20 minutes. All wild-type and heterozygous larvae, but no homozygous larvae, were able to reach the food source in the prescribed time. (B) Images of 5-day-old wild-type, Pex1s4868 heterozygous and Pex1s4868 homozygous larvae. Homozygous larvae are much smaller than heterozygous or wild-type larvae.\n\nFigure 7: Figure 7. Pex1s4868 homozygous embryos exhibit an essentially wild-type musculature. Wild-type and Pex1s4868 homozygous mutant embryos (stage 15) were analyzed by immunofluorescence microscopy using monoclonal antibody MAC147 to myosin, which recognizes all muscle. Anterior is at right in all images. Lateral views are shown, dorsal is up. Scale bar: 100 μm.\n\nFigure 8: Figure 8. The overall pattern of CNS and PNS development is abnormal in Pex1s4868 homozygous embryos. Wild-type and Pex1s4868 homozygous embryos (stage 15) were analyzed by immunofluorescence microscopy using monoclonal antibodies BP102 (anti-CNS axons), BP104 (anti-Nrg; recognizing CNS and PNS neurons) and 22C10 (anti-Futsch; recognizing neuron and axon subsets of the CNS and PNS). Anterior is to the right in all images. In lateral views, dorsal is up for BP102 and 22C10 and down for BP104. ac, anterior commissure; lc, longitudinal connective; pc, posterior commissure; VNC, ventral nerve cord. Scale bar: 100 μm.\n\nFigure 9: Figure 9. CNS and PNS neurons are disorganized in Pex1s4868 homozygous embryos. Wild-type and Pex1s4868 homozygous embryos (stage 15) were analyzed by immunofluorescence microscopy using monoclonal antibodies 2B8 (anti-Eve; recognizing the nuclei of a subset of CNS neurons), 1D4 (anti-Fas2; recognizing motor neurons and their axons in the ventral nerve cord) and 2B10 (anti-Cut; recognizing the nuclei of cells of external sensory organ precursors). Anterior is to the right in all images. In lateral views, dorsal is down for anti-Eve, and up for Fas2 and anti-Cut. ap, anal plate; asp, anterior spiracle; mt, Malpighian tubules; psp, posterior spiracle. Scale bar: 100 μm.\n\nFigure 10: Figure 10. Glial cells are disorganized in Pex1s4868 homozygous embryos. Wild-type and Pex1s4868 homozygous embryos (stage 15) were analyzed by immunofluorescence microscopy using monoclonal antibodies 8D12 (anti-Repo; recognizing all glial cells except midline glia) and 10D3 (anti-Wrapper; recognizing midline glia). Anterior is to the right in all images. In lateral views, dorsal is up. Scale bar: 100 μm."
      }
    ]
  },
  {
    "id": "PMC3236018_multi",
    "image": [
      "images/PMC3236018-f1.png",
      "images/PMC3236018-f2.png",
      "images/PMC3236018-f3.png",
      "images/PMC3236018-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Chitotriosidase as a biomarker of cerebral adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Chitotriosidase Activity is Elevated in Patients with ALD: Chitotriosidase activity was evaluated in the spinal fluid (Figure 1A) and plasma (Figure 2B) of patients with cerebral ALD or controls. There were 38 ALD patient samples and 16 controls represented in each group\n\nFigure 2: Figure 2. Chitotriosidase Activity Correlates in C-ALD Plasma and Spinal Fluid: . For the 37 patients with cerebral ALD for which both plasma and spinal fluid were available, the relative activity for both are depicted. For each patient, Statistical significance related to correlations of the 2 groups is shown (Pearson two-tailed analysis).\n\nFigure 3: Figure 3. Spinal Fluid Chitotriosidase Determinations Are Associated with MRI and Functional Scores For ALD patients with cerebral disease, the correlation of CSF chitotriosidase activity prior to transplantation and the baseline Loes MRI severity score (Fig 3A), the Loes score 1 year post transplantation (3B) and the relative increases in the Loes score from baseline to 1 year after transplantation (Loes Score; Delta; Fig 3C) are presented. The correlation of CSF chitotriosidase activity to the Moser/Raymond functional score (Table 1) prior to transplantation (Fig 3D), at 1 year after transplantation (Fig 3E) and in regards to the change in the functional score from baseline to 1 year after transplant (Functional Score; Delta; Fig 3F) are shown.\n\nFigure 4: Figure 4. Plasma Chitotriosidase Determinations Are Associated with MRI and Functional Scores: For ALD patients with cerebral disease, the correlation of plasma chitotriosidase activity prior to transplantation and the baseline Loes MRI severity score (Fig 4A), the Loes score 1 year post transplantation (4B) and the relative increases in the Loes score from baseline to 1 year after transplantation (Loes Score; Delta; Fig 4C) are presented. The correlation of plasma chitotriosidase activity to the Moser/Raymond functional score prior to transplantation (Fig 4D), at 1 year after transplantation (Fig 4E) and in regards to the change in the functional score from baseline to 1 year after transplant (Functional Score; Delta; Fig 4F) are shown."
      }
    ]
  },
  {
    "id": "PMC3276155_multi",
    "image": [
      "images/PMC3276155-f1.png",
      "images/PMC3276155-f2.png",
      "images/PMC3276155-f3.png",
      "images/PMC3276155-f4.png",
      "images/PMC3276155-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Genome-wide Fitness Profiles Reveal a Requirement for Autophagy During Yeast Fermentation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Hierarchical cluster analysis of (A) 300 homozygous and (B) 481 heterozygous diploid deletion strains with a fitness defect at 2, 4, 6, 8, 10, and 14 days of fermentation. Green, depletion; red, enrichment; black, no change; gray, no data. Numbers below the color bar represent the normalized log2 value of the microarray signal vs. day 1. Highlighted genes are in the functionally enriched categories of (A) autoproteolytic processing and modification by ubiquitination, deubiquitination, or (B) proteasome degradation. Genes that are listed twice on the clustergram have both UP and DOWN barcode tags that met the cutoff criteria.\n\nFigure 2: Figure 2. Core and starvation-induced autophagy genes contribute to cellular fitness during fermentation. The schematic is derived from Nakatogawa et al. (2009). Genes are color coded as follows: green, reduced fitness; black, no change in fitness; gray, no data obtained; purple, no homolog in S. cerevisiae.\n\nFigure 3: Figure 3. The β-ring of the proteasome core particle enhances cellular fitness during fermentation. The proteasome core particle α-ring (α1-7) and β-ring subunits (β1-7) are shown, along with the Irc25/Poc4 α-ring assembly chaperone. The proteasome regulatory particle (base and lid subunits) is also shown. Genes are color coded as follows: green, reduced fitness; red, increased fitness; black, no change in fitness; gray, no data obtained.\n\nFigure 4: Figure 4. Hierarchical cluster analysis of (A) 303 homozygous and (B) 466 heterozygous diploid deletion strains with a fitness advantage at 2, 4, 6, 8, 10, and 14 days of fermentation. Green, depletion; red, enrichment; black, no change; gray, no data. Numbers below the color bar represent the normalized log2 value of the microarray signal vs. day 1. Highlighted genes are in the functionally enriched categories of (A) peroxisome or (B) ribosomal proteins.\n\nFigure 5: Figure 5. Disruption of atg3 causes reduced CO2 and ethanol production during fermentation. EC1118 (red diamonds), wild-type (S288C, light blue circles), and atg3Δ (green squares) homozygous diploid strains were inoculated into synthetic grape juice supplemented with amino acids, and anaerobic fermentation was carried out for 16 days. Weight loss (A), ethanol (B), glucose (C), and fructose (D) measurements were taken every 2 days. Each data point on the graph represents the average of two EC1118, four wild-type, and four atg3Δ fermentations. For all graphs, error bars represent the standard deviation for each data point. (E) Growth chamber analysis of wild-type (S288C) vs. atg3Δ strain growth in YPD at 25°. Cells were inoculated into a multiwell plate at an OD600 of 0.1 and grown for 50 h. Each data point is an average of three technical replicates. For each data point, SD < ±0.04."
      }
    ]
  },
  {
    "id": "PMC3276155_multi_2",
    "image": [
      "images/PMC3276155-f6.png",
      "images/PMC3276155-f7.png",
      "images/PMC3276155-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Genome-wide Fitness Profiles Reveal a Requirement for Autophagy During Yeast Fermentation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. API processing occurs via autophagy during fermentation. Western blot analysis of cell lysates from wild-type diploid (S288C) and atg19Δ and atg1Δ homozygous diploids at days 1, 2, and 4 of fermentation. Blots were probed with anti-API antibody. Arrows point to the precursor form (pAPI) and the mature form (mAPI) of API. API, aminopeptidase I.\n\nFigure 7: Figure 7. Autophagic bodies accumulate in the vacuole during fermentation. Electron microscopy of pep4Δ/pep4Δ homozygous diploid log phase cells (A) and after two days of fermentation (B). Arrows point to autophagic bodies in the vacuole.\n\nFigure 8: Figure 8. Fermentation kinetics of the homozygous yeast deletion pool (S288C) compared with the EC1118 wine yeast strain in synthetic grape juice. Both strains [EC1118 (red diamonds) and diploid homozygous deletion set (S288C, light blue circles)] were fermented in triplicate. The average values are presented with error bars representing SD. (A) Cell growth curve measured by OD600, (B) glucose depletion, (C) ethanol production, and (D) yeast assimilable nitrogen [YAN, milligrams of nitrogen (N) per liter] measured from total ammonium sulfate and amino acids. Orange arrow in (A) marks when autophagic bodies are detected by electron microscopy. YAN, yeast assimilable nitrogen."
      }
    ]
  },
  {
    "id": "PMC3277307_multi",
    "image": [
      "images/PMC3277307-f1.png",
      "images/PMC3277307-f2.png",
      "images/PMC3277307-f3.png",
      "images/PMC3277307-f4.png",
      "images/PMC3277307-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Functional genomic analysis unravels a metabolic-inflammatory interplay in adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) A procedural diagram that indicates the pipeline followed to obtain the disease signature and progression in X-ALD mice and patients. (B) A hierarchical clustering heat-map of the expression intensities of the significantly regulated transcripts (on the Y-axis) versus the X-ALD patients and controls arrays (on the X-axis). Interestingly, we observed a clear separation between X-ALD patients and controls suggesting that hX-ALD pathology is concomitant to an alteration of transcriptional profiles.\n\nFigure 2: Figure 2. Common dysregulated pathways in spinal cords of ALD mice at 3.5, 12 and 22 months, and cerebral white matter of child and adult ALD patients. Significant KEGG pathways were identified by using the statistics gene set enrichment analysis (GSEA) (G) and hypergeometric distribution function (H). Only the pathways statistically significant in at least two tests are represented. Black spots represent dysregulated pathway when probability value P is <0.05 according to the H-test, which detects changes but does not inform about their up or down direction. Red and green spots represent up- and downregulated pathway expression based on the G-test when probability value of P is <0.05, orange spots means dysregulated pathway based on the G-test with a probability value of <0.05, in case the gene set does not have a clear tendency to be up- or downregulated. Blue circle means significant pathway with a probability value of P< 0.0001.\n\nFigure 3: Figure 3. Validation of dysregulated pathways at three different ages in Abcd1− mice spinal cords. qRT-PCR measurements of (A) adipocytokine signaling pathway, (B) aminoacyl-tRNA biosynthesis, (C) insulin signaling pathway, (D) oxidative phosphorylation and (E) ribosomal subunits. Ikbkb, NF-κB2, Tnfrsf1a, Adipor1, Sars, Gars, Aars, Akt2, Irs1, Irs2, Ndufs7, Sdha, Uqcrc1, Cox4i1, Rps9, Rps27 and Rpl23 mRNA has been quantified by qRT-PCR. 18S was used as an internal control. Significant differences have been determined by Student's t-test. Significant differences are shown as *P< 0.05 and **P< 0.01.\n\nFigure 4: Figure 4. Leptin concentration was lower in serum from Abcd1− mice (A). Leptin (pg/ml) was measured in serum from 12-month-old Wt (n= 8) and Abcd1− (n= 9) mice. Adiponectin concentration was also lower in serum from Abcd1− mice (B). Adiponectin (µg/ml) was measured in serum from 12-month-old Wt (n= 10) and Abcd1− mice (n= 12). Statistical analysis was done by Student's t-test: *P< 0.05.\n\nFigure 5: Figure 5. (A) Insulin signaling pathway in Wt and Abcd1− mouse spinal cords at 12 months of age. Western blots to monitor contents of IRS1, p-IRS1 Ser307, AKT, p-AKT Thr308, Ser473, p-S6K Thr389, JNK and p-JNK Thr183 and Tyr185 have been performed in whole spinal cord lysates from Wt and Abcd1− mice (n = 6 individuals per genotype). Representative blots are shown. Statistical analysis was done by Student's t-test: *P < 0.05. The phosphorylation of IRS1 in Ser307 was induced in Abcd1− mice spinal cord in the absence of insulin signaling activation, as shown by the lack of activation of kinases pS6K and JNK. (B) Phosphorylation of IRS1 ser307 in organotypic spinal cord slice culture (OSCSC). Western blots to monitor phosphorylation levels of IRS1 ser 307 have been performed on whole protein extracts from OSCSC (n = 6 cultures per genotype, Abcd1− or Wt littermates) incubated 24 h with BSA-conjugated C26:0 50 µm or BSA alone as control. Representative western blots are shown. C26:0 induces the IRS1 Ser307 phosphorylation in Wt but not Abcd1−-derived OSCSC."
      }
    ]
  },
  {
    "id": "PMC3277307_multi_2",
    "image": [
      "images/PMC3277307-f6.png",
      "images/PMC3277307-f7.png",
      "images/PMC3277307-f8.png",
      "images/PMC3277307-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Functional genomic analysis unravels a metabolic-inflammatory interplay in adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Activation of kinases IKK in mouse spinal cord (SC) at 12 months of age. Western blots to monitor levels of IKKα, IKKβ, IKKγ, NF-κB2 (p100/p52) and IκBα were performed in whole spinal cord lysates from Wt and Abcd1− mice (n= 6 individuals per genotype). Activated IKKs phosphorylate IκBα that liberates the NF-κB complex, which subsequently translocates into the nucleus.\n\nFigure 7: Figure 7. Activation of TLR/NF-κB in mouse spinal cords at 12 months of age. A q-PCR was performed to measure a gene array including TLRs, TLR adaptors, NF-κB forms, several cytokines and their receptors. Only differentially expressed genes are shown (n= 6 individuals per genotype). The data point to a general activation of TLR/NF-κB pathways, wherein we highlight the upregulation of Tlr8, Tlr5, Nfkbib, RANTES (Ccl5), Ccr1, Ccr2, Ccr7, Il1b, Tnf and Lta. Significant differences have been determined by Student's t-test: *P< 0.05, **P< 0.01 and ***P< 0.001.\n\nFigure 8: Figure 8. The role of oxidative stress in ALD progression in spinal cord is already manifesting as early as 3.5 months of age. The picture shows dysregulated gene expression, induced (red triangle) and repressed (green triangle), of processes and components involved in ROS generation (black stars) and antioxidant defense (white stars). Perturbations in oxidative phosphorylation, iron and calcium homeostasis and changes in GSH homeostasis may altogether represent causes and consequences of increased oxidative stress. ROS might activate NF-κB leading to the regulation of genes involved in cell survival and inflammation. 12-Hydroxyeicosatetrenoate (12-HETE), arachidonate 12-lipoxygenase (ALOX12), ATPase, Ca2+ transporting, cardiac muscle, slow twitch 2 (ATP2A2), ATPase, Ca2+ transporting, plasma membrane 1 (ATP2B1), calcium-channel, voltage-dependent, alpha 2/delta subunit 3 (CACNA2D3), calcium-channel, voltage-dependent, gamma subunit 5 (CACNG5), calcium-channel, voltage-dependent, L-type, alpha 1D subunit (CACNA1D), calcium/calmodulin-dependent protein kinase (CaM kinase) II delta (CAMK2D), calmodulin 1 (CALM1), protein phosphatase 3, catalytic subunit, alpha isoform (PPP3CA), ceruloplasmin (CP), coenzyme Q10 (CQ), coproporphyrinogen oxidase (CPOX), cystathionine beta-synthase (CBS), cytochrome b-245 (CYBA), cytochrome c (CytC), DLST, dihydroxyacetone-phosphate (DHAP), electron transport chain complexes I:V (C-I:C-V), epoxide hydrolase 1, microsomal (EPHX1), glucose-6-phosphate dehydrogenase X-linked (G6PDH), GCLC, GRX, GSH, glutathione disulfide (GSSG), GPX, glutathione reductase (GSR), GST, GSS, glyceraldehyde-3-phosphate (G3P), glycerol-3-phosphate dehydrogenase (GPDH), glyoxalase 1 (GLO1), glyoxylate reductase/hydroxypyruvate reductase (GRHPR), nuclear factor of kappa light polypeptide gene enhancer in B-cells inhibitor alpha (NFKBIA or IκBα), conserved helix–loop–helix ubiquitous kinase (CHUK or IKKα), inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase beta (IKBKB or IKKβ), inhibitor of kappa light polypeptide gene enhancer in B-cells, kinase gamma (IKBKG or IKKγ), lipid hydroperoxide (LOOH), lipid hydroxide (LOH), malic enzyme (ME), NADPH oxidase 1 (NOX1), nuclear factor of kappa light polypeptide gene enhancer in B-cells 1 and 2 (NF-κB1 and NF-κB2), OGDH, PRX, phosphodiesterase 1A, calmodulin-dependent (PDE1A), PGPX, phosphorylase kinase, alpha 1 (PHKA1), pyruvate dehydrogenase (PDH), solute carrier family 8 (sodium/calcium exchanger), member 1 (SLC8A1), thioredoxin (TRX), TCA, triosephosphate isomerase 1 (TPI), uncoupling protein 2 (UCP2), uroporphyrinogen decarboxylase (UROD), uroporphyrinogen III synthase (UROS).\n\nFigure 9: Figure 9. Proposed model for X-ALD disease mechanism. Taking together our functional validation that ensued our transcriptomic data mining and the experimental evidence provided, we put forth the following model: disease progression appears mediated by the successive action of a primarily VLCFA excess, mitochondrial dysregulation combined with ROS production and antioxidant defenses depletion, insulin desensitization, TLR activation and NF-κB-mediated proinflammatory response. The increased lipid load induces a stress response leading to the production of ROS contributing all together to a mitochondrial dysregulation. The activation of IKKs links VLCFA-induced metabolic deficiency with an NF-κB-mediated proinflammatory response. IKK activation desensitizes insulin signaling via phosphorylation of IRS1 on serines. Insulin controls glucose uptake through tyrosine phosphorylation of insulin receptor substrate (IRS) proteins. Activation of phosphatidylinositol 3-kinase (PI3K) and generation of phosphatidylinositol-3,4,5-trisphosphate (PtdIns(3,4,5)P3) activates AKT. But IRS1 serine phosphorylation attenuates insulin sensitivity and subsequently decreases glucose uptake and insulin-induced metabolism. IKKs can be induced by FA via the activation of TLRs and PKC, and the latter can be activated by DAG. The low levels of adiponectin might contribute to the increased proinflammatory response in X-ALD by reducing the inhibitory adiponectin effect on TLR signaling."
      }
    ]
  },
  {
    "id": "PMC3298485_multi",
    "image": [
      "images/PMC3298485-f1.png",
      "images/PMC3298485-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Preferential expression of mutant ABCD1 allele is common in adrenoleukodystrophy female carriers but unrelated to clinical symptoms\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Distribution of the X chromosome inactivation pattern in peripheral blood mononuclear cells of X-ALD female carriers and healthy controls. A) A severe (≥90:10) skewing of XCI was found in 30% of X-ALD carriers (9/30) and 8.6% (23/268) of healthy controls (HCs) (p = 0.0018, Fisher's exact test); a moderate (≥75:25) skewing of XCI was found in 46.7% of carriers (14/30) and 22.4% (60/268) of HCs (p = 0.0065, Fisher's exact test); a random XCI was found in 23.3% of carriers (7/30) and 69% (185/268) of HCs (p = 0.0001, Fisher's exact test). B) A severe skewing of XCI was found in 3/9 symptomatic and 6/21 asymptomatic carriers (p = 1.00; Fisher's exact test); a moderate skewing of XCI was found in 3/9 symptomatic and 11/21 asymptomatic carriers (p = 0.4397; Fisher's exact test); a random XCI was found in 3/9 symptomatic and 4/21 asymptomatic carriers(p = 0.6402; Fisher's exact test). Severe = ≥90:10; moderate = 75:25 to 89:11; random = 50:50 to 74:26.\n\nFigure 2: Figure 2. X Chromosome Inactivation (XCI) and ABCD1 Allele-Specific Expression (ASE) results in three representative samples. In the left column the electropherograms of HUMARA alleles ND (upper) and D (lower) are depicted. For each sample, the peak lengths (bps) and the corresponding area are indicated. The XCI results (ratio) are reported. In the right column the pyrograms of ASE experiments are shown and the analysed sequences of cDNA, containing the mutations (the base-change is highlighted in bold), are indicated. The mutation site is boxed in grey and the ASE (percentage of wt: mutant allele) is indicated. Sample F3 II-2shows a random XCI pattern and only a slight imbalance in ABCD1 ASE, suggesting that ABCD1 follows XCI; sample F5 II-1is characterized by severe skewing of both XCI and ABCD1 ASE, with an evident preferential expression of the mutant allele; in F3 III-1 sample XCI is moderately skewed, as well as the ABCD1 ASE. ND = DNA not digested D = DNA digested."
      }
    ]
  },
  {
    "id": "PMC3332217_multi",
    "image": [
      "images/PMC3332217-f1.png",
      "images/PMC3332217-f2.png",
      "images/PMC3332217-f3.png",
      "images/PMC3332217-f4.png",
      "images/PMC3332217-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Effects of Peroxisomal Catalase Inhibition on Mitochondrial Function\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. 3-AT inhibits catalase activity. Hs27 fibroblasts were treated with 2 mM 3-AT for varying durations. Catalase activity was determined by adding cell lysates to a 1 mM H2O2 solution. The difference in absorbance at 410 nm was due to the remaining H2O2 being converted to a yellow peroxotitanium complex by addition of TiSO4 following the 10 min incubation. Within ∼4 h of 3-AT treatment catalase activity was reduced to ∼15% that observed in untreated cells. The residual catalase activity did not diminish between 4 and 24 h of 3-AT treatment.\n\nFigure 2: Figure 2. Recovery of catalase activity requires protein synthesis. Hs27 cells were treated with 2 mM aminotriazole for 24 h followed by a 24 h recovery period (in the absence of aminotriazole) with or without 100 μg/mL of cycloheximide, an efficient inhibitor of protein synthesis. Results indicate that aminotriazole is an irreversible inhibitor of catalase, and for cells to recovery activity, synthesis of new catalase protein must occur. Determination of catalase activity is described in Section “Materials and Methods.” Letters represent values significantly different from the control and/or each other based on ANOVA analysis where p < 0.05.\n\nFigure 3: Figure 3. Catalase inhibition increases cellular 2,7-DCF staining. Hs27 fibroblasts were grown in the presence (top two panels) or absence (bottom panel) of 2 mM 3-AT for 24 h, after which they were treated with the ROS-sensitive dye 2,7-DCF (Invitrogen/Molecular Probes). Cells were live-imaged using confocal microscopy and FITC optics. Images are representative of numerous fields, imaged under identical conditions.\n\nFigure 4: Figure 4. Catalase inhibition results in increased protein carbonylation. Hs27 fibroblasts were grown in the presence or absence of 2 mM 3-AT for 4 days and protein carbonylation was determined. A quantitative spectrophotometric assay involving the derivatization of carbonyl groups with 2,4-dinitrophenylhydrazine was used, as described in Section “Materials and Methods.” An ∼7% increase in total cellular carbonyls was observed in cells treated with 3-AT (p < 0.05).\n\nFigure 5: Figure 5. Catalase inhibition increases mitochondrial DCF staining. Hs27 fibroblasts were grown in the presence (top row) or absence (bottom row) of 2 mM 3-AT for 48 h, after which they were treated with the ROS-sensitive dye 2,7-DCF (left column) and the mitochondrial ROS-sensitive dye MitoTracker Red CM-H2XRos (center column). Cells were live-imaged using confocal microscopy employing FITC optics for DCF and Texas Red optics for MitoTracker Red. Right column is a false-color overlay of the DCF and MitoTracker images. Images are representative of numerous fields, imaged under identical conditions."
      }
    ]
  },
  {
    "id": "PMC3332217_multi_2",
    "image": [
      "images/PMC3332217-f6.png",
      "images/PMC3332217-f7.png",
      "images/PMC3332217-f8.png",
      "images/PMC3332217-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Effects of Peroxisomal Catalase Inhibition on Mitochondrial Function\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Effects of treatment with 2 mM 3-AT on mitochondrial ROS staining. Control Hs27 cells (left column) demonstrate less mitochondrial ROS staining than 3-AT treated cells (right column) after 24 h (top row), 48 h (middle row), and 5 days (bottom row). In addition, staining in 3-AT treated cells appeared homogeneous throughout the mitochondria. Live cells were imaged under identical conditions, and are representative of numerous fields viewed and imaged.\n\nFigure 7: Figure 7. Inhibition of peroxisomal catalase results in the inhibition of mitochondrial aconitase. Hs27 cells were grown in the presence or absence of 2 mM 3-AT for 24 h. Aconitase activity was determined using a linked assay, as described in Section “Materials and Methods.” For recovery experiments, Hs27 cells were treated with 3-AT for 24 h followed by a 24 h recovery period (in the absence of 3-AT) with or without 100 μg/mL of cycloheximide, an inhibitor of protein synthesis. Results indicate the inhibition of the peroxisomal antioxidant enzyme, catalase, results in significant inhibition of the oxidatively sensitive mitochondrial enzyme, aconitase (p < 0.05). While aconitase activity recovers following the removal of 3-AT, this activity fails to recover and was undetectable in the presence of cycloheximide.\n\nFigure 8: Figure 8. 3-AT does not directly inhibit aconitase activity. Untreated Hs27 cell lysates were assayed for aconitase activity in the presence of absence of 2 mM 3-AT. No significant decrease in aconitase activity was observed in treated cell lysates when compared with untreated controls.\n\nFigure 9: Figure 9. Effects of treatment with 2 mM 3-AT for 4 days on mitochondrial inner membrane potential. Control Hs27 cells (upper two rows) and 3-AT treated cells (lower two rows) were incubated with JC-1 dye and imaged for the presence of the aggregate (left column, red) and the monomeric (center column, green) forms of the dye. Live cells were imaged under identical conditions, and are representative of numerous fields viewed and imaged. The increase in the monomeric, green form of the dye is indicative of a depolarization of the mitochondrial inner membrane. Treated cells had a 30% higher mean pixel intensity than control cells (143 ± 14 vs. 110 ± 10) in the monomeric form of the dye (p < 0.05)."
      }
    ]
  },
  {
    "id": "PMC3377275_multi",
    "image": [
      "images/PMC3377275-f1.png",
      "images/PMC3377275-f2.png",
      "images/PMC3377275-f3.png",
      "images/PMC3377275-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The role of ELOVL1 in very long-chain fatty acid homeostasis and X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. D3-C22:0 levels in control versus X-ALD cell lines.D3-C26:0 levels in control versus X-ALD cell lines.D3-C26:0/D3-C22:0 ratio in control versus X-ALD cell lines.Eight control and 25 X-ALD cell lines were cultured for 72 h with 50 µM D3-C16:0. Fatty acids are in nmol/mg protein. Data are mean ± SD. **p < 0.01, ***p < 0.001 by unpaired student's t-test. D3-C22:0 levels in control versus X-ALD cell lines. D3-C26:0 levels in control versus X-ALD cell lines. D3-C26:0/D3-C22:0 ratio in control versus X-ALD cell lines. Eight control and 25 X-ALD cell lines were cultured for 72 h with 50 µM D3-C16:0. Fatty acids are in nmol/mg protein. Data are mean ± SD. **p < 0.01, ***p < 0.001 by unpaired student's t-test.\n\nFigure 2: Figure 2. Pristanoyl-CoA levels in control versus X-ALD cell lines.C24:0-CoA levels in control versus X-ALD cell lines.C26:0-CoA levels in control versus X-ALD cell lines.Fatty acyl-CoAs are in pmol/mg protein. Data are mean ± SD in 3 control and 6 X-ALD cell lines. ***p < 0.001 by unpaired student's t-test. Pristanoyl-CoA levels in control versus X-ALD cell lines. C24:0-CoA levels in control versus X-ALD cell lines. C26:0-CoA levels in control versus X-ALD cell lines. Fatty acyl-CoAs are in pmol/mg protein. Data are mean ± SD in 3 control and 6 X-ALD cell lines. ***p < 0.001 by unpaired student's t-test.\n\nFigure 3: Figure 3. ELOVL1 mRNA expression in 6 control and 9 X-ALD cell lines. Data are mean ± SD.ELOVL1 protein expression in control and X-ALD cell lines. (+) positive control: CHO cells expressing ELOVL1. ELOVL1 mRNA expression in 6 control and 9 X-ALD cell lines. Data are mean ± SD. ELOVL1 protein expression in control and X-ALD cell lines. (+) positive control: CHO cells expressing ELOVL1.\n\nFigure 4: Figure 4. ELOVL1 expression in X-ALD fibroblasts cultured for 3, 4, 5 or 6 days in medium devoid of (−) or supplemented with (+) ELOVL1 siRNA.ELOVL1 expression in X-ALD fibroblasts which were untransfected (−) or transfected (+) with siRNA targeting either cyclophilin-B (control) or ELOVL1.Effect of control siRNA (white bars) or ELOVL1 siRNA (grey bars) on cell proliferation in comparison with untransfected cells (black bars).D3-C26:0 levels in ELOVL1 siRNA transfected (grey bars) versus untransfected (black bars) X-ALD fibroblasts.C26:0 levels in control and X-ALD fibroblasts which were untransfected (black bars) and in X-ALD fibroblasts which were transfected with either control siRNA (white bars) or ELOVL1 siRNA (grey bars). Fatty acids are in nmol/mg protein. Data are mean ± SD. ***p < 0.001 by unpaired student's t-test. ELOVL1 expression in X-ALD fibroblasts cultured for 3, 4, 5 or 6 days in medium devoid of (−) or supplemented with (+) ELOVL1 siRNA. ELOVL1 expression in X-ALD fibroblasts which were untransfected (−) or transfected (+) with siRNA targeting either cyclophilin-B (control) or ELOVL1. Effect of control siRNA (white bars) or ELOVL1 siRNA (grey bars) on cell proliferation in comparison with untransfected cells (black bars). D3-C26:0 levels in ELOVL1 siRNA transfected (grey bars) versus untransfected (black bars) X-ALD fibroblasts. C26:0 levels in control and X-ALD fibroblasts which were untransfected (black bars) and in X-ALD fibroblasts which were transfected with either control siRNA (white bars) or ELOVL1 siRNA (grey bars). Fatty acids are in nmol/mg protein. Data are mean ± SD. ***p < 0.001 by unpaired student's t-test."
      }
    ]
  },
  {
    "id": "PMC3465988_multi",
    "image": [
      "images/PMC3465988-f1.png",
      "images/PMC3465988-f2.png",
      "images/PMC3465988-f3.png",
      "images/PMC3465988-f4.png",
      "images/PMC3465988-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Farnesyl diphosphate synthase, the target for nitrogen-containing bisphosphonate drugs, is a peroxisomal enzyme in the model system Dictyostelium discoideum\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic representation of DdFDPS showing the putative PTS2 in red. The amino acid sequence of the PTS2 in FDPS from D. discoideum (UniProt number Q9NH03) is compared with the amino acid sequences of the consensus PTS2 sequences in FDPS from the related species D. purpureum (Dp) (UniProt number F0Z8Y9) and D. fasciculatum (Df) (UniProt number F4PYV9). Amino acid residues matching the consensus sequence are indicated in red. The consensus PTS2 sequence is shown in the form proposed in [16]. (B) Amoebae expressing GFP–PTS1 (I), S. cerevisiae thiolase (possessing a PTS2) fused to GFP (PTS2–GFP) (II), GFP (III) or DdFDPS–GFP (IV) were imaged by use of epifluorescence microscopy and the images are shown as maximum intensity projections of Z-stacks. (C) Unfixed amoebae expressing both mRFP–PTS1 and FDPS–GFP were imaged (I). Because peroxisomes tend to move during imaging, the RFP and GFP fluorescence do not appear to colocalize completely. However, after amoebae had been fixed in 3.6% (v/v) formaldehyde (II), complete colocalization of the RFP and GFP fluorescence is apparent, although fixation partially destroys cell morphology. ‘Merge’ is the overlay of the GFP fluorescence and the bright-field image (B) or the overlay of the GFP and RFP fluorescence (C). Scale bar represents 20 μm.\n\nFigure 2: Figure 2. Amoebae were transformed with the DdFDPS–GFP expression plasmid (pFDPS–GFP) and grown in the presence of either alendronate (80 μM) or the antibiotic G418 (10 μg/ml). Amoebae were imaged by use of epifluorescence microscopy at the times indicated after addition of either alendronate or G418. All images were captured with the same exposure times and processed identically. An enhanced image of G418-selected cells is included to show the high percentage of low-expressing cells. The percentage of cells displaying detectable FDPS–GFP expression is indicated for each time point (at least 200 cells were counted each time). Scale bar represents 50 μm.\n\nFigure 3: Figure 3. Amoebae co-expressing DdFDPS–GFP with either mRFP (A) or mRFP–PTS1 (B) were incubated with digitonin (50 μg/ml) and analysed by epifluorescence microscopy. Selective permeabilization of the plasma membrane at this digitonin concentration is slow and some cells permeabilize earlier than others. Arrowheads indicate cells with time-dependent permeabilization. Scale bar represents 20 μm.\n\nFigure 4: Figure 4. S. cerevisiae strains co-expressing the peroxisomal matrix marker HcRed–PTS1 and DdFDPS–GFP were imaged by use of epifluorescence microscopy. Images are shown as maximum intensity projections of Z-stacks. Scale bar represents 5 μm. WT, wild-type.\n\nFigure 5: Figure 5. (A) Characterization of the targeting information in the N-terminus of DdFDPS. Amoebae were transformed to express either amino acid residues 1–22 (I) or amino acid residues 11–22 (II) of DdFDPS fused to GFP. The first PTS2 amino acid residue (Arg8) was mutated to alanine in the construct comprising amino acids 1–22 of DdFDPS fused to GFP and expressed in D. dicoideum amoebae (III). Similarly, the eighth residue in the PTS2 (His15) was also mutated to alanine (IV). Unfixed amoebae were imaged by epifluorescence microscopy and the images are shown as maximum intensity projections of Z-stacks. (B) Unfixed amoebae expressing mRFP–PTS1 and either 1-22–GFP (I) or 1-22–GFP (His15Ala) (II) were imaged. Scale bar represents 20 μm."
      }
    ]
  },
  {
    "id": "PMC3470570_multi",
    "image": [
      "images/PMC3470570-f1.png",
      "images/PMC3470570-f2.png",
      "images/PMC3470570-f3.png",
      "images/PMC3470570-f4.png",
      "images/PMC3470570-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Targeting the Oncogenic E3 Ligase Skp2 in Prostate and Breast Cancer Cells with a Novel Energy Restriction-Mimetic Agent\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Structure of CG-12. (B) Relative expression levels of Skp2 and β-TrCP in six different prostate and breast cancer cell lines. (C) Western blot analysis of the dose- or time-dependent effects of CG-12, 2-DG, and glucose deprivation on the expression of Skp2, β-TrCP, and Sp1 in LNCaP (upper panel) and MDA-MB-468 cells (lower panel). Cells were exposed to CG-12 or 2-DG at the indicated concentrations in 10% FBS-supplemented medium for 72 h. (D) RT-PCR analysis of the dose-dependent effect of CG-12 on the mRNA expression of Skp2, β-TrCP, and Sp1 in LNCaP cells after 72 h of treatment.\n\nFigure 2: Figure 2. (A) Western blot (left panel) and RT-PCR (right panel) analyses of the effects of siRNA-mediated knockdown of Skp2 on the expression levels of β-TrCP and Sp1 in LNCaP, PC-3, MDA-MB-231, and/or MDA-MB-468 cells. (B) Western blot (left panel) and RT-PCR (right panel) analyses of the effects of ectopic expression of β-TrCP on the expression of levels of Sp1 and Skp2 in LNCaP, PC-3, MDA-MB-231, and/or MDA-MB-468 cells. Scrb, scrambled siRNA control; pCMV, empty vector control.\n\nFigure 3: Figure 3. (A) Western blot analysis of the dose-dependent effects of CG-12 on the expression of Emi1, Cdh1, and various F-box proteins related to cell proliferation, including Fbw7, Fbx2, Fbx4, Fbx7, Fbx31, and Fbxw8, after 72 h of treatment. (B) Western blot analysis of the time-dependent effects of 5 µM CG-12 (left panel) and 5 mM 2-DG (right panel) on the expression levels of Sirt1, Csn5, Skp2, and β-TrCP. (C) RT-PCR analysis of time-dependent effects of 5 µM CG-12 on the mRNA expression levels of Sirt1, Csn5, Skp2, and β-TrCP. (D) Ectopic expression of Sirt1 mimicked the effects of ERMAs on the expression of Csn5, Skp2 and β-TrCP proteins. (E) Dominant-negative inhibition of Sirt1 by ectopically expressed H363Y-Sirt1 protected cells from the effect of CG-12 on the expression of Csn5, Skp2 and β-TrCP proteins. (F) Pharmacological inhibition of Sirt1 deacetylase activity by nicotinamide and splitomycin protected cells from the effect of CG-12 on the expression of Csn5, Skp2 and β-TrCP proteins.\n\nFigure 4: Figure 4. (A) Overexpression of wild-type Csn5, but not the deneddylase-deficient D151N mutant, protected against the time-dependent effects of CG-12 (left panel) and 2-DG (right panel) on the expression of Skp2 and β-TrCP proteins. (B) Exposure to 5 µM CG-12 gave rise to a time-dependent increase in Cul1 neddylation, which paralleled changes in the expression levels of Skp2 and β-TrCP shown in Fig. 3B. (C) CG-12-mediated changes in Skp2 and β-TrCP expression were blocked by ectopically expressed K720A-Cul1, a dominant-negative form of Cul1 lacking the Nedd8 modification site.\n\nFigure 5: Figure 5. (A) Ectopic expression of Skp2 abrogated CG-12-induced upregulation of β-TrCP protein expression, while the ectopic expression of the negative control Fbw7 showed no appreciable effect. (B) siRNA-mediated silencing of Skp2 enhanced the suppressive effect of CG-12 on β-TrCP ubiquitination. LNCaP cells were co-transfected with plasmids encoding β-TrCP-Myc and ubiquitin (UB)-HA, with or without Skp2 siRNA, and then treated with 5 µM CG-12 in 10% FBS-supplemented medium for the indicated time intervals. Equal amounts of cell lysates were probed with anti-Myc or anti-Skp2 antibodies (left panel; input) or immunoprecipitated (IP) with anti-Myc affinity gels, followed by immunoblotting (WB) with anti-Myc or anti-HA antibodies (right panel). (C) Pull-down analysis of the selective binding of β-TrCP to Skp2 versus Fbw7. LNCaP cells were nucleofected with plasmids encoding Skp2-Myc or Fbw7-Myc, or with empty pCMV vector. Equal amounts of cell lysates were probed with anti-β-TrCP or anti-Myc antibodies (left panel; input) or immunoprecipitated (IP) with anti-Myc affinity gels, followed by immunoblotting (WB) with anti-β-TrCP or anti-Myc antibodies (right panel). (D) In vitro pull-down of β-TrCP-Myc versus Fbw7-Myc by bacterially expressed GST-Skp2. LNCaP cells were transfected with plasmids encoding β-TrCP-Myc or Fbw7-Myc, and equal amounts of cell lysates were incubated with bacterially expressed GST, or GST-Skp2 immobilized onto glutathione beads. The resulting complexes were washed, centrifuged and subjected to Western blot analysis (WB) with anti-Myc antibodies (right panel). One tenth volume of each cell lysate was collected as input and then probed with anti-Myc antibodies, and used to confirm purity and integrity of the recombinant GST-fusion proteins (GST and GST-Skp2) with GST antibody (left panel)."
      }
    ]
  },
  {
    "id": "PMC3470570_multi_2",
    "image": [
      "images/PMC3470570-f6.png",
      "images/PMC3470570-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Targeting the Oncogenic E3 Ligase Skp2 in Prostate and Breast Cancer Cells with a Novel Energy Restriction-Mimetic Agent\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Upper panel, schematic representation of the structures of the wild type and mutant forms of β-TrCP-Myc. Lower panels, pull-down analysis of the binding of different mutant forms of β-TrCP-Myc versus the wild-type β-TrCP to endogenous Skp2 in LNCaP cells. LNCaP cells were nucleofected with plasmids encoding wild type (1) or mutated forms (2–6) of β-TrCP-Myc. Equal amounts of cell lysates were probed with anti-Myc or anti-Skp2 antibodies (left panel; input) or immunoprecipitated (IP) with anti-Myc affinity gels, followed by immunoblotting (WB) with anti-Myc or anti-Skp2 antibodies (right panel). (B) Identification of the kinase responsible for the proline-directed phosphorylation of Ser-412 required for Skp2-mediated β-TrCP degradation. LNCaP cells ectopically expressing Skp2-Myc were exposed to DMSO vehicle, the CDK2 inhibitor roscovitine (10 µM), the GSK3β inhibitor SB216763 (10 µM), the ERK inhibitor PD98059 (25 µM), and the JNK inhibitor SP600125 (10 µM) for 24 h. Cell lysates were immunoblotted with anti-β-TrCP and anti-Myc antibodies. (C) The S412A mutation of β-TrCP blocks Skp2 recognition and Skp2-mediated ubiquitination of β-TrCP. LNCaP cells were co-transfected with plasmids encoding Skp2-Myc, ubiquitin (UB)-HA, and the wild type or S412A form of β-TrCP-Flag versus pCMV, and incubated for 24 h. Equal amounts of cell lysates were probed with anti-Myc or anti-Flag antibodies (lower panel; input) or immunoprecipitated (IP) with anti-Flag affinity gels, followed by immunoblotting (WB) with anti-HA or anti-Myc antibodies (upper panel). (D) Identification of the β-TrCP-interacting region of Skp2 by mutational analysis of Skp2 binding to β-TrCP. Upper panel, schematic representation of the structures of wild type and truncated forms of the Skp2-Myc fusion protein. Lower panels, pull-down analysis of the binding of wild type versus different truncated forms of Skp2-Myc to endogenous β-TrCP in LNCaP cells. Wild type (1) and truncated forms (2–4) of Skp2-Myc were ectopically expressed in LNCaP cells. Equal amounts of cell lysates were probed with anti-Myc or anti-β-TrCP antibodies (left panel; input) or immunoprecipitated (IP) with anti-Myc affinity gels, followed by immunoblotting (WB) with anti-Myc or anti-β-TrCP antibodies (right panel).\n\nFigure 7: Figure 7. (A) Sequence of the promoter region of the SKP2 gene showing two putative Sp1 recognition sites [Sp1(A), Sp1(B)], as well as one putative binding site each for YY-1 and GATA-1. TSS, transcriptional start site. (B) Left panel, siRNA-mediated Sp1 knockdown suppressed Skp2 protein expression in LNCaP cells. Right panel, overexpression of Sp1 protected cells against CG-12-mediated suppression of Skp2 protein expression. (C) Time-dependent decreases in the recruitment of Sp1 to the Skp2 gene promoter in response to CG-12 treatment in LNCaP cells as determined by ChIP analysis. (D) Mutations at the Sp1 A and/or B binding sites, but not at the YY1 or GATA-1 site, abrogated CG-12-mediated suppression of Skp2 promoter transcriptional activity as determined by promoter-luciferase reporter assays. Columns, means (n = 3); bars, S.D. (E) Schematic diagram depicting a novel Skp2-β-TrCP-Sp1 regulatory loop downstream of Sirt1-mediated downregulation of Csn5 in response to energy restriction, culminating in accentuated upregulation of β-TrCP-mediated apoptosis signaling."
      }
    ]
  },
  {
    "id": "PMC3470694_multi",
    "image": [
      "images/PMC3470694-f1.png",
      "images/PMC3470694-f2.png",
      "images/PMC3470694-f3.png",
      "images/PMC3470694-f4.png",
      "images/PMC3470694-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Bezafibrate lowers very long-chain fatty acids in X-linked adrenoleukodystrophy fibroblasts by inhibiting fatty acid elongation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Only BF, and not other drugs from the fibrate class, reduces C26:0 in X-ALD fibroblasts. (a) C26:0 levels in 3 X-ALD cell lines cultured for 7 days without drugs (black bar), in the presence of BF (gray bar), fenofibrate (white bar), or clofibrate (hatched bar). (b) C26:0 levels in 3 X-ALD cell lines cultured for 7 days without drugs (black bar), in the presence of BF (gray bar), agonists of PPAR-α (WY 14643), PPAR-β (GW 501516) and PPAR-γ (rosiglitazon), or with different combinations of PPAR agonists (white bars). (c) C26:0 levels in 8 control (white bar) and 8 X-ALD cell lines cultured without (black bar) or with 400 μM BF (gray bars) for up to 3 weeks. Fatty acid levels are in nmol/mg protein. Data are mean ± SD. * = p < 0.05, ** = P < 0.01, *** = P < 0.001 by ANOVA followed by Dunnett's multiple comparison test compared with untreated X-ALD cells\n\nFigure 2: Figure 2. BF, but not other fibrates, inhibits D3-C26:0 synthesis. (a) D3-C26:0 synthesis from D3-C16:0 in 5 X-ALD cell lines cultured for 3 days without drugs (black bar) and in the presence of BF (gray bar), fenofibrate (FF, white bar), or clofibrate (CF, hatched bar). (b) D3-C26:0 analysis from D3-C16:0 in 4 control (white bar) and 4 X-ALD cell lines cultured for 3 days without (black bar) or with increasing concentrations of BF (gray bars). Fatty acid levels are in nmol/mg protein. Data are mean ± SD. ** = P < 0.01, *** = P < 0.001 by ANOVA followed by Dunnett's multiple comparison test compared with untreated X-ALD cells\n\nFigure 3: Figure 3. Effect of BF on mitochondrial and peroxisomal β-oxidation and peroxisome number. Measurement of (a) C16:0 β-oxidation and (b) C26:0 β-oxidation activity in 5 control cell lines (white bar) and 5 X-ALD cell lines cultured without (black bar) or with 400 μM BF (gray bar) for 7 days. Activities are in pmol/mg/hour. Data are mean ± SD. * = P < 0.05 and *** = P < 0.001 by ANOVA followed by Dunnett's multiple comparison test compared with untreated X-ALD cells. (c) Peroxisome number in 10 X-ALD cell lines cultured without (white bar) or with 400 μM BF (gray bar) for 3 days. Mean and quartiles are indicated, the error bars represent the range\n\nFigure 4: Figure 4. C26:0 reduction by BF is not mediated by increased peroxisomal β-oxidation. Analysis of de novo D3-C26:0 synthesis in 3 X-ALD (black bar) cell lines and 3 cell lines from patients with a peroxisomal biogenesis disorder (PBD, white bar). Cells were incubated with 50 μM D3-C16:0 for 3 days without or with 400 μM BF (cross-hatched bars). Fatty acid levels are in nmol/mg protein. Data are mean ± SD. *** = p < 0.001 by student’s unpaired t-test\n\nFigure 5: Figure 5. C26:0 reduction by BF is not mediated by increased mitochondrial β-oxidation. (a) C18:1 β-oxidation in 3 X-ALD cell lines cultured without (black bar), or for 48 hours with 400 μM BF (gray bar), or with BF and increasing concentrations of MK-886 (white bars). Activities are in pmol/mg/hour. Data are mean ± SD. (b) De novo D3-C26:0 synthesis in 4 X-ALD cell lines incubated with 50 μM D3-C16:0 without (black bar) or with 400 μM BF (gray bar), 50 μM MK-886 (white bar), or 400 μM BF and 50 μM MK-886 (cross-hatched bar). Fatty acid levels are in nmol/mg protein. Data are mean ± SD. ** = p < 0.01; *** = p < 0.001 by ANOVA followed by Dunnett's multiple comparison test compared with untreated X-ALD cells"
      }
    ]
  },
  {
    "id": "PMC3470694_multi_2",
    "image": [
      "images/PMC3470694-f6.png",
      "images/PMC3470694-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Bezafibrate lowers very long-chain fatty acids in X-linked adrenoleukodystrophy fibroblasts by inhibiting fatty acid elongation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Effect of BF on gene expression of genes involved in fatty acid metabolism. Expression levels of genes involved in fatty acid metabolism in 3 X-ALD cell lines cultured without (black bars) or with 400 μM BF (gray bars) for 48 hours were analyzed by quantitative PCR. Data are mean ± SD. * = p < 0.05 by student’s unpaired t-test\n\nFigure 7: Figure 7. BF inhibits fatty acid elongation. (a) Fatty acid elongation activity of C16:0-CoA (a substrate of ELOVL6) in the presence of an increasing concentration of BF (o) and BF-CoA (●). (b) Fatty acid elongation activity of C22:0-CoA (a substrate of ELOVL1) in the presence of an increasing concentration of BF (o) and BF-CoA (●) or with an increasing concentration of fenofibrate (FF, □) or clofibrate (CF, ∆). Fatty acid elongation activity was measured using 20 μM C16:0-CoA or C22:0-CoA as substrate with concentrations of the inhibitor up to 400 μM. Error bars represent the standard deviation"
      }
    ]
  },
  {
    "id": "PMC3472792_multi",
    "image": [
      "images/PMC3472792-f1.png",
      "images/PMC3472792-f2.png",
      "images/PMC3472792-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Several Lipid-Related Gene Polymorphisms Interact with Overweight/Obesity to Modulate Blood Pressure Levels\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Genotyping of 10 lipid-related gene polymorphisms by polymerase chain reaction and restriction fragment length polymorphism (PCR-RFLP). ABCA1, ATP-binding cassette transporter A1. Lane M, 100 bp marker ladder; lanes 1 and 2, GG genotype (525 bp); lanes 3 and 4, GA genotype (525-, 302- and 223-bp); and lanes 5 and 6, AA genotype (302- and 223-bp); ACAT-1, acyl-CoA:cholesterol acyltransferase-1. Lane M, 100 bp marker ladder; lanes 1–3, AA genotype (389 bp); lanes 4 and 5, AC genotype (389-, 279- and 110-bp); and lanes 6 and 7, CC genotype (279- and 110-bp); LDL-R, low density lipoprotein receptor. Lane M, 50 bp marker ladder; lanes 1–6, A+A+ genotype (141- and 87-bp); lanes 7–12, A-A+ genotype (228-, 141- and 87-bp); and lanes 13–15, A-A- genotype (228-bp); LIPC, hepatic lipase gene. Lane M, 100 bp marker ladder; lanes 1–3, GG genotype (411 bp); lane 4, GA genotype (411-, 301- and 110-bp); and lanes 5–7, AA genotype (301- and 110-bp); LIPG, endothelial lipase gene. Lane M, 50 bp marker ladder; lane 1, the PCR product of the sample (254 bp); lanes 2 and 3, CC genotype (254 bp); lanes 4 and 5, CT genotype (254-, 217- and 37-bp); and lanes 6 and 7, TT genotype (217- and 37-bp). The 37 bp fragment was invisible in the gel owing to its fast migration speed; MTHFR, methylenetetrahydrofolate reductase. Lane M, 50 bp marker ladder; lanes 1–3, CC genotype (245 bp); lanes 4–6, CT genotype (245-, 173- and 72-bp); and lanes 7 and 8, TT genotype (173- and 72-bp); MYLIP, the E3 ubiquitin ligase myosin regulatory light chain-interacting protein. Lane M, 100 bp marker ladder; lanes 1 and 2, AA genotype (387 bp); lanes 3 and 4, AG genotype (387-, 306- and 81-bp); and lanes 5 and 6, GG genotype (306- and 81-bp); PCSK9, proprotein convertase subtilisin-like kexin type 9. Lane M, 100 bp marker ladder; lanes 1 and 2, PCR products of the samples (440 bp); lanes 3 and 4, AG genotype (440-, 290- and 150-bp); and lanes 5 and 6, AA genotype (290- and 150-bp). The GG homozygous of the PCSK9 E670G was not detected in our study population; PPARD, peroxisome proliferator-activated receptor delta. Lane M, 100 bp marker ladder; lanes 1 and 2, TT genotype (269 bp); lanes 3–5, TC genotype (269-, 167- and 102-bp); and lanes 6 and 7, CC genotype (167- and 102-bp); SCARB1, Scavenger receptor class B type 1. Lane M, 50 bp marker ladder; lanes 1 and 2, TT genotype (218 bp); lanes 3 and 4, CT genotype (218-, 187- and 31-bp); and lanes 5 and 6, CC genotype (187- and 31-bp). The 31 bp fragment was invisible in the gel owing to its fast migration speed.\n\nFigure 2: Figure 2. The parts of the nucleotide sequence of 10 lipid-related gene polymorphisms by direct sequencing. ABCA-1, ATP-binding cassette transporter A1; ACAT-1, acyl-CoA:cholesterol acyltransferase-1; LDL-R, low density lipoprotein receptor; LIPC, hepatic lipase gene; LIPG, endothelial lipase gene; MTHFR, methylenetetrahydrofolate reductase; MYLIP, the E3 ubiquitin ligase myosin regulatory light chain-interacting protein. PCSK9, proprotein convertase subtilisin-like kexin type 9; PPARD, peroxisome proliferator-activated receptor delta; SCARB1, Scavenger receptor class B type 1.\n\nFigure 3: Figure 3. The genotypes of 10 SNPs and blood pressure levels between the normal weight and overweight/obese subjects. SBP, systolic blood pressure; DBP, diastolic blood pressure; PP, pulse pressure; ABCA-1, ATP-binding cassette transporter A1; ACAT-1, acyl-CoA:cholesterol acyltransferase-1; LDL-R, low density lipoprotein receptor; LIPC, hepatic lipase gene; LIPG, endothelial lipase gene; MTHFR, methylenetetrahydrofolate reductase; MYLIP, the E3 ubiquitin ligase myosin regulatory light chain-interacting protein; PCSK9, proprotein convertase subtilisin-like kexin type 9; PPARD, peroxisome proliferator-activated receptor delta; SCARB1, Scavenger receptor class B type 1. Sex, age, education level, physical activity, alcohol consumption, cigarette smoking, and hyperlipidemia have been adjusted for the statistical analysis. a p < 0.01 and b p < 0.001 (after permutation correction)."
      }
    ]
  },
  {
    "id": "PMC3503704_multi",
    "image": [
      "images/PMC3503704-f1.png",
      "images/PMC3503704-f2.png",
      "images/PMC3503704-f3.png",
      "images/PMC3503704-f4.png",
      "images/PMC3503704-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"X-linked adrenoleukodystrophy (X-ALD): clinical presentation and guidelines for diagnosis, follow-up and management\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MRI of the brain in a case of childhood cerebral ALD showing characteristic extensive white matter changes in the parieto-occipital region and internal capsules on FLAIR sequences (A). This area is initially affected in about 80% of cases of cerebral ALD. The rim enhances after administration of gadolinium on T1 sequences (B). In about 20% of cases the site of initial involvement in cerebral ALD is the frontal white matter as shown on this FLAIR image of a different patient with cerebral ALD (C), with prominent rim enhancement after administration of gadolinium on a T1 weighted image (D).\n\nFigure 2: Figure 2. MRI of the brain in a patient with AMN showing increased signal in the pyramidal tracts on T2-weighed coronal (A) and axial (B) images indicative of Wallerian degeneration.\n\nFigure 3: Figure 3. MRI of the brain (T2 (A) and FLAIR (C) images; T1 with gadolinium (B, D)) of a patient with AMN who rapidly deteriorated clinically with new symptoms of cognitive decline. On MRI extensive white matter changes were seen in the parieto-occipital white matter and corpus callosum (A), but no enhancement of the lesion after administration of gadolinium (B). A follow-up MRI about 3 months later shows progression of the white matter lesion (C) and there is now faint enhancement of the rim of the lesion after gadolinium administration (D).\n\nFigure 4: Figure 4. Thin and scanty scalp hair in a man with X-ALD (AMN phenotype). Written informed consent was obtained from the patient for publication of these images.\n\nFigure 5: Figure 5. Flowchart describing the outpatient management of X-ALD. *If there is no gadolinium enhancement present, consider arrested cerebral ALD and repeat the MRI in 3 months."
      }
    ]
  },
  {
    "id": "PMC3514026_multi",
    "image": [
      "images/PMC3514026-f1.png",
      "images/PMC3514026-f2.png",
      "images/PMC3514026-f3.png",
      "images/PMC3514026-f4.png",
      "images/PMC3514026-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitylation by Trim32 causes coupled loss of desmin, Z-bands, and thin filaments in muscle atrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Trim32 is required for muscle atrophy induced by fasting. TA muscles were electroporated with shRNA vectors against Trim32 (shTrim32) or Lacz (shLacz), and 4 d later mice were deprived of food for 2 d. In fed mice, muscles were dissected 6 d after electroporation. Electroporation of shLacz into fibers of fasted or fed control mice did not affect fiber size (Sandri et al., 2004). (A) shRNA-mediated knockdown of Trim32 in HEK293 cells (top) and muscles from fasted animals (bottom). Soluble extracts were analyzed by immunoblotting. (B) Down-regulation of Trim32 in muscles from fasted mice reduces fiber atrophy. Measurement of cross-sectional area of 500 fibers transfected with shTrim32 (and expressing GFP; black bars) vs. 500 nontransfected fibers (open bars) in the same muscle. Data acquired from six mice. Green fibers express shTrim32 and laminin staining in red. Bar, 75 µM. (C) Down-regulation of Trim32 attenuates the loss of muscle mass during fasting. shTrim32 was delivered to more than 70% of muscle fibers. Mean weights of electroporated muscles are plotted as the percent weight loss. n = 6. *, P < 0.001 vs. fed control; #, P < 0.05 vs. shLacz (see also data in Fig. 5 B). (D) Down-regulation of Trim32 prevents the loss of thin and slightly reduced the loss of thick filament components during fasting. Left: isolated myofibrils from shLacz- (shaded) or shTrim32-expressing muscles (open) were analyzed by SDS-PAGE and Coomassie blue staining. To obtain the absolute content of each myofibrillar protein, densitometric measurement of specific bands was performed, and the values were multiplied by the total amount of myofibrils per muscle and then by muscle weight. The content of each myofibrillar protein is presented as the percentage of fed control. n = 6. *, P < 0.05 vs. fed control; #, P < 0.05 vs. shTrim32. Right: equal fractions of myofibrils were analyzed by Western blot using anti-actin and anti-MyHC. (E) Trim32 is not induced upon fasting. Top: soluble fraction of muscles, 1 or 2 d after food deprivation, were analyzed by SDS-PAGE and immunoblotting. Bottom: quantitative RT-PCR of mRNA preparations from atrophying and control muscles using primers for MuRF1 and Trim32. Data are plotted as the mean fold change relative to control. n = 6.\n\nFigure 2: Figure 2. Actin and other myofibrillar proteins are substrates for Trim32. (A) In vitro ubiquitylation of actin, tropomyosin (Tm), and MyLC by Trim32 was analyzed by immunoblotting with specific antibodies. Asterisk represents nonspecific bands. (B) Muscle extracts contain soluble forms of actin, α-actinin, Tm, MyHC, MyLC2, and MyBP-C, whose loss requires Trim32 during fasting. Soluble fractions of normal and atrophying muscles expressing shLacz or shTrim32 were analyzed by SDS-PAGE, and immunoblot analysis using antibodies against the indicated proteins. Each lane is a separate muscle, and representative bands were chosen based on similar atrophy rates in transfected muscles.\n\nFigure 3: Figure 3. Desmin is lost during atrophy induced by fasting. (A) Paraffin-embedded longitudinal sections of TA muscle from fed mice and ones deprived of food (2 d) were stained with an antibody against desmin. Bar, 25 µM. (B) During fasting, depolymerization of desmin filaments is prevented in muscle fibers expressing Trim32-DN. Paraffin-embedded longitudinal sections of TA muscles expressing Trim32-DN (green) from fasted mice were stained with an antibody against desmin (red). Desmin filaments are degraded in two fibers, which do not express Trim32-DN, at the two opposite edges of the image. Expression of Trim32-DN in the three fibers in the center of the image markedly attenuated the loss of desmin. Bar, 25 µM.\n\nFigure 4: Figure 4. Trim32 promotes disassembly and destruction of phosphorylated desmin filaments. (A) Desmin filaments are phosphorylated during fasting. Top: the pellet from atrophying muscle expressing shTrim32 was analyzed by isoelectric focusing 2D gel electrophoresis and Coomassie blue staining. Four spots were observed at ∼53 kD and were identified by mass spectrometry as vimentin and desmin phosphorylated at serines 28, 32, and 68. Bottom: the three phosphorylated serine residues are located in desmin’s head domain. (B) Trim32 promotes disassembly and destruction of phosphorylated desmin filaments during fasting. Left: desmin filaments were isolated from normal and atrophying muscles expressing shLacz or shTrim32, and analyzed in parallel to the soluble fraction by SDS-PAGE and immunoblotting. Phosphorylated desmin was detected with phospho-serine antibody. The AKT blot serves as a loading control. Right: densitometric measurement of blots which were stained for phospho-serine. *, P < 0.05 shTrim32 vs. fed control; #, P < 0.005 shTrim32 vs. shLacz in fasting; n = 13. (C) During fasting, desmin accumulates as a phosphorylated species in the cytosol of muscles deficient in active Trim32. Desmin was immunoprecipitated from the soluble fraction of muscles expressing shLacz or dominant-negative to Trim32 (Trim32-DN) from fed or fasted mice. Precipitates were analyzed by immunoblotting using anti-desmin and phospho-serine. (D) Trim32 ubiquitylates desmin during fasting in vivo. Desmin filaments, which were purified from normal or atrophying muscles expressing shLacz or Trim32-DN, were analyzed in parallel to the soluble fraction by Western blot analysis using a desmin antibody. (E) Phosphorylation of desmin filaments facilitates their ubiquitylation by Trim32. Isolated desmin filaments from normal (lanes 2 and 3) and atrophying muscles expressing shLacz (lanes 4 and 5) or Trim32-DN (lanes 6–11) were treated with protein phosphatase 1 (PP1; lanes 9–11) or left untreated (lanes 6–8) and then subjected to ubiquitylation by pure Trim32 and UbcH5 using 6His-tagged ubiquitin. The 6His-tagged ubiquitin conjugates were purified with a Ni column and analyzed by SDS-PAGE and immunoblotting using anti-desmin. The band above the dashed line, which is also marked with an asterisk, is nonspecific.\n\nFigure 5: Figure 5. Depolymerization of desmin filaments promotes the loss of thin filaments during fasting. To test if disassembly of desmin filaments influences the stability of thin filaments, TA muscles were co-electroporated with Trim32-DN and either shLacz or a dominant-negative mutant of desmin (Desmin-DN) to induce filament disassembly. 4 d later, animals were deprived of food for 2 d. (A) Desmin-DN enhances disassembly of desmin filaments during fasting in muscles expressing Trim32-DN. Isolated desmin filaments and the soluble fraction from transfected muscles were analyzed by SDS-PAGE and immunoblotting. Representative bands were chosen based on similar atrophy rates in transfected muscles. Ponceau S staining is shown as a loading control for the pSER membrane. (B) The ability of Trim32-DN to protect against loss of muscle mass is not affected by the coexpression of desmin-DN. Mean weights of electroporated muscles are plotted as percent weight loss. n = 6. *, P < 0.005. (C) Depolymerization of desmin filaments by Desmin-DN during fasting reduces the sparing of thin filament proteins and MyHC by Trim32-DN. Left: myofibrils purified from atrophying muscles expressing shLacz alone (black bars), Trim32-DN together with shLacz (shaded bars), or Trim32-DN together with Desmin-DN (open bars) were analyzed by SDS-PAGE and Coomassie blue staining. The absolute content of each myofibrillar protein was obtained as described in Fig. 1 D. Data are expressed as percentages of fed control. n = 10, *, P < 0.05 vs. fed control; #, P < 0.05 vs. Trim32-DN/Lacz; §, P < 0.05 vs. Trim32-DN/Lacz. Right: equal fractions of myofibrils from different muscle samples were analyzed by immunoblotting using anti-actin and anti-MyHC. Ponceau S staining is shown as a loading control for each membrane. (D) Electroporation of desmin-DN into normal muscle to promote desmin disassembly does not trigger destruction of thin filaments. Myofibrils from normal muscles expressing desmin-DN were analyzed by SDS-PAGE and Coomassie blue staining, and the absolute content of each protein was calculated as in Fig. 1 D. Data are presented as percentage of control (expressing shLacz). n = 6. (E) During fasting, loss of desmin precedes degradation of myofibrillar proteins and Z-bands. Time course of the loss of desmin and myofibrillar proteins was analyzed by immunoblotting of equal amounts of myofibrils from TA muscles of fed mice and ones deprived of food for 1 or 2 d. Representative bands were chosen based on similar atrophy rates. Ponceau S staining is shown as a loading control."
      }
    ]
  },
  {
    "id": "PMC3517545_multi",
    "image": [
      "images/PMC3517545-f1.png",
      "images/PMC3517545-f2.png",
      "images/PMC3517545-f3.png",
      "images/PMC3517545-f4.png",
      "images/PMC3517545-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mammalian Alpha Arrestins Link Activated Seven Transmembrane Receptors to Nedd4 Family E3 Ubiquitin Ligases and Interact with Beta Arrestins\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Vasopressin receptor 2 HA-V2R-V5-stably transfected HEK293T cells were transiently transfected with expression constructs of alpha arrestins with C-terminal fusions of fluorescent protein mCherry. Unstimulated or 1 uM arginine vasopressin (AVP)-stimulated (15 m) cells were fixed, and epifluorescence images were captured using an AxioVision confocal microscope.\n\nFigure 2: Figure 2. (A) Subcellular colocalization of alpha-arrestin-mCherry in receptor HA-b2AR permanent cell lines. HEK-293T cells stably expressing HA-b2AR were transiently cotransfected with ARRDC3-mCherry construct. 24 h after transfection, cells were serum-starved for 2 h, treated or not with 1 uM isoproterenol (Iso) ligand for 30 m, and then washed, and fixed and permeabilized. HA-b2AR was stained with rabbit anti-HA antibodies followed by incubation with Alexa Fluor 488-conjugated goat anti-rabbit secondary antibody. Epifluorescence images were captured using AxioVision or Zeiss 510 META confocal microscope (receptor, green; aArr, red). (B) Co-immunoprecipitation of aArr ARRDC3 with b2AR, clathrin and Hrs. HEK-293T cells were transiently cotransfected with HA-b2AR-V5 plus either empty vector, pBSR-ARRDC3-GFP, or pBSR-ARRDC3 PY motif mutant construct respectively. After 24 h incubation, cells were serum-starved for 2 h and treated or not with 1 uM Iso for 30 m. The cells were lysed, and lysates were immunoprecipitated (IP) and analyzed by western blot (WB). (C) Co-immunoprecipitation of aArr ARRDC4 with V2R, clathrin, and Hrs. HEK-293T cells were transiently cotransfected with HA-V2R-V5 plus either empty vector, pcDNA3-ARRDC4-Flag, or pcDNA3-ARRDC4 PY motif mutant construct respectively. After 24 h incubation, cells were serum-starved for 2 h and treated or not with 1 uM AVP for 30 m. The cells were lysed, the lysates were immunoprecipitated (IP), and analyzed as above. (D, E) Histograms of B and C from three independent experiments including the mean (+/− S.D.) and p-values calculated by paired, two-tailed t-tests on signal from untreated and ligand-treated samples versus their respective vector control are denoted by thin lines and treated vs. untreated samples are denoted by bold lines (***, p<0.001; **, p<0.01; *p<0.05). (F) Subcellular colocalization of alpha-arrestin-mCherry with early (Rab5) and late (Rab7) endosomal markers in HA-V2R-V5 permanent cells. HA-V2R-V5 permanent cells were transiently co-transfected with ARRDC3- or ARRDC4-mCherry construct with Rab5- or Rab7-GFP construct. After 24 h, transfected cells were serum-starved, treated or not with 1 uM AVP for 30 m, and fixed with 4% paraformaldehyde. Epifluorescence images were captured using AxioVision confocal microscope (aArr, red; Rab, green).\n\nFigure 3: Figure 3. (A) HEK-293T cells were transiently cotransfected with HA-b2AR-V5 plus pBSR-ARRDC3-Flag, or HA-V2R-V5 plus pcDNA3-ARRDC4-Flag respectively. After 24 h incubation, cells were serum-starved and treated with 1 uM Iso or AVP for 1, 5, 15, 30, and 60 m. The cells were lysed, and lysates were immunoprecipitated (IP) and analyzed by western blot (WB). Note ARRDC4-Flag protein appears as two bands; we believe this is also the case for ARRDC4-mCherry (Fig. 2C), but that is less evident due to the large size of the fusion protein. The basis of this is not yet determined. (B, C) The histogram of A with mean (+/− S.D.) and p-values calculated by comparing levels of ligand-treated samples with respective vector controls (paired, two-tailed t-tests from three independent experiments; ***, p<0.001; **, p<0.01; *p<0.05).\n\nFigure 4: Figure 4. (A) Interactions of PY motif-containing alpha arrestin tails and WW region fragments demonstrated by yeast two-hybrid analysis. Bait plasmid (pDEST32-ARRDC1 or -ARRDC3) which contain two sets of PY motifs and prey plasmid (pDEST22-ITCH, -WWP2, -SAV1, -PLEKHA5, -Nedd4L, or -MAGI-2) which contain 1–4 sets of WW domains were transformed into competent yeast strain MaV203. pEXP32/Krev1 plus pEXP22/RalGDS-wt was included as strong positive control, pEXP32/Krev1 plus pEXP22/RALGDS-m1 weak positive control, pEXP32/Krev1 plus pEXP22/RALGDS-m2 and empty bait vector pDEST32 plus empty prey vector pDEST22 negative controls. Positive clones growing on SD/-Trp/-Leu/-His/-Ura plates are selected and the activity of lacZ reporter gene is examined with colony-lift filter assay by X-gal. (B) Subcellular colocalization of alpha-arrestin-mCherry and Nedd4 in HA-b2AR permanent cell lines. HA-b2AR permanent cells were transiently co-transfected with ARRDC3 -mCherry and pBJ-Nedd4-myc constructs. After 24 h, transfected cells were serum-starved, treated with 1 uM Iso for 30 m, and fixed. Nedd4 was stained with mouse monoclonal anti-myc antibody followed by incubation with Alexa Fluor 488-conjugated goat anti-mouse second antibody. Confocal epifluorescence images were obtained (aArr, red; Nedd4, green). (C) Co-immunoprecipitation of alpha arestin ARRDC3 and Nedd4 family E3 ubiquitin ligases with overexpressed b2AR. Empty vector, pBSR-ARRDC3-Flag, or pBSR-ARRDC3-Flag PY motif mutant construct was cotransfected respectively with pcDNA3-HA-b2AR-V5. After 24 h incubation, cells were serum-starved and treated or not with 1 uM Iso for 5 m. The transfected cells were lysed, lysates were immunoprecipitated (IP), and analyzed by western blot (WB). (D) Co-immunoprecipitation of aArr ARRDC4 and Nedd4 family E3 ubiquitin ligases with overexpressed V2R, unstimulated or 5 m post 1 uM AVP stimulation. (E, F) Histograms of C and D from three different experiments; p-values were calculated by comparing levels of ligand-treated or non-treated samples with their respective vector control (p value levels and thin/bold lines used as in Fig. 2).\n\nFigure 5: Figure 5. (A) Ubiquitination effect of alpha arrestins on GPCR. Empty vector, pBSR-ARRDC3-Flag, or pBSR-ARRDC3-Flag PY motif mutant construct was cotransfected with pcDNA3-HA-b2AR-V5. After 24 h incubation, cells were serum-starved for 2 h and treated or not with 1 uM Iso for 30 m. The transfected cells were lysed, and lysates were immunoprecipitated (IP) and analyzed by western blot (WB). The same experiment was performed with ARRDC4 and V2R (1 uM AVP treatment for 30 m). (B) The mean values (+/− S.D.) of three independent experiments are included in the histogram (p value levels and lines used as in Fig. 2). (C.) Effects of siRNA-mediated ADDRC3 knockdown on b2AR ubiquitination and ITCH expression. Scrambled siRNA, and ARRDC3 siRNAs #1 and #2 were cotransfected with HA-b2AR-V5 construct. After 48 h incubation, cells were serum-starved for 2 h and treated with 1 uM Isoproterenol Iso for 30 m. The transfected cells were lysed, and the lysates were immunoprecipitated (IP) and analyzed by western blot (WB). (D) Histograms of mean (+/− S.D.) and p-values calculated from three different experiments by paired, two-tailed t-tests comparing ligand-stimulated cells transfected with ARRDC3 siRNA versus with control siRNA (p value levels used as in Fig. 2)."
      }
    ]
  },
  {
    "id": "PMC3517545_multi_2",
    "image": [
      "images/PMC3517545-f6.png",
      "images/PMC3517545-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Mammalian Alpha Arrestins Link Activated Seven Transmembrane Receptors to Nedd4 Family E3 Ubiquitin Ligases and Interact with Beta Arrestins\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Subcellular colocalization of alpha and beta arrestins in HA-b2AR and HA-V2R-V5 permanent cell lines. HA-b2AR and HA-V2R-V5 permanent cells were transiently co-transfected with either ARRDC3- or ARRDC4-mCherry construct plus pArrb2-EGFP. After 24 h, transfected cells were serum-starved for 2 h, treated or not with 1 uM ligand for 30 m, and then washed and fixed with 4% paraformaldehyde. Fluorescent confocal images were captured (aArr, red; ARRB2, green). (B) Subcellular colocalization of mutant alpha- and beta-arrestin in ligand treated V2R permanent cell line. HA-V2R-V5 permanent cells were transiently co-transfected with either ARRDC3- or ARRDC4-mCherry PY mutant construct plus pArrb2-EGFP. After 24 h, transfected cells were serum-starved for 2 h, treated with 1 uM AMP for 30 m, and then washed and fixed. Fluorescent confocal images were captured (aArr, red; ARRB2, green). (C) Co-immunoprecipitation of wild type aArrs and bArrs. HEK-293Tcells were co-transfected either with empty vector, or pBSR-ARRDC3-Flag, or pcDNA3-ARRDC4-Flag plus pcDNA3-HA-b2AR or pcDND3-HA-V2R-V5. After 24 h incubation, cells were serum-starved and treated or not with 1 uM ligand for 5 m. The cells were lysed, and lysates were immunoprecipitated and analyzed by western blot. (D) Co-immunoprecipitation of wild type or mutant aArrs and bArrs. HEK-293T cells were co-transfected either with empty vector, pBSR-ARRDC3-Flag, or pBSR-ARRDC3-Flag PY mutant, plus pcDNA3-HA-b2AR. Protein levels of ARRB1/2 and aArrs were detected by western blot. (E) The same concept as in D was done with ARRDC4 plus HA-V2R-V5. P-values were calculated by paired, two-tailed t-tests (p values and thin/bold lines used as in Fig. 2).\n\nFigure 7: Figure 7. In the case of 7TMRs, receptor activation results in heterotrimeric G protein signaling through second messenger systems. This is instantly followed by receptor phosphorylation by GRK, which results in beta arrestin binding (arresting further G protein binding/signaling). Our findings suggest that alpha and beta arrestins heteroassociate and have coordinated functions. Among the biological functions that could be regulated by integrated alpha/beta arrestin functions are endocytic trafficking of cell surface cargoes (recycling or lysosomal degradation), kinase signaling (e.g., metabolism, cell growth, survival/apoptosis) and cytoskeletal dynamics. Alpha and beta arrestins could have a yin yang relationship with both antagonistic (e.g., inactivating and activating, respectively) and cooperative properties depending on context. We envision that arrestins are dynamic adaptors that can integrate internal and external information to mediate programmed ends (i.e., programs created through evolutionary processes). This is largely achieved through reversible posttranslational modifications, such as phosphorylation (not shown) and ubiqutination, and their effects on protein-protein interactions."
      }
    ]
  },
  {
    "id": "PMC3538638_multi",
    "image": [
      "images/PMC3538638-f1.png",
      "images/PMC3538638-f2.png",
      "images/PMC3538638-f3.png",
      "images/PMC3538638-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"On the Molecular Basis of D-Bifunctional Protein Deficiency Type III\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The first line represents Low molecular weight protein standard (Bio-Rad) and lines 2–7 protein samples purified by Ni-NTA and Superdex 200 gel filtration columns as follows: 2) wild type HsDH, 3) T15A variant, 4) N158D variant, 5) E232K variant, 6) R248C variant and 7) W249G variant. The molecular masses of all the recombinant protein monomers (∼36 kDa) correspond to the monomer mass (36.14 kDa) estimated from the aa sequence of the wild type HsDH [29].\n\nFigure 2: Figure 2. The dilution series were done on YPD (0.2% glucose)- oleic acid (0.125%) plates and the BY4741 Δfox2 cells were grown at +30°C for one week indicated by: (1) BY4741 Δfox2+ pYE352::HsMFE-2, (2) BY4741 Δfox2+ pYE352::ScMFE-2, (3) BY4741 Δfox2 strain, (4) BY4741 Δfox2+ pYE352::CTA1, (5) BY4741 Δfox2+ pYE352::HsMFE-2(T15A), (6) BY4741 Δfox2+ pYE352::HsMFE-2(N158D), (7) BY4741 Δfox2+ pYE352::HsMFE-2(E232K), (8) BY4741 Δfox2+ pYE352::HsMFE-2(R248C), (9) BY4741 Δfox2+ pYE352::HsMFE-2(W249G). When the yeast is able to utilize the oleic acid as a sole source of carbon, there will appear a clear zone around (samples 1, 2, 5, 6, 7, 8 & 9), but if the functional fox2 gene is missing the environment remains opaque (samples 3 & 4).\n\nFigure 3: Figure 3. The two dehydrogenase monomers in the middle of the figure are colored in green and blue, amino acids T15, N158, E232, R248 and W249 are shaded grey and shown in stick presentations, NAD+ are colored in yellow and shown also in stick presentation. The rectangles indicate parts of the structure that are represented in larger details in small figures. The figures were done using the program PyMol (Schrödinger) and human 3R-hydroxyacyl-CoA dehydrogenase structure (PDB ID 1ZBQ; [7]).\n\nFigure 4: Figure 4. The two dehydrogenase monomers are shown as surface presentation; monomer A is colored in green and monomer B in blue. For both monomers the larger (upper) part in panel A is the Rossmann fold core domain and the smaller (lower) part is the C-terminal subdomain. Variation sites are color coded with the fluctuation analysis as follows: N158D (green), E232K (violet), R248C (yellow) and W249G (light brown). Residues found essential for discussion on the D-BP deficiency mechanism are colored as follows: amino acids belonging to catalytic triad (S151, T164 and K168) in magenta, amino acids locating at the tip of the cavity leading to the active site (I180, Y156 [36] and I288) in purple blue and amino acids important for the substrate binding (E250 and R251) in orange [36]. NAD+ is colored in yellow and presented in stick presentation. (A) The front side of both monomers. The groove for the substrate binding begins from the crossing area of C-terminal subdomains and continues to the cavity leading to the active site. Four different areas in which the variations cause structural fluctuation compared to native protein are marked with ellipses and linked to the fluctuation figures. In the fluctuation figures each rectangle shows the evolution of the distance (in nm; y-axis) of a specific hydrogen bond (as indicated) for 50 ns (x-axis). On each four fluctuation figures the leftmost rectangle (in black) is the native protein, while the other rectangles show the distance evolution of the indicated hydrogen bond in protein variants as follows: N158D (top left and bottom right in green), W249G (top left and right in light brown) and E232K (bottom left in violet). Representative surface-exposed hydrogen bonds were chosen for the figure; a complete list of hydrogen bonds, which were found fluctuating, is presented in table 2. (B) The substrate binding groove and cavity from above. The figures were done using the program PyMol (Schrödinger) and human 3R-hydroxyacyl-CoA dehydrogenase structure (PDB ID 1ZBQ)."
      }
    ]
  },
  {
    "id": "PMC3551712_multi",
    "image": [
      "images/PMC3551712-f1.png",
      "images/PMC3551712-f2.png",
      "images/PMC3551712-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Specific combination of compound heterozygous mutations in 17β-hydroxysteroid dehydrogenase type 4 (HSD17B4) defines a new subtype of D-bifunctional protein deficiency\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Retinal photograph of Patient 1 at 15½ years old identified retinitis pigmentosa. Widespread peripheral retinal atrophy was seen with relative sparing of the central macula. Clinically this corresponds to involvement of peripheral rods and relative sparing of cones.\n\nFigure 2: Figure 2. MRI of the brain. MRI was performed on Patient 1 at 12 years of age. T1W1 sagittal image demonstrates prominent cerebellar atrophy involving superior and middle cerebellar folia. Axial images (not shown) revealed normal subcortical and cerebellar white matter. MR spectroscopy was normal (not shown). Repeat MRI imaging at 16 years old was unchanged (not shown). MRI of the brain (Patient 2) showed a similar pattern but milder cerebellar atrophy (not shown).\n\nFigure 3: Figure 3. Sanger sequencing and segregation. (A) Pedigree of family with DBP deficiency. X=variant; N=normal. (B) Sanger sequencing validation of HSD17B4 variants identified by exome sequencing. Genomic DNA was amplified for sequencing with primers flanking exon 2 and 18 (see text for primer sequences). Asterisks indicate heterozygous mutations. Red X = c.101C>T (p. Ala34Val) at chr5:118792052. Blue X = c.1547T>C (p. Ile516Thr) at chr5:118860954."
      }
    ]
  },
  {
    "id": "PMC3567975_multi",
    "image": [
      "images/PMC3567975-f1.png",
      "images/PMC3567975-f2.png",
      "images/PMC3567975-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"MRI characterisation of adult onset alpha-methylacyl-coA racemase deficiency diagnosed by exome sequencing\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Chronic and acute brain MRI findings in α-methylacyl-coA racemace deficiency. A) Representative axial T2-images showing different brainstem levels and the thalami in a caudocranial direction. There is evidence of chronic degeneration of both cerebellar efferent and afferent pathways. A1) No evidence of inferior olivary lesion in the medulla oblongata. A2) High signal of the dentate nucleus (arrow). This finding was preceded by loss of T2 hypointensity. High signal and atrophy of the pons is also apparent at this level. A3) High signal in the superior cerebellar peduncle (SCP; arrow). In addition, there is degeneration of the cerebellar afferents with pontine atrophy and hyperintensity corresponding to the transverse pontine fibers. A4) High signal corresponding to the decussation of SCP. A5) High signal corresponding to the dentatothalamic tract (arrow) at the level of the inferior colliculus in the midbrain. A6) Probable loss of T2 hypointensity in the red nucleus (arrow) on 3 Tesla MRI and high signal in the superior colliculus. A7) High signal in the posterior commissure (arrow). A8) High signal in the thalami. B) Acute lesion two weeks into an encephalopatic episode with aphasia, right upper limb paresis, central facial palsy and reduced consciousness in patient B. Left frontal high T2-signal cortical lesion (B1), showing a mixed diffusion pattern with areas of both high and low apparent diffusion coefficient (ADC) (B2-B3).\n\nFigure 2: Figure 2. Ophthalmic features in patient B. A – C) Fundus images of the right eye showing pronounced asteroid hyalosis (A). Pigment epithelial atrophy and moderate pigmentary retinopathy are present in the mid-periphery. The macula, optic disc and retinal vessles are normal (B). Areas resembling pigmented and nonpigmentet small congenital hypertrophy of the retinal pigment epithelium were present (C). D) Optical coherence tomography showing a normal macula (top) but peripheral retinal pigment layer degeneration and disturbances in the photoreceptor layer (bottom).\n\nFigure 3: Figure 3. Goldmann perimetry in patient B. Constricted visual fields were found. In the right eye a conserved central horizontal field of 30 degrees nasally and 40 degrees temporally are seen. In the left eye the conserved visual field is 10 degrees nasally and 40 degrees temporally."
      }
    ]
  },
  {
    "id": "PMC3573110_multi",
    "image": [
      "images/PMC3573110-f1.png",
      "images/PMC3573110-f2.png",
      "images/PMC3573110-f3.png",
      "images/PMC3573110-f4.png",
      "images/PMC3573110-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Tysnd1 Deficiency in Mice Interferes with the Peroxisomal Localization of PTS2 Enzymes, Causing Lipid Metabolic Abnormalities and Male Infertility\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A. Map of Tysnd1 −/− targeting constructs. P1, P2 and P3 indicate primers used for genotyping by PCR. B. Identification of genotyping by PCR. Wild type and Tysnd1 −/− genotype were identified by 237 bp and 339 bp PCR products, respectively. C. Relative expression level of Tysnd1 mRNA measured by quantitative real-time PCR in liver. D. Tysnd1 protein was absent in the liver of Tysnd1 −/− mice as shown by Western blotting using anti-Tysnd1 antibody. E. The expression of known Tysnd1 substrates in the liver homogenate was detected by Western blotting using anti-Acox1, -ScpX/Scp2, -Hsd17b4 and -Acaa1 antibodies. Processed forms of Tysnd1 substrates were not detected in Tysnd1 −/− mice. Arrows indicate the processed form of each enzyme. F. Peroxisomal β-oxidation activity was measured by [1-C14]lignoceric acids in 15 weeks old control diet-fed (CE2, Clea Japan) male mice liver homogenate. ***p<0.001. Each error bar represents the mean ± SE in n = 3.\n\nFigure 2: Figure 2. A. Semi-thin (8–10 micron) testes sections of 20 weeks old Tysnd1 +/+ and Tysnd1−/− mice were stained with hematoxylin-eosin. Abnormal, round sperm heads are visible in the seminiferous tubules of Tysnd1 −/− mice. B. Abnormal morphology of Tysnd1 −/− sperms. Epididymal sperms of 15 weeks-old Tysnd1 +/+ and Tysnd1 −/− mice were stained with mitochondrial stains (MitoFluor Red) and nuclear staining (DAPI). Scale bar = 20 µm. C. Percentage of sperms showing normal morphology in Tysnd1 +/+ (n = 4), Tysnd1 +/− (n = 4) and Tysnd1 −/− (n = 5) mice. Each error bar represents the mean ± SE. D. Anti-MN9 antibody immunostaining and Hoechst nuclear staining of epididymal sperms isolated from a 20 weeks old Tysnd1 −/− mouse (red: acrosome and blue: nucleus). Arrow heads and arrows indicate abnormal round-headed sperms and normal sperms, respectively. Scale bar = 5 µm. E. Acrosomes of a semi-thin testis section from a 10 weeks old Tysnd1 −/− and a heterozygous control mouse were stained with PNA-FITC (green) and Hoechst nuclear stain (blue). F. EM image of a Tysnd1 −/− caudal epididymal sperm. The round-headed sperm lacks the acrosome and shows an abnormal mitochondrial sheath (M) around the nucleus (N). Scale bar = 1 µm. G. EM image showing normal spermatogenesis in Tysnd1 +/− male mice. S7: step 7 round spermatid; S16: step 16 elongated spermatid. Acrosomes (A) are normally formed. Scale bar = 2 µm. H. EM image of Tysnd1 −/− elongated spermatid. S16: step 16 spermatid. In some spermatids the acrosome (*) is detached from the nucleus (N). Scale bar = 2 µm.\n\nFigure 3: Figure 3. Plasmalogen levels of whole testes and epididymides of Tysnd1 +/+ (white bars) and Tysnd1−/− (black bars) mice were measured by LC/ESI-MS/MS. Each error bar represents the mean ± SE in n = 5. * p<0.05, **p<0.01 and *** p<0.001.\n\nFigure 4: Figure 4. A. Livers after 13 days of phytol feeding. Left: enlarged, beige-coloured liver of phytol-fed Tysnd1 −/− mouse. Right: liver of phytol-fed Tysnd1 +/+ mouse. B. Hematoxylin-eosin stained semi-thin liver sections. Lipid droplets are indicated by yellow arrow heads. Green arrow heads indicate giant cells. C. Blood serum-derived phytanic acid measurement by GC/MS normalized for C16∶0 (hexadecanoic acid) content. Each error bar represents the mean ± SE in n = 4–9. ***p<0.001. D. Measurement of blood serum C24∶0 (tetracosanoic acid), C25∶0 (pentacosanoic acid) and C26∶0 (hexacosanoic acid) VLCFAs by GC/MS normalized by C22∶0 (docosanoic acid) content. Each error bars: mean ± SE in n = 4–9. ***p<0.001. E. Measurement of liver peroxisomal β-oxidation activity with or without orally administered 0.5% phytol in carboxyl methyl cellulose (CMC). Each error bars: mean ± SE in n = 3–6. NS: not significant. ***p<0.001. F. EM image of liver sections with or without orally administered phytol in CMC. The blue and purple arrow heads indicate peroxisomes and autophagosomes, respectively.Bar: 2 µm. G. Numbers of peroxisomes and autophagosomes counted within same field areas of EM images. Error bars: mean ± SE in n = 5–8. ***p<0.001.\n\nFigure 5: Figure 5. A. COS7 cells were transiently co-transfected with Agps-V5 and Tysnd1 expression plasmids. With increasing amounts of Tysnd1 unprocessed Agps-V5 decreased (arrow). Processed Agps-V5 is indicated by an arrowhead B. Agps processing by Tysnd1 is specific and was affected by MG132 proteasome inhibitor. C. Western blot of testes extract using anti-Agps antibody shows unprocessed (arrow) and processed (arrowhead) forms of Agps. D. COS7 cells were transiently co-transfected with Phyh-V5 and Tysnd1 expression plasmids. With increasing amounts of Tysnd1, unprocessed Phyh-V5 decreased (arrow) and processed Phyh-V5 increased (arrowhead). E. Western blot of liver extract using anti-Phyh antibody shows unprocessed (arrow) and processed (arrowhead) forms of Phyh."
      }
    ]
  },
  {
    "id": "PMC3573110_multi_2",
    "image": [
      "images/PMC3573110-f6.png",
      "images/PMC3573110-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Tysnd1 Deficiency in Mice Interferes with the Peroxisomal Localization of PTS2 Enzymes, Causing Lipid Metabolic Abnormalities and Male Infertility\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Confocal laser-scanning microscopy of Tysnd1 −/− and Tysnd1+/+ primary hepatocytes co-transfected with Tysnd1 GFP-substrate constructs (green) and peroxisomal marker DsRed2-Peroxi (red). Small boxes indicate image sections that were magnified 1.5 times and shown in large boxes. A. Acaa1-GFP (PTS2). B. Phyh-GFP (PTS2). C. Agps-GFP (PTS2). D. GFP-Acox1 (PTS1). E. GFP-Hsd17b4 (PTS1). F. GFP-ScpX (PTS1). G. Western blot of fractionated liver protein extracts of Tysnd1 −/− and wild-type. I: input (post-nuclear fraction), C: cytosol-rich fraction, P: peroxisome-rich fraction. Arrow: unprocessed forms of Tysnd1 substrates, A: Arrowhead: processed form of Tysnd1 substrates. Pex5 and Pex7 are the PTS1 and PTS2 receptors, respectively. Pmp70 is a peroxisomal membrane marker and Gapdh a marker for post-nuclear and cytosol-rich fractions.\n\nFigure 7: Figure 7. A. Unprocessed PTS2 protein is imported from the cytoplasm into the peroxisome by Pex7 in association with the long isoform of Pex5 (Pex5pL). Tysnd1 processes the imported protein after the PTS2 signal and Pex7 and Pex5pL are recycled to the cytoplasm. The PTS2-containing fragment is exported from the peroxisome to the cytoplasm. Subsequent Pex5 and Pex7 docking components Pex13 and Pex14 are displayed as gray circles, but not individually labelled for reasons of simplicity. B. Tysnd1-deficient mouse peroxisome. Unprocessed PTS2-containing proteins remain bound as Pex7-Pex5pL cargo complex. Saturation of Pex7 and Pex5pL transport with relative shortage of free Pex5pL and Pex7 causes partial peroxisomal location appearance and accumulation of peroxisomal proteins outside the peroxisome."
      }
    ]
  },
  {
    "id": "PMC3578850_multi",
    "image": [
      "images/PMC3578850-f1.png",
      "images/PMC3578850-f2.png",
      "images/PMC3578850-f3.png",
      "images/PMC3578850-f4.png",
      "images/PMC3578850-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"ABCD2 Is a Direct Target of β-Catenin and TCF-4: Implications for X-Linked Adrenoleukodystrophy Therapy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic representation of the human ABCD2 promoter showing the two putative LEF-1/TCF binding sites identified with Genomatix software (MatInspector™). The two putative TCF binding sites (TBE1 and TBE2) are located at nucleotide positions −324 to −318 and −299 to −293 relative to the ATG translational start site in the upstream sequence of ABCD2 promoter. (B) Each reporter construct was transfected into HepG2 cells using Fugene6 (upper panel), whereas these constructs were electroporated into fibroblast cells from an X-ALD patient with a microporator (lower panel). Thirty-six hours after transfection, cells were harvested, and luciferase activities were determined and normalized by Renilla luciferase activity. Data represent the mean (±SEM) of triplicate experiments and each experiment was repeated three times. *p<0.05; **p<0.01; ns, not significant.\n\nFigure 2: Figure 2. (A) HepG2 cells were cotransfected with ABCD2 promoter reporter (800-Luc) plasmids together with the indicated expression plasmids. At 36 h after transfection, cells were harvested, and luciferase activities were determined. The amount of DNA in each transfection was kept constant by adding an appropriate amount of pcDNA3 empty vector. (B) HepG2 cells were transfected with either scrambled or β-catenin siRNA and were then further transfected with 800-Luc 24 h later. Luciferase activity was determined 48 h later (left panel). The efficacy of silencing was verified by real-time PCR (right panel). Data represent the mean (± SEM) of triplicate experiments and each experiment was repeated three times. *p<0.05.\n\nFigure 3: Figure 3. (A) HepG2 cells were cotransfected with the indicated expression plasmids along with either wild-type (WT) 800-Luc reporter plasmid containing wild-type (WT) sequences or double mutant (Dm) 800-Luc reporter plasmid containing mutations in the two TBE sites of the ABCD2 promoter. Mutated sequences are underlined (lower panel). At 36 h after transfection, cells were harvested, and luciferase activities were determined. The amount of DNA in each transfection was kept constant by adding an appropriate amount of pcDNA3 empty vector. Data represent the mean (± SEM) of triplicate experiments. (B) A ChIP assay was performed by immunoprecipitation of DNA/protein complexes from HepG2 cells with an anti-β-catenin antibody. The immunoprecipitated DNA was amplified with primers specific for the ABCD2 promoter. Purified rabbit IgG (IgG) was used as a negative control. Input DNA (before immunoprecipitation) was amplified as a positive control for the PCR. The amplified DNA was analyzed by agarose gel electrophoresis.\n\nFigure 4: Figure 4. HepG2 cells were cotransfected with Flag-tagged constitutively active β-catenin (Flag-catenin 4A) and Myc-tagged TCF-4 expression plasmids. (A) At 48 h after transfection, mRNA was isolated from transfected cells. The levels of ABCD1 and ABCD2 mRNA were measured by real-time PCR and were normalized to GAPDH expression (upper panel). Data represent the mean (± SEM) of triplicate experiments. Total cell lysates harvested from transfected cells were immunoblotted with the indicated antibodies (lower panel). Protein expression of β-actin was used as a loading control. **p<0.001; ns, not significant; control vector transfected cells versus β-catenin and TCF-4 transfected cells. (B) HepG2 cells were transfected with either scrambled or β-catenin siRNA. At 3 days after transfection, mRNA was isolated from transfected cells. The levels of ABCD1 and ABCD2 mRNA were measured by real-time PCR and normalized to GAPDH expression (upper panel). *p<0.05; ns, not significant; scrambled transfected cells versus β-catenin siRNA transfected cells. Efficacy of silencing was verified by western blotting with anti-β-catenin antibody (lower panel). Protein expression of β-actin was used as a loading control.\n\nFigure 5: Figure 5. Primary fibroblasts isolated from an X-ALD patient were electroporated with either GFP or ABCD2-GFP expressing plasmid using a microporator. (A) At 48 h after electroporation, cells were fixed and incubated with anti-PMP70 antibody for 2 h. After washing with PBS, cells were incubated with Alexa Fluor 594-conjugated donkey anti-rabbit IgG for 1 h. Immunofluorescence staining was analyzed using a confocal microscopy system. Cells were counterstained with 4′,6-diamidino-2-phenylindole (DAPI) to label nuclei. (B) At 48 h after electroporation, mRNA was isolated from cells. The levels of ectopically expressed ABCD2 were measured by real-time PCR and normalized to GAPDH expression. Data represent the mean (± SEM) of triplicate experiments. (C) At 4 days after electroporation, cells were harvested and the levels of VLCFA were measured. The values are expressed as the ratio of C26∶0 to C22∶0. Data represent the mean (± SEM). *p<0.01; GFP-expressing cells versus ABCD2-GFP-expressing cells."
      }
    ]
  },
  {
    "id": "PMC3578850_multi_2",
    "image": [
      "images/PMC3578850-f6.png",
      "images/PMC3578850-f7.png",
      "images/PMC3578850-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"ABCD2 Is a Direct Target of β-Catenin and TCF-4: Implications for X-Linked Adrenoleukodystrophy Therapy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Primary fibroblasts isolated from an X-ALD patient were electroporated with Flag-tagged constitutively active β-catenin (4A active mutant) and Myc-tagged TCF-4 expression plasmids using a microporator. (A) At 48 h after electroporation, mRNA was isolated from cells. The levels of ABCD2 mRNA were measured by real-time PCR and normalized to GAPDH expression (upper panel). Data represent the mean (± SEM) of triplicate experiments. At 48 h after electroporation, total cell lysates harvested from transfected cells were immunoblotted with the indicated antibodies (lower panel). Protein expression of β-actin was used as a loading control. (B) Four days after electroporation, cells were harvested and the levels of VLCFA were measured. Values are expressed as the ratio of C26∶0 to C22∶0. Data represent the mean (± SEM). *p<0.001; GFP-expressing cells versus β-catenin and TCF-4-expressing cells.\n\nFigure 7: Figure 7. Primary fibroblast cells isolated from an X-ALD patient were transfected with either scrambled or β-catenin siRNA. (A) At 3 days after transfection, mRNA was isolated from transfected cells. The levels of ABCD2 mRNA were measured by real-time PCR and were normalized to GAPDH expression (upper panel). Data represent the mean (± SEM) of triplicate experiments. At 3 days after transfection, the efficacy of silencing was verified by western blotting with anti-β-catenin antibody (lower panel). Protein expression of β-actin was used as a loading control. (B) Four days after transfection, cells were harvested and the levels of VLCFA were measured. The values are expressed as the ratio of C26∶0 to C22∶0. Data represent the mean (± SEM). *p<0.001; scrambled transfected cells versus β-catenin siRNA-transfected cells.\n\nFigure 8: Figure 8. X-ALD fibroblast cells were transfected with either scrambled or ABCD2 siRNA. Two days after transfection, cells were electroporated with Flag-tagged constitutively active β-catenin (4A active mutant) and Myc-tagged TCF-4 expression plasmids using a microporator. (A) Two days after electroporation, mRNA was isolated from cells. The levels of ABCD2 mRNA were measured by real-time PCR and normalized to GAPDH expression. Data represent the mean (± SEM) of triplicate experiments. (B) Four days after electroporation, cells were harvested and the levels of VLCFA were measured. Values are expressed as the ratio of C26∶0 to C22∶0. Data represent the mean (± SEM). *p<0.05; **p<0.01; ns, not significant."
      }
    ]
  },
  {
    "id": "PMC3580430_multi",
    "image": [
      "images/PMC3580430-f1.png",
      "images/PMC3580430-f2.png",
      "images/PMC3580430-f3.png",
      "images/PMC3580430-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The gene expression profiles of induced pluripotent stem cells from individuals with childhood cerebral adrenoleukodystrophy are consistent with proposed mechanisms of pathogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Characterization of iPSCs from patient with CCALD. (A) Representative images of alkaline phosphatase (AP) staining and pluripotency protein biomarker immunostaining analysis of childhood cerebral adrenoleukodystrophy (CCALD) patient induced pluripotent stem cell (iPSCs) are presented. (B) Representative CCALD iPSCs were subject to in vitro differentiation (Materials and methods) and cell lineages derived from all three germ layers were identified by immunostaining, as depicted. Antibodies against Tuj1, αSMA and AFP were used to identify cells of ectodermal, mesodermal, and endodermal origin, respectively. (C) Histological analysis of teratomas derived from representative CCALD iPSC clones from two patients is provided. Evidence of cell lineages derived from all three germ layers is provided. C, Cartilage tissue; G, Glandular tissue; N, Neural rosettes; P, pigment neuroepithelium. Scale bar = 50 μm.\n\nFigure 2: Figure 2. The gene expression and DNA methylation profiles of fibroblasts and iPSCs. (A) A dendrogram generated based on the unsupervised hierarchical clustering analysis of gene expression data from childhood cerebral adrenoleukodystrophy (CCALD) patient and control fibroblasts and induced pluripotent stem cells (iPSCs) is provided. The analysis was based on data from 672 probe sets producing log2-tranformed gene expression scores with coefficient of variation (CV) > 0.25 and conducted using average linkage and Euclidean distance; (B) A dendrogram generated based on the unsupervised hierarchical clustering analysis of DNA methylation data from CCALD patient and control fibroblasts and iPSCs is provided. Data from 7,493 DNA methylation assays interrogating autosomal CpG loci with CV > 0.5 and the fifth largest and smallest β-values being > 0.6 and < 0.4, respectively, were used in this analysis in order to represent the most variable loci. Clustering was performed using average linkage and the Pearson dissimilarity distance.\n\nFigure 3: Figure 3. Comparison of saturated very long chain fatty acid (sVLCFA) and plasmalogen levels in patient and healthy control fibroblasts and iPSCs. (A) Relative sVLCFA levels in patient and healthy control fibroblasts grown in fibroblast media or iPSC media, as represented by the C26:0/C22:0 LPC (lysophosphatidylcholine) ratio; (B) Relative sVLCFA levels in patient and healthy control iPSC clones grown in induced pluripotent stem cell (iPSC) media, again represented by the C26:0/C22:0 LPC ratio; (C) Relative plasmalogen level in patient and healthy control fibroblasts grown in fibroblast media and iPSC media, as represented by the total phosphatidyl ethanolamine (PE) plasmalogen/C22:0 lysophosphatidylcholine (LPC) ratio; (D) Relative plasmalogen in patient and healthy control iPSC clones grown in iPSC media, again represented by the total PE plasmalogen/C22:0 LPC ratio.\n\nFigure 4: Figure 4. qRT-PCR confirmation of PEX11B gene expression in patient and healthy control iPSCs. Data from the analysis of PEX11B gene expression levels are provided. The error bars represent one standard deviation. The expression was lower in patients relative to control cells (two-tailed Student's t-test P-value < 0.5)."
      }
    ]
  },
  {
    "id": "PMC3583843_multi",
    "image": [
      "images/PMC3583843-f1.png",
      "images/PMC3583843-f2.png",
      "images/PMC3583843-f3.png",
      "images/PMC3583843-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Proteome of Human Liver Peroxisomes: Identification of Five New Peroxisomal Constituents by a Label-Free Quantitative Proteomics Survey\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomes were isolated by differential and Nycodenz density gradient centrifugation and subjected to triplicate LC/MS/MS analyses for protein identification. Subcellular distribution of 263 and 400 proteins according to identification numbers (A, C) and spectral counts (B, D) that were detected in the peroxisomal peak fraction 6 and in nine consecutive gradient fractions adjacent to the peroxisomal peak fraction, respectively.\n\nFigure 2: Figure 2. Protein profiles were established as an average of normalized peptide abundances and correlated to the mean peroxisomal profile by statistical analysis using the χ2-method. (A) Mean peroxisomal profile. (B-D) Profiles of peroxisomal 3,2-trans-enoyl-CoA isomerase and catalase as well as the mitochondrial O subunit of ATP synthase. (E, F) Profiles of ISOC1 and HSDL2 identified as new candidate proteins of human liver peroxisomes.\n\nFigure 3: Figure 3. Huh7 cells were transfected with plasmids for expression of DsRed fusion proteins of ISOC1, HSDL2, MDH1, LDHA and ADH1A as well as EGFP-SKL as peroxisomal marker. Images from the left to right: EGFP-SKL (green), candidate fusion protein (red), merge. Images were assembled from z-projections; the scale bar represents 20 µm.\n\nFigure 4: Figure 4. Nycodenz gradient fractions of human liver were subjected to SDS-PAGE followed by immunoblot analysis using antibodies against the peroxisomal candidate proteins HSDL2 and ISOC1 as well as catalase (peroxisomal marker) and the voltage-dependent anion channel VDAC (mitochondrial marker). In addition to its partial localization to peroxisomes, HSDL2 was found to localize to mitochondria."
      }
    ]
  },
  {
    "id": "PMC3599312_multi",
    "image": [
      "images/PMC3599312-f1.png",
      "images/PMC3599312-f2.png",
      "images/PMC3599312-f3.png",
      "images/PMC3599312-f4.png",
      "images/PMC3599312-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Age-dependent roles of peroxisomes in the hippocampus of a transgenic mouse model of Alzheimer’s disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pex14p protein levels and distribution in the hippocampus of WT and Tg mice. (a) Densitometric values of Pex14p WB, performed on hippocampal protein extracts of 3-, 6-, 9-, 12-, and 18-month-old WT and Tg mice. Data are expressed as mean ± SD. *P <0.05; **P <0.01; ***P <0.001. (b) Pex14p immunohistochemical localization in CA1 hippocampal field of 3-, 6-, 9-, and 18-month-old WT and Tg mice. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm.\n\nFigure 2: Figure 2. PMP70 protein levels and distribution in the hippocampus of WT and Tg mice. (a) Densitometric values of PMP70 WB, obtained analyzing the hippocampal protein extracts of 3-, 6-, 9-, 12-, and 18-month-old WT and Tg mice. Data are expressed as mean ± SD. *P <0.05; **P <0.01; ***P <0.001. (b) Immunohistochemical distribution of PMP70 in CA1 hippocampal field of 3-, 6-, 9-, and 18-month-old WT and Tg mice. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm. (c) PMP70 pre-embedding immunoelectron microscopy of 3-month-old CA1 pyramidal neurons of WT and Tg animals. In both genotypes positive peroxisomes (arrows) are observed and they appear more numerous in the cytoplasm of Tg neurons. N, neuronal nucleus; m, mitochondrion. Scale bars, 1 μm.\n\nFigure 3: Figure 3. GFAP protein levels and distribution in the hippocampus of WT and Tg mice. (a) GFAP immunohistochemical localization in CA1 hippocampal field of 9-, 12-, and 18-month-old WT and Tg mice. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm. (b) Densitometric analysis of GFAP WB performed on hippocampal protein extracts of 3-, 6-, 9-, 12-, and 18-month-old mice. Values are expressed as mean ± SD. **P < 0.01; ***P < 0.001. (c) Double immunofluorescence of PMP70 (green) in combination with GFAP (red) in the CA1 hippocampal field of 18-month-old WT and Tg brain. Several PMP70+/GFAP+ cells (yellow) are especially numerous in the pathological genotype. Scale bars, 25 μm.\n\nFigure 4: Figure 4. Peroxisomal fatty acid β-oxidation enzymes in the hippocampus of WT and Tg mice. (a, c) Densitometric values of AOX and THL WB performed on hippocampal protein extracts of 3-, 6-, 9-, 12-, and 18-month-old WT and Tg brains. Data are expressed as mean ± SD. *P <0.05; **P <0.01; ***P <0.001. (b) AOX immunolocalization in CA1 hippocampal field of 3-, 6-, and 18-month-old WT and Tg brains. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm.\n\nFigure 5: Figure 5. H2O2-scavenging enzymes in WT and Tg hippocampus. (a, c) Densitometric values of CAT and GPX1 WB performed on hippocampal protein extracts of 3-, 6-, 9-, 12-, and 18-month-old WT and Tg brains. Values are expressed as mean ± SD. *P <0.05; **P <0.01; ***P <0.001. (b, d) CAT and GPX1 immunolocalization in CA1 hippocampal field of 3-, 6-, 9- and 18-month-old WT and Tg brains. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm."
      }
    ]
  },
  {
    "id": "PMC3599312_multi_2",
    "image": [
      "images/PMC3599312-f6.png",
      "images/PMC3599312-f7.png",
      "images/PMC3599312-f8.png",
      "images/PMC3599312-f9.png",
      "images/PMC3599312-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Age-dependent roles of peroxisomes in the hippocampus of a transgenic mouse model of Alzheimer’s disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. SOD1 protein levels and distribution in WT and Tg hippocampus. (a) Densitometric values of SOD1 WB performed on hippocampal protein extracts of 3-, 6-, 9-, 12- and 18-month-old WT and Tg brains. Values are expressed as mean ± SD. *P <0.05; **P <0.01; ***P <0.001. (b) SOD1 immunolocalization in CA1 hippocampal field of 3-, 6-, 9-, 12- and 18-month-old WT and Tg brains. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm.\n\nFigure 7: Figure 7. SOD2 protein levels and distribution in WT and Tg hippocampus. (a) Densitometric values of SOD2 WB performed on hippocampal protein extracts of 3-, 6-, 9-, 12- and 18-month-old WT and Tg brains. Values are expressed as mean ± SD. **P <0.01; ***P <0.001. (b) SOD2 immunolocalization in CA1 hippocampal field of 3-, 6-, 9-, 12- and 18-month-old WT and Tg brains. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm. (c) Higher magnification showing SOD2 immunopositive glial cells around senile plaques in 18-month-old Tg hippocampus. Scale bar, 15 μm.\n\nFigure 8: Figure 8. Immunolocalization of oxidative stress markers at early and advanced AD stages. (a, b) Acrolein and 8-OH(d)G in CA1 hippocampal field of 3- and 18-month-old WT and Tg mice. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm.\n\nFigure 9: Figure 9. PPARα immunolocalization in 3-month-old WT and Tg mice. (a) PPARα immunohistochemistry in CA1 pyramidal cell layer shows a higher immunoreactivity in Tg hippocampus, than in its WT counterpart. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm. (b) Confocal image of triple immunofluorescence for PPARα (green) in combination with GFAP (red) and NeuN (blue) demonstrates the presence of PPARα-positive neurons and astrocytes. Note the brightness of green signal in the Tg section. Scale bars, 25 μm. (c) PPARα pre-embedding immunoelectron microscopy of CA1 pyramidal neurons shows the nuclear localization of the immunoreaction product, especially concentrated in the Tg nucleus. Arrows indicate the nuclear envelope. N, nucleus; n, nucleolus. Scale bars, 2 μm.\n\nFigure 10: Figure 10. PGC-1α immunohistochemistry in CA1 hippocampal field of 3, 6-, 9-, 12- and 18-month-old WT and Tg mice. Arrowheads, Aβ plaques. or, stratum oriens; pyr, stratum pyramidale; rad, stratum radiatum. Scale bars, 25 μm."
      }
    ]
  },
  {
    "id": "PMC3670168_multi",
    "image": [
      "images/PMC3670168-f1.png",
      "images/PMC3670168-f2.png",
      "images/PMC3670168-f3.png",
      "images/PMC3670168-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A method for measuring fatty acid oxidation in C. elegans\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic illustration of the fatty acid oxidation assay in live C. elegans. The radioactively labeled fatty acids are complexed to BSA in order to be soluble in water-based buffer. Worms ingest FA-BSA complexes and the labeled fatty acids are absorbed by intestinal cells. Once imported, the labeled fatty acids are activated to acyl-CoA esters, which are transported across the mitochondrial double membrane by the carnitine shuttle system. In the mitochondrial matrix, the labeled acyl-CoA esters are metabolized through β-oxidation, the citric acid cycle and the electron transport chain to ultimately produce tritiated water.\n\nFigure 2: Figure 2. Control experiments. (A) Specific activity of palmitic or oleic acid oxidiation in C. elegans wild type animals. (B) β-oxidation of palmitic acid in live and heat-killed worms. L4 worms were incubated with tritiated oleic acid complexed to BSA for one hour, and the amount of tritiated water generated by oxidation was determined, normalized to protein levels, and expressed relative to control levels. For the boiling experiments, worms were boiled in 5 mL S-basal for 15 min at 95°C. (C) β-oxidation of oleic acid in controls vs. azide-treated worms. Azide to 10mM was added to the samples just after addition of assay mix. Average ± SEM is shown; n indicates the number of determinations. Asterisks indicate statistical significance (***: p < 0.0001).\n\nFigure 3: Figure 3. β-oxidation of oleic acid increases during starvation. L4 worms were incubated with tritiated oleic acid complexed to BSA for one hour, and the amount of tritiated water generated by oxidation was determined, normalized to protein levels, and expressed relative to control levels. The starvation experiments were performed, when non-starved animals were L4 (see Experimental Section for details). Average ± SEM is shown; n indicates the number of determinations. Asterisks represent statistical significance (**: p < 0.01; ***: p ≤ 0.0001). Black asterisks indicate a significant difference from non-starved mutants.\n\nFigure 4: Figure 4. β-oxidation of oleic acid is increased in worms grown on HB101 compared with standard OP50 diet. N2 animals were grown on OP50 or HB101 for one generation. L4 animals were incubated with tritiated oleic acid complexed to BSA for one hour, and the amount of tritiated water generated by oxidation was determined, normalized to protein levels, and expressed relative to control levels. Average ± SEM is shown; n indicates the number of determinations. Asterisks represent statistical significance (**: p < 0.01)."
      }
    ]
  },
  {
    "id": "PMC3674738_multi",
    "image": [
      "images/PMC3674738-f1.png",
      "images/PMC3674738-f2.png",
      "images/PMC3674738-f3.png",
      "images/PMC3674738-f4.png",
      "images/PMC3674738-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Metabolic Causes of Epileptic Encephalopathy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Cobalamin transport and metabolism. Hydroxycobalamin (OH-Cbl) enters the cell bound to transcobalamin (TC), a binding protein. The hydroxycobalamin-transcobalamin complex is broken down inside the lysosome, and the enzyme cobalamin C (CblC) removes the hydroxyl group to generate free cobalamin (Cbl), which is synthesized via additional steps into methyl- and adenosyl-cobalamin.\n\nFigure 2: Figure 2. EEG of 4-day-old infant with MSUD shows comb-like rhythm over the right central (C4) area. (sensitivity 7 mcv/mm, HFF 70 Hz, time constant 0.5 sec, 8 sec epoch). Pearl [2].\n\nFigure 3: Figure 3. (a) EEG of 3-year-old female with SSADH deficiency. Note diffuse spike-wave paroxysm with lead-in over right hemisphere. (b) Same recording as top, showing left-sided spike-wave paroxysm. Pearl [2].\n\nFigure 4: Figure 4. 7-year-old boy diagnosed with Alpers' syndrome presented with encephalopathy, tonic-clonic seizures and myoclonic seizures. EEG shows high amplitude anterior poorly formed 2-3 Hertz sharp and slow activity. Pearl [2].\n\nFigure 5: Figure 5. EEG of term infant with glycine encephalopathy shows burst-suppression pattern. Pearl [2]."
      }
    ]
  },
  {
    "id": "PMC3676453_multi",
    "image": [
      "images/PMC3676453-f1.png",
      "images/PMC3676453-f2.png",
      "images/PMC3676453-f3.png",
      "images/PMC3676453-f4.png",
      "images/PMC3676453-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"E3 Ubiquitin Ligase E6AP Negatively Regulates Adipogenesis by Downregulating Proadipogenic Factor C/EBPalpha\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. 3T3L1 cells were transfected with E6AP (2.0 µg) and E6AP-C843A (2.0 µg). Post 48 h of transfection, cells were treated with MDI for next 8 days followed by Oil red O staining.\n\nFigure 2: Figure 2. (a,b) 3T3-L1 preadipocytes were transfected with increasing amounts of E6AP (0.5 µg–2.0 µg) and E6AP-C843A (0.5 µg–2.0 µg). Post 48 h transfection, WCEs were prepared and resolved on 10% SDS-PAGE followed by immunoblotting with C/EBPα, E6AP and β actin antibodies; lysates of 293T alone and transfected with C/EBPα were used as positive and negative control, note that there is no endogenous expression of C/EBPα in 293T. E6AP promotes C/EBPα degradation through ubiquitin-proteasome pathway: (c) 3T3-L1 preadipocytes pre-treated with MDI for 48 h were transiently transfected with expression plasmids for E6AP, E6AP-C843A and His-ubiquitin. Post 48 h Transfection, WCEs were prepared and C/EBPα was co-immunoprecipitated. IgG was used as a control. Co-immunoprecipitates were resolved on 8% SDS-PAGE and blots were probed with anti-His and anti-C/EBPα antibody respectively. E6AP inhibits C/EBPα transactivation potential to activate PPRE-Luc: (d) E6AP mediated downregulation of C/EBPα curtails its transactivation potential: 3T3-L1 preadipocytess were transiently transfected with pPPRE-luc reporter and expression plasmids for C/EBPα, E6AP and E6AP-C843A. 24 h post transfection, luciferase activity was measured. MG132 and lactacytin (LCN) treatment was given 3 h prior to cell harvesting for luciferase activity measurement. Data are representative of three independent experiments. Results are given as standard error of mean (± s.e.m.); *p<0.05; **p<0.001, ***<0.0001.\n\nFigure 3: Figure 3. (a) 3T3L1 preadipocytes pre-treated with MDI were transfected with siE6AP or scrambled siRNA, 48 h post transfection, cells were harvested, resolved on 10% SDS-PAGE and probed C/EBPα, E6AP and β-actin antibody (lysates of 293T transfected with C/EBPα were used as control) (b) 3T3L1 preadipocytes were transfected with siE6AP or scrambled siRNA. Cells were grown in the presence or absence of MDI for 10 days followed by Oil red O staining.\n\nFigure 4: Figure 4. (a) 3T3L1 cells were transfected with siE6AP or scrambled siRNA. Post 48 h transfection, cells were treated with MDI for until ten days; subsequently mRNA expression levels of indicated adipogenic genes was determined with qRT-PCR. Over expression of wild type E6AP down regulates while catalytically inactive E6AP-C843A up regulates proadipogneic factors: (b) 3T3L1 cells were transfected with E6AP and E6AP-C843A. After transfection cells were treated with MDI for 10 days and mRNA expression level of various adipogenic genes was determined with real time PCR. The primers used for C/EBPα, PPARγ, Leptin, SREBP1c and Adipsin listed in table 1.\n\nFigure 5: Figure 5. Mesenchymal progenitor cells were transfected with E6AP (2.0 µg) and E6AP-C843A (2.0 µg). Post 48 h of transfection, cells were grown in presence or absence of MDII for next 8 days followed by Oil red O staining."
      }
    ]
  },
  {
    "id": "PMC3706230_multi",
    "image": [
      "images/PMC3706230-f1.png",
      "images/PMC3706230-f2.png",
      "images/PMC3706230-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"SURF1 deficiency: a multi-centre natural history study\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clinical features in 44 patients with SURF1 deficiency. The x axis indicates the age of onset (years) and the y axis indicates the clinical features. Percentages denote the proportion of patients with a given clinical feature, and box-and-whisker plots show the age of onset. The median age of onset is indicated by the vertical line within the boxes. Boxes represent upper and lower quartiles, whiskers represent extreme values, and dots represent outliers which are ≥1.5 times the interquartile range from the median. Other less commonly observed features included hypertrichosis (41%), optic atrophy (23%), encephalopathy (20%), seizures (14%) and cardiomyopathy (2%).\n\nFigure 2: Figure 2. Pathogenic mutations in the human SURF1 gene. A schematic diagram of the SURF1 gene illustrating 83 mutations reported to date. Red: novel unreported mutations identified in this study, blue: other mutations which have been previously reported and found in this study, black: mutations previously reported in the literature.\n\nFigure 3: Figure 3. Kaplan-Meier survival curves comparing SURF1 deficiency, LRPPRC-deficient LS and nuclear-encoded complex I deficient Leigh/Leigh-like syndrome. Blue line: SURF1 deficient patients, n = 142 (this article and literature), red line: LRPPRC deficient patients, n = 56 [8], green line: complex I deficient Leigh/Leigh-like syndrome n = 63 [9]. Logrank test p < 0.001."
      }
    ]
  },
  {
    "id": "PMC3713238_multi",
    "image": [
      "images/PMC3713238-f1.png",
      "images/PMC3713238-f2.png",
      "images/PMC3713238-f3.png",
      "images/PMC3713238-f4.png",
      "images/PMC3713238-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Expanding functional repertoires of fungal peroxisomes: contribution to growth and survival processes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Hyphal tip bursting upon hypotonic shock in the filamentous fungus A. oryzae. (A) Time-lapse observation of hyphal tip bursting upon hypotonic shock. Hyphal tips at the edge of a colony grown on agar medium were observed by DIC microscopy before and after flooding hyphae with water. Bar: 50μm. (B) Excessive loss of cytoplasmic constituents is prevented upon hyphal tip bursting induced by hypotonic shock. The cytoplasm was labeled by EGFP. An arrowhead and arrow indicate a burst hyphal tip and the adjacent septum, respectively. Note that the cell (2nd) adjacent to the lysed cell (1st) retains its cytoplasmic constituents, as determined by DIC and fluorescence microcopy. Bar: 10μm.\n\nFigure 2: Figure 2. Morphology and function of the Woronin body. (A) Schematic model of Woronin body function. (B) Transmission electron microscopic observation of Woronin bodies (arrows) in A. oryzae (Maruyama et al., 2005). Bar: 500 nm. (C) Confocal images of Woronin bodies (red, arrows) and septa (green, asterisks) before (left) and after (right) hyphal tip bursting induced by hypotonic shock. Woronin bodies and septa were fluorescently labeled by expressing DsRed2–AoHex1 and RNase T1–EGFP fusion proteins, respectively (Maruyama et al., 2005). Bar: 2μm.\n\nFigure 3: Figure 3. Differentiation of the Woronin body from peroxisomes. (A) Fluorescence microscopic analysis of wild-type and Δpex11 strains of A. oryzae expressing EGFP-PTS1 and mDsRed-AoHex1 fusion proteins for visualization of peroxisomes and the major Woronin body protein, respectively (Escaño et al., 2009). Asterisks denote septa and arrows indicate Woronin bodies (red) independent of peroxisomes (green). Arrowheads represent assembly of Hex1 attached to the matrix side of the peroxisome. Bars: 5 μm. (B) Schematic model of Woronin body differentiation from peroxisomes.\n\nFigure 4: Figure 4. Biotin biosynthetic pathway and biotin auxotrophy in peroxisome-deficient strains. (A) The final four reactions of the biotin biosynthetic pathway and involved enzymes from fungi and plants (in parentheses). (B) Growth impairment of strains defective in peroxisomal targeting signal receptors (Δpex5 and Δpex7) grown on minimal medium containing glucose as the sole carbon source. Growth of the wild-type, Δpex5, and Δpex7 strains and the complemented strains (indicated to the right) on medium with and without biotin.\n\nFigure 5: Figure 5. Phylogenetic relationship and peroxisomal localization of fungal BioF proteins. (A) Phylogenetic analysis of fungal BioF proteins. The amino acid residues of the C-terminal peroxisomal targeting signals (PTS1) are indicated by open boxes. The full-length amino acid sequences of the fungal BioF proteins were aligned using the Clustal W program (version 2.1), and then the phylogenetic tree was constructed. The Genbank accession numbers for the sequences used in the analysis are as follows: Aspergillus oryzae, XP_001817022.1; Aspergillus flavus, XP_002383037.1; Aspergillus fumigatus, XP_747713.1; Aspergillus nidulans, ACR44939.1; Aspergillus niger, XP_001396737.1; Penicillium chrysogenum, XP_002563821.1; Podospora anserina, XP_001903515.1; Yarrowia lipolytica, XP_504066.1; Sclerotinia sclerotiorum, XP_001590700.1; Ustilago maydis, XP_757344.1; Cryptococcus neoformans, XP_566616.1; Coprinopsis cinerea, XP_001836705.2; and Schizophyllum commune, XP_003028193.1. (B) Peroxisomal localization of fungal BioF protein. Note that BioF (BioF-mDsRed-PTS1) co-localizes with peroxisomes (EGFP-PTS1), but disperses in the absence of PTS1 (BioF-mDsRed-ΔPTS1) (Tanabe et al., 2011). Bars: 5 μm."
      }
    ]
  },
  {
    "id": "PMC3713238_multi_2",
    "image": [
      "images/PMC3713238-f6.png",
      "images/PMC3713238-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Expanding functional repertoires of fungal peroxisomes: contribution to growth and survival processes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Model of subcellular compartmentalization of the biotin biosynthetic pathway in eukaryotes.\n\nFigure 7: Figure 7. Phylogenetic relationship and peroxisomal localization of plant BioF proteins. (A) Phylogenetic analysis of plant BioF proteins (Maruyama et al., 2012). The amino acid residues of C-terminal peroxisomal targeting signals (PTS1) are indicated by open boxes. The full-length amino acid sequences of the plant BioF proteins were aligned using the method described in Figure 5. The Genbank accession numbers for the sequences used in the analysis are as follows: Arabidopsis thaliana, NP_974731.1; Arabidopsis lyrata, XP_002871105.1; Oryza sativa-1, BAD87813.1; Oryza sativa-2, NP_001065381.1; Hordeum vulgare, BAK03504.1; Brachypodium distachyon, XP_003574335.1; Sorgham bicolor, XP_002467492.1; Zea mays-1, ACG35792.1; Zea mays-2, ACG35881.1; Selaginella moellendorffii-1, XP_002969752.1; Selaginella moellendorffii-2, XP_002981364.1; Physcomitrella patens, XP_001769874.1; Picea sitchensis, ABR18106.1; Vinis vinifera, XP_002268950.1; Medicago truncatula, XP_003598166.1; Glycine max-1, XP_003527547.1; and Glycine max-2, XP_003522881.1. The amino acid sequence of the BioF protein of Marchantia polymorpha was confirmed by PCR amplification and cDNA sequencing based on information obtained from the Marchantia expression sequence tag database (Maruyama et al., 2012). (B) Peroxisomal localization of plant BioF protein. Note that BioF (EGFP-BioF-PTS1) co-localizes with the peroxisomes (PTS2-mRFP1), but disperses in the absence of PTS1 (EGFP-BioF-ΔPTS1) (Tanabe et al., 2011). Bars: 5 μm."
      }
    ]
  },
  {
    "id": "PMC3743609_multi",
    "image": [
      "images/PMC3743609-f1.png",
      "images/PMC3743609-f2.png",
      "images/PMC3743609-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Developing therapeutic approaches for metachromatic leukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Sulfatide metabolic pathway. Notes: The figure shows the biosynthetic pathways of sulfatide, the sphingolipid that accumulates during metachromatic leukodystrophy MLD. The specific enzymes described in each step of the pathway are in italics. The rounded boxes depict the products or substrates of the reactions. The green shaded square shapes show different therapeutic approaches for MLD treatment. Two current substrate reduction therapies for another lysosomal disease (Gaucher disease) are also shown: N-Butyldeoxynojirimycin (NB-DNJ) miglustat (Zavesca®, Actelion Pharmaceuticals Ltd, Allschwil, Switzerland), and eliglustat tartrate. Both of these small molecules competitively inhibit ceramide glucosyltransferase. Abbreviations: ASA, arylsulfatase A; EET, enzyme enhancement therapy; ERT, enzyme replacement therapy; Gal, galactose; HSCT, hematopoietic stem cell transplantation; Glc, glucose; SGal-Glc-cer, sulfo-galactose-glucosylceramide; MLD, metachromatic leukodystrophy; SRT, substrate reduction therapy.\n\nFigure 2: Figure 2. Schematic representation of the mechanism of action of enzyme enhancement agents including pharmacological chaperones (PCs) and proteostasis regulators (PRs). Notes: ASA is synthesized in the endoplasmic reticulum (ER) as several other proteins target to different intracellular organelles, plasma membrane, and those destined to be secreted to the extracellular environment. Concomitant to the translation process, nascent ASA peptide interacts with several components of the ER folding system. Once folded properly, ASA is targeted to the ER exit pathway and ultimately reaches the lysosomal compartment, where it exerts its physiological function. Missense mutations in the ARSA gene can affect physicochemical interactions between amino acids, resulting in impairment of the folding process of the mutant ASA. PCs (blue boxes) are small molecules that physically interact with the target protein, in this case ASA, and assist its folding, preventing it from being targeted to the ERAD pathway and ultimately degraded by the ubiquitin-proteasomal system. Thus, increased levels of mutant ASA reach the lysosomes to degrade the natural substrate (sulfatides). eventually, other small molecules function as PRs (beige/brown boxes), which can improve the cellular folding capacity by interacting with ER folding components. These molecules can also promote physiological cellular responses, such as unfolded protein response, which can be advantageous to enhance folding of specific misfolded ASA mutants. Other PRs (red boxes) can also potentially inhibit components of ERAD and favor the interactions of misfolded ASA mutants with the ER folding elements, increasing the probability of reaching a folding-like conformation. Abbreviations: ASA, arylsulfatase A; ER, endoplasmic reticulum; ERAD, endoplasmic reticulum associate degradation; PC, pharmacological chaperones; PR, proteostasis regulators.\n\nFigure 3: Figure 3. Cell-based high-throughput screening (HTS) assay. Notes: Here, a cell-based HTS assay for galactocerebrosidase (GALC), which is the lysosomal enzyme deficient in Krabbe disease or globoid cell leukodystrophy (GLD), is depicted for (A and B). The 1,536-well plate contains GLD patient cells that are cultured and treated with a small molecule collection for a specific period of time. After the treatment period, the specific enzyme GALC can be measured using a fluorescent substrate, 6-hexadecanoylamino-4-methylumbelliferyl-β-D-galactoside (HMU) for the enzyme. In each 1,536-well plate, control cells (columns 2 and 3) are seeded and later assayed. These control cells have normal Gal-ase enzymatic activity and are not treated with the library. The columns 1 and 2 contain only culture medium and no cells, and are used as backgrounds for the assays. Columns 5–48 contain cultured patients cells (B)– in this case, fibroblasts. Each well (yellow square) corresponds to a specific small molecule from the library, which is tested in different concentrations. (C) Two-plate view diagrams are shown with the fluorescent signals generated from the HMU against the different rows of a 1,536-well plate. Substantial assay window is observed between GALC enzymatic activity of controls (triangles) and GLD patient cells (circles). The small molecule candidates are selected based on the enhancement of the residual GALC enzyme activity. (D) The quantitative nature of the HTS assay, where seven different concentrations of the target library were tested, allows the generation of concentration-response curves (CRCs) given by the HMU fluorescence signal increase. Based on the characteristics of the CRCs,146 prioritization of “hits” can be done during the validation process with secondary and tertiary assays."
      }
    ]
  },
  {
    "id": "PMC3764329_multi",
    "image": [
      "images/PMC3764329-f1.png",
      "images/PMC3764329-f2.png",
      "images/PMC3764329-f3.png",
      "images/PMC3764329-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomes and sexual development in fungi\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The sexual life cycle of a model filamentous ascomycete fungus. Sexual reproduction of most filamentous Ascomycetes takes place inside of multicellular fruiting bodies, which consist on sexual tissues (the hymenium) surrounded by a protective envelope. The hymenium is derived from mating and after karyogamy and meiosis produces sexual spores (ascospores), whereas the envelope tissues originate from maternal vegetative hyphae and are sterile. In a number of Ascomycetes, pyriform-shaped sexual fructifications are known as perithecia (singular perithecium). The sexual life cycle of filamentous Ascomycetes initiates by the differentiation of female organs (ascogonia), which originate as curved branches arising from vegetative hyphal cells. Ascogonia then become surrounded by aggregated hyphae, which eventually develop the perithecial envelope. Ascogonia can be fertilized by hyphae or asexual spores, but some fungi differentiate specialized cells that act as male gametes (spermatia). In heterothallic (self-sterile) fungi, fertilization only takes place between reproductive structures that differ genetically at their mating type (denoted in the figure as mat+ and mat− and illustrated by nuclei with different shading). After fertilization, the male gametic nucleus is delivered into the ascogonium, which contains the female gametic nuclei. This results in the formation of the hymenium. The upper inset illustrates the development of the hymenium from the dikaryotic stage to ascospore formation (from left to right): the two gametic nuclei (of opposite mating type in heterothallic fungi) are isolated in pairs in specialized hook-shaped cells called croziers. After coordinated mitoses (lines linking nuclei represent spindles) and septa formation, three cells are formed in each crozier: an upper binucleated and two flanking uninucleated cells. The two uninucleated cells fuse to produce a new dikaryotic crozier, which propagates the dikaryotic stage, whereas the upper dikaryotic cell undergoes karyogamy and develops into an ascus (the meiocyte). Meiosis takes place in this upper cell. Finally, the haploid nuclear products issued from meiosis are packaged into ascospores. In the figure, which illustrates the development of P. anserina, the eight nuclei issued from a post-meiotic mitosis are enclosed two by two into ascospores resulting in asci with four binucleated ascospores. Ascospores maturate inside the original mother ascus, from which they are ultimately forcibly ejected out.\n\nFigure 2: Figure 2. Metabolic pathways for fatty acid and acetate utilization. Triacylglycerides, which accumulate inside of lipid droplets, are converted to fatty acids and transferred to peroxisomes for catabolism. Fatty acids are converted to acetyl-coenzyme A (-CoA) by the fatty acid β-oxidation pathway. In ascomycete yeasts like Saccharomyces cerevisiae, the β-oxidation pathway is exclusively peroxisomal (Hiltunen et al., 2003; Shen and Burger, 2009). However, in most other fungi, this pathway occurs in peroxisomes and mitochondria (Maggio-Hall and Keller, 2004; Boisnard et al., 2009; Shen and Burger, 2009; Kretschmer et al., 2012a,b; Patkar et al., 2012) (only the peroxisomal pathway is illustrated). The anaplerotic glyoxylate cycle then allows the conversion of acetyl-CoA to four-carbon dicarboxylic acids by bypassing the decarboxylation reactions of the tricarboxylic acid (TCA) cycle (note that two reactions can feed acetyl-CoA into the glyoxylate cycle, asterisks). The glyoxylate shunt intermediates can replenish the TCA cycle or serve as precursors for gluconeogenesis (shuttling between compartments of some intermediates, such as malate and oxaloacetate, is not illustrated). The glyoxylate cycle consists of five enzymatic reactions, of which three are shared with the TCA cycle. Depending on the fungal lineage, these three enzymatic steps (blue font) can take place in peroxisomes, mitochondria or the cytosol (except for citrate synthase, for which no cytosolic form has been described so far). In contrast, the specific enzymes of the glyoxylate cycle, isocitrate lyase and malate synthase (red font), are typically peroxisomal (Kunze et al., 2006; Hynes, 2010; Strijbis and Distel, 2010). The most notable exception is S. cerevisiae, which harbors cytosolic isocitrate lyase (Taylor et al., 1996). Peroxisomal β-oxidation-produced acetyl-CoA can also be transferred to mitochondria for energy generation via TCA cycle. This transport depends on the interconversion of acetyl-CoA and acetyl-carnitine by carnitine acetyl-CoA transferases (green font). Acetyl-carnitine can then be imported into mitochondria by an acyl-carnitine carrier protein (Strijbis and Distel, 2010). Fatty acyl-CoA β-oxidation intermediates may also be transferred to mitochondria for further β-oxidation and acetyl-CoA generation within mitochondria (not shown). Cytosolic acetyl-CoA, which can be produced from C2 compounds, can also be transferred via acetyl-carnitine to mitochondria and peroxisomes for metabolism via the TCA and glyoxylate cycles. Only relevant enzymes are shown, abbreviations are as follows: ACO, aconitase; CAT, carnitine acetyltransferase; CS, citrate synthase; FUM, fumarase; IDH, isocitrate dehydrogenase; IL, isocitrate lyase; KDH, α-ketoglutarate dehydrogenase; MDH, malate dehydrogenase; MS, malate synthase; SCS, succinyl CoA synthetase; SDH, succinate dehydrogenase.\n\nFigure 3: Figure 3. Model for the regulation of the docking/translocation machinery for peroxisome matrix protein import during sexual development in P. anserina. The peroxins of the docking/translocation machinery are differentially required during sexual development in P. anserina. PEX14 (only the peroxin number is indicated) is required for peroxisome matrix protein import at the dikaryotic stage, in asci after the first meiotic metaphase and in ascospores; but not during the first meiotic prophase or in the early stages of ascospore differentiation (not depicted). PEX14/17 is involved in the import of matrix proteins in meiosis after metaphase-I, but it is not required for import in young differentiating ascospores (not illustrated). Upon ascospore maturation, PEX14/17 is required for the import of PTS1-containing proteins, but not for the PEX5-dependent import of proteins missing PTS1 signals, like the peroxisomal fatty acid β-oxidation multifunctional enzyme FOX2. The third docking protein, PEX13, is likely required for the activity of the docking/translocation machinery throughout meiotic development; however, absence of this protein blocks meiocyte formation. Thus, its function during meiotic development cannot be assessed (depicted with translucent shading). In addition to PEX13 (and unlike PEX5, PEX7, PEX14, or PEX14/17), PEX20 is also required for meiocyte formation, which suggests an alternative import pathway required at the dikatyoric stage for meiocyte formation. PEX20 could provide a pore-forming activity (illustrated by a translucent membrane location) additional to PEX5 for the translocation of proteins across the peroxisomal membrane (see text and Peraza-Reyes et al., 2011 for details).\n\nFigure 4: Figure 4. Examples of sexual development defects produced by deficient peroxisome biogenesis in P. anserina. Sexual fruiting bodies of P. anserina wild-type (A) or Δpex14 (B) homozygous crosses contain asci with four ascospores. In absence of PEX14, ascospore pigmentation is deficient (B). In contrast, perithecia from RING-finger-complex (C, here a Δpex2Δpex10Δpex12 strain) or Δpex20 (D) mutants contain only crozier-shaped dikaryotic cells. Image in (D) shows the nuclei distribution in these cells (DAPI staining). Lowercase letters indicate progressive developmental stages of crozier differentiation: (a) binucleated young croziers bending. (b) After simultaneous mitoses, each crozier contains four nuclei. (c) Septa formation (arrowheads) delimitates a dikaryotic upper cell from uninucleate lateral and basal cells. The uninucleated cells fuse (asterisk arrow) and the lateral-cell nucleus migrates into the basal compartment. Instead of undergoing karyogamy and meiosis as in the wild type, the nuclei from the upper dikaryotic crozier cell will be engaged in the formation a new crozier (arrow). This results in crozier “trees” where no asci are produced, as shown in (C). Note how each original crozier (inset in C, arrowhead) produces two new croziers (arrows). Scale bars, A–C: 10 μm; D: 5 μm."
      }
    ]
  },
  {
    "id": "PMC3829121_multi",
    "image": [
      "images/PMC3829121-f1.png",
      "images/PMC3829121-f2.png",
      "images/PMC3829121-f3.png",
      "images/PMC3829121-f4.png",
      "images/PMC3829121-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"III. Cellular ultrastructures in situ as key to understanding tumor energy metabolism: biological significance of the Warburg effect\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Mouse 3. The erythrosomes (ES) and the fibroblast (FB) oriented “diagonally” separated the tumor nodules. One nodule contained plasma cells (T-PC), as partly shown in the upper right corner. Cells in the lower and left part of the image belonged to the other nodule. Flanked by tumor cells were the vasculature-initiating cells: erythroblast (T-EB), as identified by the disappearing nucleus and mitochondria converting into peroxisomes, and endothelial cell (T-EC). The two cells were locally separated by anoikis (arrows) 30. To the left of the T-EC, is a partly shown large nucleus with two nucleoli, likely belonging to a megakaryocyte of tumor origin (T-M); peroxisomes are visible in the cytoplasm above the nucleus.\n\nFigure 2: Figure 2. Mouse 4. The erythroblast (T-EB), differentiating endothelial cell (T-EC), possibly megakaryocyte (T-M). Ovals contain peroxisomes forming in tumor cells (T). Arrows point to the anoikis 30 area.\n\nFigure 3: Figure 3. Mouse 4. Mitochondria at various stages of conversion into peroxisomes (white stars); ER (black stars); autophagosomes (+). The arrows point to electron lucent vesicles that might contain catalase (compare with Figure 7 in 16). The enlarged boxed area is rotated left in Figure 4[A] whereas the microenvironment of the erythroblast (T-EB) is shown in Figure 2. Mitochondria (M) of the tumor cell (T) in the upper right corner are characteristic of the quiescent cells but some show signs of hypoxia (m), as do dilated cisternae of ER (black stars).\n\nFigure 4: Figure 4. Mouse 4. The point of contact for mitochondrial outer membrane (white star), ER (black star) and nuclear membrane (x) is located in the center of the circle [ A]. Such membrane continuity between the ER and mitochondrion converting into peroxisome was also seen in a tumor cell with intact nucleus [ B]. Examples of more advanced forming peroxisomes are shown in [ C & D]. Arrows point to peroxisomes with a single membrane [ D].\n\nFigure 5: Figure 5. Mouse 5. Electron lucent regions were commonly associated with atypically shaped mitochondria (stars). Calmyrites were detected by immunocytochemical staining with calmyrin-specific antibody."
      }
    ]
  },
  {
    "id": "PMC3829121_multi_2",
    "image": [
      "images/PMC3829121-f6.png",
      "images/PMC3829121-f7.png",
      "images/PMC3829121-f8.png",
      "images/PMC3829121-f9.png",
      "images/PMC3829121-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"III. Cellular ultrastructures in situ as key to understanding tumor energy metabolism: biological significance of the Warburg effect\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Mouse 5 [ A– H] and normal rat lung [ I]. Erythroblast [ A], megakaryocyte [ B], platelet [ C], granulocyte [ D], plasma cell [ E], hemangioblast [ F], smooth muscle [ G], erythrosome [ H], and lung endothelium of control sample from normal rat lung [ I].\n\nFigure 7: Figure 7. Mouse 4. Gold grains associated with chromatin of the interphase nucleus and a cluster of the gold particles (arrow) co-localized with one of the peroxisomes (stars) in [ A]. The label was also found in the mitotic chromosomes and mitochondria of the dividing cell [ B]. In the cell undergoing mitosis, the mitochondria were comparatively smaller, more electron-dense and often accompanied by an electron-lucent region, similar to those converting into peroxisomes [ C]. Mice 3 [ A] & 4 [ B& C].\n\nFigure 8: Figure 8. Mouse 4. The cell partly shown in [ A] (enlargement of the boxed area in [ B]) displayed features typical of definitive erythroblasts undergoing nucleo-cytoplasmic conversion: dark nuclear lobes separated from cytoplasm by multilayered corrugated membranes and peroxisomes in the absence of mitochondria. However, the shape and location of that cell were such that by light microscopy, it would look like an EC [ B]. At one region, its plasma membrane appeared fused with the membrane of an underlying EC (arrow in [ A]) suggesting that simultaneously with experiencing erythrogenic conversion, the cell was penetrating the endothelium of a vessel that already contained some non-circulating blood (as judged by irregular shapes of the erythrosomes). A smaller, forming vessel in [ C] appeared to have converted one of its’ ECs into erythroschizosome, which had then moved into the lumen, leaving a vacant space behind, and had already separated one monomer completely and another one partially. The cell in [ D] represented an ambivalent (hemangioblastic) phenotype, similar to those seen five days after pseudo-orthotopic implantation 5. However, here it had an increased level of phenotypic complexity, as manifested by the presence of caveolae (arrow), a hallmark of EC, and remodeling of the internal membranes covering the emerging erythrosome (upper left corner), in addition to collagen synthesis (bundle of collagen fibers under the right end of the scale bar).\n\nFigure 9: Figure 9. Mouse 3. The erythrosomes (ES, red) and the fibroblast (FB, yellow) oriented “diagonally” separated the tumor nodules. One nodule contained plasma cells (T-PC, brown), as partly shown in the upper right corner. Cells in the lower and left part of the image belonged to the other nodule. Flanked by tumor cells (T, brown) were the vasculature-initiating cells: erythroblasts (T-EB, red), as identified by the disappearing nucleus and mitochondria converting into peroxisomes, and endothelial cell (T-EC, green). The two cells were locally separated by anoikis (arrows) 30. To the left of the T-EC, is a partly shown large nucleus with two nucleoli, likely belonging to a megakaryocyte of tumor origin (T-M, purple); peroxisomes are visible in the cytoplasm above the nucleus.\n\nFigure 10: Figure 10. Mouse 4. The erythroblast (T-EB, red), differentiating endothelial cell (T-EC, green), possibly megakaryocyte (T-M, purple). Ovals contain peroxisomes (red) forming in tumor cells (T, brown). Arrows point to the anoikis 30 area."
      }
    ]
  },
  {
    "id": "PMC3829121_multi_3",
    "image": [
      "images/PMC3829121-f11.png",
      "images/PMC3829121-f12.png",
      "images/PMC3829121-f13.png",
      "images/PMC3829121-f14.png",
      "images/PMC3829121-f15.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"III. Cellular ultrastructures in situ as key to understanding tumor energy metabolism: biological significance of the Warburg effect\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Mouse 4. Mitochondria at various stages of conversion into peroxisomes (white stars); ER (black stars); autophagosomes (+). The arrows point to electron lucent vesicles that might contain catalase (compare with Figure 7 in 16). The enlarged boxed area is rotated left in Figure S4[A] whereas the microenvironment of the erythroblast (T-EB, reddish brown) is shown in Figure S2. Mitochondria (M) of the tumor cell (T) in the upper right corner are characteristic of the quiescent cells but some show signs of hypoxia (m), as do dilated cisternae of ER (black stars).\n\nFigure 12: Figure 12. Mouse 4. The point of contact for mitochondrial outer membrane (white star), ER (black star) and nuclear membrane (x) is located in the center of the circle [ A]. Such membrane continuity between the ER and mitochondrion converting into peroxisome was also seen in a tumor cell with intact nucleus [ B]. Examples of more advanced forming peroxisomes are shown in [ C & D]. Arrows point to peroxisomes with a single membrane [ D]. Mitochondria and peroxisomes are in different shades of brown in comparison to the rest of each cell.\n\nFigure 13: Figure 13. Mouse 5. Electron lucent regions were commonly associated with atypically shaped mitochondria (brown). Calmyrites were detected by immunocytochemical staining with calmyrin-specific antibody. Arrows indicate anoikis.\n\nFigure 14: Figure 14. Mouse 5 [ A– H] and normal rat lung [ I]. Erythroblast [ A, red], megakaryocyte (purple) [ B], platelet (purple) [ C], granulocyte [ D], plasma cell [ E], hemangioblast [ F], smooth muscle [ G], erythrosome (red) [ H], lung endothelium (green) of control sample from normal rat lung [ I].\n\nFigure 15: Figure 15. Mouse 4. Gold grains associated with chromatin of the interphase nucleus and a cluster of the gold particles (arrow) co-localized with one of the peroxisomes (stars) in [ A]. The label was also found in the mitotic chromosomes and mitochondria of the dividing cell [ B]. In the cell undergoing mitosis, the mitochondria were comparatively smaller, more electron-dense and often accompanied by an electron-lucent region, similar to those converting into peroxisomes [ C]. Mice 3 [ A] & 4 [ B & C]. Mitochondria and peroxisomes are in different shades of brown."
      }
    ]
  },
  {
    "id": "PMC3830196_multi",
    "image": [
      "images/PMC3830196-f1.png",
      "images/PMC3830196-f2.png",
      "images/PMC3830196-f3.png",
      "images/PMC3830196-f4.png",
      "images/PMC3830196-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Calmodulin-like protein AtCML3 mediates dimerization of peroxisomal processing protease AtDEG15 and contributes to normal peroxisome metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. AtDEG15 interacts with AtCML3 through its N-terminal 25 amino acids. To analyse protein interaction by Y2H, the full-length coding regions of AtDEG15, several truncated variants and AtCML3 were cloned into pBridge and pGAD424, fusing them with the DNA-binding domain or with the DNA-activation domain, respectively. As negative controls a combination of empty vectors and vectors harbouring one of the constructs were used. A Schematic representation of AtDEG15 and the various deletion constructs used in B and C: green, AtCML3 binding domain; red, protease domain with plant-specific loop; blue, PTS1. B Growth on His-free medium (−His) indicates interaction by transcription of the His3-reporter; (+His), positive growth control. Negative controls are shaded in grey. Yeast cultures were diluted from 105 cells (left) to 101 cells (right) per 50 μl drop applied. C Interaction is also demonstrated by transcription of the lacZ reporter (β-galactosodase activity in Miller units). Mean (n = 3) ± SD\n\nFigure 2: Figure 2. AtDEG15 is a CaM-binding protein as demonstrated by affinity chromatography on CaM-agarose under native conditions. Recombinant full length AtDEG15 (A) or a C-terminally truncated protein (AtDEG15_N-terminus; DEG15_N) comprising only the first 327 amino acids without the protease and C-terminal domains (B) were incubated with CaM-agarose immediately after His-tag purification in the presence of 0.1 mM CaCl2. Bound protein was eluted with an excess of bovine CaM and all fractions were analyzed by SDS-PAGE and Coomassie staining. In case of AtDEG15 several C-terminally truncated degradation products are visible in addition to the full length protein (A), the longest of which were also able to bind to the calmodulin-agarose matrix. While AtDEG15 and AtDEG15_N-terminus bound specifically to the matrix in the presence of Ca2+ and could be eluted with bovine CaM (A) and (B), no binding occurred in the absence of Ca2+ (5 mM EGTA/EDTA; see supplemental Fig. S2)\n\nFigure 3: Figure 3. Bioinformatic analyses of the putative CML-binding domain in the N-terminal 20 amino acids of plant DEG15. A Helical wheel projection of AtDEG15 Val-3 to Glu-20 reveals a basic amphipathic helix structure (http://cti.itc.virginia.edu/~cmg/Demo/wheel/wheelApp.html). Yellow, nonpolar aa; green, polar, uncharged aa; red, acidic aa; blue, basic aa. B Calmodulin target database (CTDB, http://calcium.uhnres.utoronto.ca/) calculates the highest possible probability (0–9, with 9 being the highest probability) for a CaM binding motif between AtDEG15 Val-6 and Glu-20. C Two established Ca2+-dependent CaM-binding motifs, 1–8–14 and 1–14 based on the spacing between the hydrophobic residues (red), are found within the N-terminal 23 amino acids; charged residues in the amphipathic helix are colored blue; the conserved GP-linker C-terminal to the CaM-binding motif is shaded in grey. The motifs are conserved between dicots and monocots. Ath, Arabidopsis thaliana; Aly, Arabidopsis lyrata; Ptr, Populus trichocarpa; Vvi, Vitis vinifera; Sly, Solanum lycopersicum; Csa, Cucumis sativus; Ppe, Prunus persicus; Gma, Glycine max; Rco, Ricinus communis; Mes, Manihot esculenta; Mgu, Mimulus guttatus; Sit, Setaria italica; Zma, Zea mays; Sbi, Sorghum bicolour; OsJ, Oryza sativa Japonica; Bdi, Brachypodium distachyon. For accession numbers see Supplemental Tab. S2A\n\nFigure 4: Figure 4. AtDEG15 homodimerizes in the presence of AtCML3 as shown by Y3H. Only the full-length AtDEG15 processes PTS2 in planta. A Schematic representation of AtDEG15 and the various deletion constructs analyzed by Y3H and/or by transformation into the A. thaliana deg15 insertion mutant plant SALK007184; green, AtCML3 binding domain; red, protease domain with the plant-specific loop; blue, PTS1; nd, not determined. B Interaction assay using Y3H. The full length AtDEG15 was cloned in pBridge; the various AtDEG15 deletion constructs were cloned in pGAD424. AtCML3 was cloned into the second multiple cloning site of pBridge; it is expressed in the absence of methionine (0 mM Met) and is repressed in the presence of methionine (1 mM Met). Interaction of AtDEG15 with AtDEG15 is strong in the presence of AtCML3; no homodimerization takes place in the absence of AtCML3. Both AtDEG15 molecules need the CML binding domain to achieve homodimerization. The domain N-terminal to the protease domain, especially the CML binding domain in the 25 N-terminal amino acids is necessary for homodimerization. Mean (n = 3) ± SD. C Analysis of PTS2 processing ability of AtDEG15 and its deletion constructs in planta after transformation into the deg15 KO mutant plant (SALK007184). Left: PTS2 processing ability of WT Col0 and deg15 mutant lines SALK007184 and GABI-Kat GK_237G09; middle and right: mutant line SALK007184 transformed with the various AtDEG15c constructs. (a) The transformed constructs are transcribed as shown by RT-PCR. (b) Only full-length AtDEG15 processes pre-gMDH to the mature subunit as shown by westernblot analysis with α-gMDH antibodies. Loss of N-terminal domains, loss of the C-terminus or of the loop within the protease domain abolishes processing. Deletion of N-terminal domains despite including the AtCML3-binding sequence also abolishes PTS2 processing. MM, DNA marker (GeneRuler 1 kb DNA Ladder, Fermentas) and prestained protein molecular weight markers (blue: 58 kDa, 46 kDa, 30 kDa; green 23 kDa; BioLabs), respectively\n\nFigure 5: Figure 5. Analysis of PTS2 processing ability of atcml3 and atdeg15 mutant lines. Only the full-length AtDEG15 processes pre-thiolase to the mature thiolase in planta. A and B The atcml3 mutant line (pst16586, RIKEN)—unlike the atdeg15 mutant line (SALK007184)—is not impaired in processing of pre-gMDH to the mature gMDH (A) or pre-thiolase to the mature thiolase (B) as shown by western blot analysis of protein extracts using antibodies directed against gMDH or thiolase. C Analysis of several AtDEG15 variants shows that only full-length AtDEG15 processes pre-thiolase to mature thiolase as shown by western blot analysis with α-thiolase antibodies. Loss of the N-terminal CML binding-domain, loss of the C-terminus, loss of N- and C-terminus or of the loop within the protease domain all abolish processing. MM, prestained protein molecular weight markers (red, 80 kDa; blue: 58, 46, 30 kDa; green 23 kDa; BioLabs)"
      }
    ]
  },
  {
    "id": "PMC3830196_multi_2",
    "image": [
      "images/PMC3830196-f6.png",
      "images/PMC3830196-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Calmodulin-like protein AtCML3 mediates dimerization of peroxisomal processing protease AtDEG15 and contributes to normal peroxisome metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Resistance of atcml3 and atdeg15 knock out plants to the herbicide precursor 2,4-DB. Photographs show seedlings grown for seven days on solid medium containing 0 μM or 1.8 μM 2,4-DB. WT, wild type plants; cml3(RIKEN), atcml3 knock out plants pst16586; deg15(SALK), atdeg15 knock out plants SALK007184\n\nFigure 7: Figure 7. Phylogenetic relationship of peroxisomal processing proteases from plants, animals and cellular slime molds and of DEG proteases in Arabidopsis. The dotted lines indicate that this part of the tree is not drawn to scale. Sequence alignemnts were obtained by ClustalX 2.0 (Thompson et al. 1997) and phylogenetic tree construction was performed by maximum likelihood using tree-puzzle-5.2 (Strimmer and Haeseler 1996). The alignment on which the phylogenetic tree was based is provided in Supplemental Fig. 7. For accession numbers see Supplemental Tab. S2A"
      }
    ]
  },
  {
    "id": "PMC3837297_multi",
    "image": [
      "images/PMC3837297-f1.png",
      "images/PMC3837297-f2.png",
      "images/PMC3837297-f3.png",
      "images/PMC3837297-f4.png",
      "images/PMC3837297-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome deficient invertebrate and vertebrate animal models\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generalized scheme of peroxisomal β-oxidation in animals. On top, structures of some fatty carboxylates that, after activation (not shown), are degraded by peroxisomal β-oxidation. At the right, enzymatic reactions/enzymes involved in degradation of substrates containing a 2-methylbranch, based on the situation in mammals. Most of these enzymes can act on straight chain substrates, shown at the left, as well. The latter compounds are also recognized by more selective enzymes which do not tolerate a 2-methylbranch. ACAA1, 3-ketoacyl-CoA thiolase; ACOX, acyl-CoA oxidase; AMACR, 2-methylacyl-CoA racemase; MFP, multifunctional protein; SCPx, sterol carrier protein X-thiolase.\n\nFigure 2: Figure 2. Peroxisomal α-oxidation. Scheme of the enzymatic reactions/enzymes involved in the peroxisomal breakdown of phytanic acid (left) and 2-hydroxy long chain fatty acids (right). Enzymes in blue are associated with peroxisomes. ACS, acyl-CoA synthetase; FADH, fatty aldehyde dehydrogenase; HACL1, 2-hydroxyacyl-CoA lyase; PHYH, phytanoyl-CoA α-hydroxylase.\n\nFigure 3: Figure 3. Etherlipid biosynthesis. Scheme of the reactions involved in formation of ether lipids, starting with dihydroxyacetone-phosphate. The long chain alcohol used by ADHAPS it generally 16–18 carbons, either saturated or with one double bond. Double arrows indicate multiple steps, catalyzed by ER-associated enzymes like headgroup addition and the introduction of the double bond in the 1-alkylchain. Generally, plasmalogens are enriched in PUFA at position 2 of the glycerol moiety (shown is 1-hexadecyl-2-arachidonoyl-plasmenylethanolamine). Dietary 1-alkylglycerol can bypass the peroxisomal steps in this pathway (dashed arrow). GNPAT, dihydroxyacetone-phosphate acyltransferase; ADHAPS, alkyl dihydroxyacetone-phosphate synthase; ADR, acyl/alkyl-dihydroxyacetone-phosphate reductase.\n\nFigure 4: Figure 4. Peroxisome biogenesis in animals. Simplified scheme for the import of PTS1-proteins, PTS2-proteins and integral peroxisomal membrane proteins (PMP) in animals and the involved peroxins, indicated by their PEX number. Role of ubiquitination of PEX5 and farnesylation of PEX19 is not shown. After import, some PTS1-proteins are processed by TYSND1, a peroxisomal protease (T), while the signal peptide of PTS2-proteins is cleaved off. Adapted from Van Veldhoven (2010).\n\nFigure 5: Figure 5. Developmental delay in peroxisome deficient animals. (A) Developmental arrest of C. elegans at the L1/L2 stage by Pex5 RNAi (top panel), compared to wild type nematode (bottom panel), being photographed 3 days after being laid. Bar, 10 μm. Reproduced/adapted with permission from Thieringer et al. (2003). (B) Reduced body size and weight of an adult male homozygous pex161 fruitfly compared to heterozygous animal. Taken from Nakayama et al. (2011). (C) Appearance of newborn mice pups, showing severe hypotonia and growth delay in a Pex5−/− pup compared to a wild type littermate."
      }
    ]
  },
  {
    "id": "PMC3888033_multi",
    "image": [
      "images/PMC3888033-f1.png",
      "images/PMC3888033-f3.png",
      "images/PMC3888033-f4.png",
      "images/PMC3888033-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Childhood adrenoleukodystrophy – Classic and variant – Review of clinical manifestations and magnetic resonance imaging\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Bilateral symmetrical areas of altered signal intensities hypointense on T1 (a) and hyperintense on T2 weighted and FLAIR noted in the splenium (b white arrow). Similar areas in the bilateral parieto-occipital white matter in the T1 (c) T2 weighted (d) and FLAIR sequence (f white arrow). Post-contrast study showed typical peripheral enhancement in the corresponding areas (e) Similar intensities (g and h) seen involving the region of the medial geniculate bodies (h white arrow), extending to involve the region of the lateral lemniscus (i white arrow) and along the brainstem\n\nFigure 3: Figure 3. Bilateral symmetrical linear and patchy areas of altered signal intensities noted in the bilateral internal capsules (a white arrow), seen in the pontine fibers extending into the mid-brain (B white arrow) and middle cerebellar peduncles (c white arrow). The post-contrast study showed significant linear and peripheral enhancement in the above areas (c, d, e white arrows)\n\nFigure 4: Figure 4. Biochemical reports show elevated levels of very long chain fatty acids in plasma\n\nFigure 5: Figure 5. Schematic diagram of central auditory pathway"
      }
    ]
  },
  {
    "id": "PMC3893467_multi",
    "image": [
      "images/PMC3893467-f1.png",
      "images/PMC3893467-f2.png",
      "images/PMC3893467-f3.png",
      "images/PMC3893467-f4.png",
      "images/PMC3893467-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Neuropathology of brain and spinal malformations in a case of monosomy 1p36\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MRI images at ages 1 and 10 years. (A) Sagittal T2 weighted image at age 1 year showed a small cerebellar vermis (black arrows) and abnormal posterior arch of C1 (white arrow) causing compression of the posterior aspect of the upper cervical spinal cord. (B) Parasagittal T1 weighted image at age 10 years showed subtle irregularity of the cortical-white matter junction and the surface of the cortex in the left frontal lobe (arrows), consistent with polymicrogyria or similar dysgenesis. (C) Coronal T2 weighted image at age 10 years showed ventriculomegaly and malrotated hippocampi. (D) Coronal T2 weighted image at age 10 years at the level of the ventricular trigones showed periventricular nodular heterotopia of moderate (black arrow) and small (white arrow) sizes.\n\nFigure 2: Figure 2. Macroscopic neuropathology. (A) Superior aspect of brain showed “Moroccan leather” appearance of frontal cortex bilaterally. (B) Inferior aspect of brain showed smooth gyral surfaces. (C) Surface of right frontal cortex corresponding to boxed area in (A), with leptomeninges removed, showed irregular surface of cortical gyri. (D) Coronal slice through the hemispheres revealed bilateral polymicrogyria-like cortical dysgenesis (arrows) involving superior and middle frontal gyri. The gray-white matter junction was irregular in these regions. The corpus callosum was thin, and the lateral and third ventricles were enlarged. (E) Coronal slices of the left occipital lobe demonstrated multiple periventricular nodular heterotopia (arrows). (E’) Magnified view of boxed area in E with multiple heterotopia (arrows). (F-H) The cerebellum exhibited a small, anteriorly rotated vermis with normal number of lobules. (I) Central canal of the lower thoracic and upper lumbar cord was mildly dilated. Scale bars: (in A) A, B, 3 cm; C, 1 cm; D, 3 cm; E, 2 cm; E’, 1 cm; (in F) F, G, 3 cm; H, 2 cm; I, 0.5 cm.\n\nFigure 3: Figure 3. Histologic neuropathology. (A, B) Polymicrogyria-like cortical dysgenesis stained by immunohistochemistry for (A) N52 and (B) MAP1B. Note “festooned” supragranular layers in the patient’s superior frontal gyrus (SFG) and adjacent dorsolateral frontal cortex (superior up, lateral left). The cingulate cortex (Cg) was unaffected, except in the depth of the cingulate sulcus. The corpus callosum (CC) was hypoplastic. (C-E) Lamination of normal, age-matched control cortex demonstrated by (C) N52, (D) MAP1B, and (E) cresyl violet (Nissl) stains. (F, G) Polymicrogyria -like cortical dysgenesis seen at higher magnification (boxed areas from A, B). (H-K) Two-color, double-label immunofluorescence detection of N52 (green) and calretinin (red) in control (H, J) and patient (I, K) cerebral cortex. Low magnification views (H, I) show dot plots of immunolabeled cells. In patient cortex, the number and size of N52+ neurons appeared smaller, but the relative positions of N52+ and calretinin + neurons were unaltered. (L) Multiple synaptophysin-immunoreactive periventricular nodular heterotopia and small irregular heterotopia were identified in occipitotemporal regions adjacent to the lateral ventricle (LV). (M) Periventricular heterotopia exhibited N52 (green) and calretinin (red) immunoreactivity, represented in dot plots. Insets (a, b) show higher magnification photomicrographs. (N) The inferior olivary nuclei appeared slightly simplified with reduced convolutions. (O) The central canal of the spinal cord showed mild hydromyelia with a cross-shaped dilatation in lower thoracic and upper lumbar levels. Note also pallor of anterior and lateral funiculi. Scale bars: (in A) A, B, 5 mm; (in C) C-E, 1 mm; (in F) F, G, 1 mm; (in H) H, I, 500 μm; (in J) J, K, 250 μm; L, 2 mm; M, 500 μm; N, 2 mm; O, 2 mm.\n\nFigure 4: Figure 4. Hippocampal malrotation. (A, C) Normal control hippocampus (stained with Luxol fast blue, and hematoxylin and eosin) and interpretive line diagram. (B, D) Patient hippocampus (immunostained to detect MAP2) and diagram. (B’) Higher magnification of patient’s dentate gyrus showing reduced neuronal population. The patient’s hippocampus, including dentate gyrus (D), CA1-CA3, and subiculum (S) was rotated by ~90 degrees from normal orientation. The temporal horn (T) of the lateral ventricle directly contacted the subiculum in patient but not control brain. The entorhinal cortex (EC), characterized by large neuron clusters in supragranular layers, appeared expanded in the patient brain (small arrows in D). Other abbreviations: P, presubiculum; L, lateral geniculate nucleus; PNH, periventricular nodular heterotopia; TEC, transentorhinal cortex. Large arrows indicate collateral sulcus. Scale bars: (in B) A-D, 750 μm; B’, 75 μm.\n\nFigure 5: Figure 5. Terminal deletion in the distal short arm of chromosome 1. Microarray analysis showed a single-copy loss of 34 BAC clones from 1p36.3, spanning approximately 6.8 Mb, with break point between RP1-126A5 and RP3-438 L4. Probes are arranged with the most distal p-arm clones on the left. The blue tracing shows array comparative genomic hybridization data from the first microarray slide (reference Cy5/patient Cy3). The pink tracing shows data from the second microarray slide in which the dyes have been reversed (patient Cy5/reference Cy3). A subset of genes involved in neural development or function are indicated at their approximate position in the deleted region."
      }
    ]
  },
  {
    "id": "PMC3896743_multi",
    "image": [
      "images/PMC3896743-f1.png",
      "images/PMC3896743-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Neurological impairment among heterozygote women for X-linked Adrenoleukodystrophy: a case control study on a clinical, neurophysiological and biochemical characteristics\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Associations relating JOA and SSPROM scales to independent variables age, disease duration and somato-sensory evoked responses. (A and B) Disease duration of symptomatic heterozygotes. (C and D) Age at examination all heterozygotes. (E) Somato-sensory evoked responses of lower limbs of all heterozygotes.\n\nFigure 2: Figure 2. NSE among the X-ALD heterozygotes and the control women."
      }
    ]
  },
  {
    "id": "PMC3901192_multi",
    "image": [
      "images/PMC3901192-f1.png",
      "images/PMC3901192-f2.png",
      "images/PMC3901192-f3.png",
      "images/PMC3901192-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Perturbations of Lipid Metabolism Indexed by Lipidomic Biomarkers\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pathways of lipid metabolism and traffic in liver.\n\nFigure 2: Figure 2. (A) Identification of molecular species of phosphatidylcholine from total lipid analysis of serum. (B) The distribution of 17 major fatty acids in the total circulating lipidome was obtained by gas chromatography of fatty acid methyl esters prepared by acidic transmethylation. (C) Sera from 93 patients (adults and children) were randomly sampled. Four sera (Obs 66, 21, 5 and 84) show an enrichment in fatty acid marking the accelerated de novo lipogenesis; fatty acid 16:1 (palmitoleic), 18:1ω7 (vaccenic), 20:3ω9 (mead acid) are increased in these patients scored in left part of the biplot. The enrichment is recorded at the expense of the ω-3 essential fatty acid (C 22:6ω3 (docosahexaenoic), 20:5ω3 (eicosapentaenoic), 22:5ω3 (docosapentaenoic acid)) shown “diametrically” opposite in the right part of the biplot. The biplot is obtained by the superimposition of the load plot for the variations of serum fatty acids (the factorial plan F1/F2 represents 46% of the total variations) and the score plot for the 93 observations.\n\nFigure 3: Figure 3. Relationships between endogenous biosynthesis of non-essential fatty acids and dietary sources of essential fatty acids. The separation between pathways leading to the synthesis of non-essential fatty acids (saturated (SAT) and monounsaturated (MUFA-ω7 and -ω9 families) and essential polyunsaturated fatty acids (PUFA-ω6 and -ω3 families) is shown. The interaction (competition for substrate, gene expression) between the separated pathways is presented in the text. Adapted from reference [42].\n\nFigure 4: Figure 4. Discriminant Analysis of Liver Triglycerides in mice models prepared for Non-alcoholic fatty liver disease (NAFLD) treatment tests. Four different subgroups (n = 133) were identified with 2 genetic backgrounds (blue/green and dark blue/black symbols) as a function of the enriched or depleted lipid diets (green/dark blue and blue/black symbols). Triglyceride molecular species in the liver lipid extract were assayed by LCMS2. The multivariate analysis was conducted taking into account an increasing number of molecular species A = 11, B = 21, C = 31 and D = 51. In each subgroup the centroid (yellow dot) and confidence ellipses are calculated and positioned to maximize the discrimination of subgroups in the factor plan F1/F2. It is apparent that the within-class dispersion is decreased but the separation (between-classes covariance) is increased between centroid subgroups as a function of the number of molecular species which is taken into account for calculation. However the confusion matrix reveals that the rate of erroneous assignment to subgroups of test samples is sharply rising with the number of molecular species taken into account in the calculation (A, 0%; B, 0%; C, 77%; D, 83%). See Section 5."
      }
    ]
  },
  {
    "id": "PMC391370_multi",
    "image": [
      "images/PMC391370-f1.png",
      "images/PMC391370-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Pathogenesis of peroxisomal deficiency disorders (Zellweger syndrome) may be mediated by misregulation of the GABAergic system via the diazepam binding inhibitor\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Molecular conditions leading to Zellweger-like syndromes in human and mouse. Biochemical and pathological consequences that are not common to all disorders are indicated. PEXn = any of the peroxisome biogenesis proteins that can be mutated in classical Zellweger syndrome. MFP1/2 = multifunctional proteins of peroxisomal beta-oxidation. DHAPAT = dihydroxyacetone phosphate acyl transferase. VLCFAs = very long-chain fatty acids. DHA = docosahexaenoic acid.\n\nFigure 2: Figure 2. Possible regulatory network leading to disturbed GABAergic signaling in peroxisome-deficient patients. Arrows indicate the predicted direction of change in the patients. See text for details."
      }
    ]
  },
  {
    "id": "PMC3926955_multi",
    "image": [
      "images/PMC3926955-f1.png",
      "images/PMC3926955-f2.png",
      "images/PMC3926955-f3.png",
      "images/PMC3926955-f4.png",
      "images/PMC3926955-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Atg37 binds Atg30 or palmitoyl-CoA to regulate phagophore formation during pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Atg37 is an integral PMP that binds Pex3. (A) Pex3 coimmunoprecipitates with Atg37. IP, immunoprecipitate. Cells were induced in methanol medium for 4 h. (B) Atg37ΔC binds Pex3ΔN in vitro. I, input; U, unbound; P, pull-down. (C) Atg37 is an integral membrane protein. PNS, postnuclear supernatant; 27S, 27,000 g supernatant; 27P, 27,000 g pellet; S, 200,000 g supernatant; P, 200,000 g pellet. (D) Atg37 localizes to the peroxisomal membranes (in WT) or ER-associated peroxisome remnants labeled with Pex3-mRFP (in Δpex19). DIC, differential interference contrast. Bar, 5 µm. (E) The TMD is essential for peroxisomal localization of Atg37. SKL, Ser-Lys-Leu, a peroxisomal targeting signal. Bar, 5 µm.\n\nFigure 2: Figure 2. Atg37 is required for pexophagy at the stage of phagophore formation. (A) Atg37 is expressed strictly under peroxisome proliferation conditions. Glc, glucose medium; Eth, ethanol medium; Mth, methanol medium; Ole, oleate medium; F1β, loading control. (B and C) Atg37 is dispensable for peroxisome biogenesis. Peroxisome biogenesis was assessed by the growth of strains in methanol (B) and oleate (C) media. The data shown are from a single representative experiment out of two repeats. (D and E) Atg37 is required for micropexophagy (D) and macropexophagy (E). Cells were replica plated from methanol to glucose and ethanol plates, respectively. The residual activity of AOX was used to assess pexophagy. (F and G) Atg37 is needed for the delivery of peroxisomes to the vacuole during micropexophagy (F) and macropexophagy (G). Methanol-grown cells were adapted to glucose and ethanol media, respectively. FM 4-64 labeled vacuolar membranes. Arrows point to the WT vacuoles with the peroxisome-associated GFP-SKL. Bars, 5 µm. (H and I) Atg37 is essential for MIPA (H) and pexophagosome (I) formation during micropexophagy and macropexophagy, respectively. Methanol-grown cells were adapted to glucose and ethanol media. Arrows point to MIPA (H) and pexophagosome (I) in the WT cells. Bars, 5 µm.\n\nFigure 3: Figure 3. Atg37 is dispensable for the Cvt pathway and nonselective autophagy. (A) Atg37 is not required for the maturation of prApe1. Cells were grown in glucose medium (“Growth”) and then adapted to glucose medium without nitrogen for 6 h (“Starvation”). mApe1, mature Ape1; *, nonspecific band. (B) Atg37 is dispensable for cell survival during nitrogen starvation. Aliquots of cultures starved in glucose medium without nitrogen were plated on YPD medium. The number of cells able to form colonies was counted after 2–3 d of incubation. The data shown are from a single representative experiment out of two repeats. (C) Atg37 is not required for GFP-Atg8 processing by autophagy. Glucose-grown cells were adapted to glucose medium without nitrogen (SD-N).\n\nFigure 4: Figure 4. Overexpression of Atg37 does not interfere with pexophagy. (A and B) Overexpression of Atg37 does not induce pexophagy (A) or affect the growth of cells in methanol medium (B). The data shown in B are from a single representative experiment out of two repeats. Ee, endogenous expression; Oe, overexpression. (C) Overexpression of neither N-terminal (GFP-Atg37) nor C-terminal (Atg37-GFP) fusions of Atg37 and GFP affects pexophagy. Methanol-grown cells were adapted to ethanol medium without nitrogen (SE-N). (D) Overexpression of Atg37 does not interfere with micropexophagy and macropexophagy. Cells were replica plated from methanol to glucose and ethanol plates, respectively. The residual activity of AOX was used to assess pexophagy.\n\nFigure 5: Figure 5. Atg37 binds and requires Atg30 for proper localization. (A) Atg37 coimmunoprecipitates with Atg30. Methanol-grown cells were adapted to glucose medium for 0.5 h to induce pexophagy. (B) Atg37ΔC (BD-37ΔC) interacts with Atg30 (AD-30) in Y2H. 3-AT, 10 mM 3-amino-1,2,4-triazole; AD, activation domain; BD, DNA binding domain. (C and D) Atg30 does not bridge the interaction between Pex3 and Atg37. Pex3 still coimmunoprecipitated with Atg37 in the absence of Atg30 under both peroxisome proliferation (C) and pexophagy (D) conditions. (E) Atg37 is not required for peroxisomal localization of Atg30. Cells were grown in methanol medium. Bar, 5 µm. (F) Atg30 is required for localization of Atg37 at the peroxisome cluster periphery. Arrows point to the peroxisome cluster with an accumulation of Atg37-GFP in the middle. Bar, 5 µm. (G) Quantitation of data in F presented as the mean + SD (error bars; n = 3; *, P < 0.001 vs. WT). (H) Atg37 accumulates in the middle of the peroxisome cluster in Δatg30 cells. Cells were grown in methanol medium. Z slices of peroxisome clusters are labeled 1–10. Bar, 2 µm."
      }
    ]
  },
  {
    "id": "PMC3926955_multi_2",
    "image": [
      "images/PMC3926955-f6.png",
      "images/PMC3926955-f7.png",
      "images/PMC3926955-f8.png",
      "images/PMC3926955-f9.png",
      "images/PMC3926955-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Atg37 binds Atg30 or palmitoyl-CoA to regulate phagophore formation during pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Atg30 requires Atg37 for recruitment of Atg11 to the pexophagic RPC. (A) Atg37 is required for pexophagy induced by the overexpression of Atg30. (B) Atg37 is necessary for the growth suppression in methanol medium caused by the overexpression of Atg30. The data shown are from a single representative experiment out of two repeats. (C) Atg11 does not coimmunoprecipitate with Atg30 in the absence of Atg37. Methanol-grown cells were adapted to the glucose medium without nitrogen for 0.5 h. The results are presented for two independent colonies of Δatg37. *, nonspecific band. (D) Atg37 is required for the Atg30-dependent localization of Atg11 to the proximity of peroxisomes. Methanol-grown cells were adapted to the glucose medium without nitrogen for 1 h. Arrows point to the accumulation of GFP-Atg11 near the peroxisomes in WT cells and on the vacuolar membrane in the mutant cells. Bar, 5 µm.\n\nFigure 7: Figure 7. Atg37 binds palmitoyl-CoA, which competes with Atg30 for binding to Atg37. (A) The acyl-CoA–binding domain of Atg37 faces the cytosol. The organelle pellet, 27P, was subjected to proteinase K and trypsin treatment. TX100, Triton X-100. Arrow points to the protease-protected C-terminal GFP fragment of Atg37-GFP. (B) Atg37ΔC binds specifically to palmitoyl-CoA. The amounts of [14C]palmitoyl-CoA and [14C]oleoyl-CoA bound by 0.07 µM His-Atg37ΔC are shown as the mean ± SD (error bars; n = 3; *, P < 0.0001 between corresponding concentrations). (C) The ACBS of Atg37ΔC is required to bind palmitoyl-CoA. The amounts of [14C]palmitoyl-CoA (9 µM) bound by 0.07 µM His-Atg37ΔC (WT or acbs mutant) or GST-Atg30 are presented as the mean of the disintegration rates ± SD (error bars; n = 3; *, P < 0.001 vs. WT His-Atg37ΔC). (D and E) The acbs mutant of Atg37ΔC can bind Pex3ΔN (D), but not Atg30 (E). (F) Palmitoyl-CoA inhibits the in vitro binding of Atg30 and Atg37ΔC. The 36 µM and 360 µM palmitoyl-CoA partially and completely inhibits the pull-down of 0.28 µM His-Atg37ΔC by 0.14 µM GST-Atg30, respectively. I, input; U, unbound; P, pull-down.\n\nFigure 8: Figure 8. ACBS/30BS is required for Atg37 localization and phagophore formation. (A) The ACBS/30BS is required for proper localization of Atg37. Arrows point to the peroxisome clusters with accumulation of Atg37-GFP in the middle. Bar, 5 µm. (B) Quantitation of data in A. The data shown are from a single representative experiment out of three repeats. (C and D) The ACBS/30BS of Atg37 is also necessary for phagophore formation (C) and pexophagy (D). Methanol-grown cells were adapted to glucose medium (C) or ethanol medium without nitrogen (D; SE-N). Arrows point to the MIPA. Bar, 5 µm.\n\nFigure 9: Figure 9. ATG37/ACBD5 is essential for pexophagy in human cells. (A and C) ACBD5 is needed for the delivery of peroxisomes to the lysosomes in HeLa (A) and Ntera-2 (C) cells expressing peroxisomally targeted mRFP-EGFP-SKL. Arrows point to the autolysosomes with acid-resistant mRFP fluorescence. Bars, 10 µm. (B) Quantitation of data in A. The percentage of cells with mRFP-labeled autolysosomes is shown as the mean + SD (error bars; n ≥ 50; *, P < 0.05 vs. control siRNA). (D) Quantitation of data in C. The ratio of mRFP and EGFP intensities per cell reflects the occurrence of pexophagy and is presented as the mean + SD (error bars; n ≥ 10 images; *, P < 0.05 vs. control siRNA).\n\nFigure 10: Figure 10. ATG37/ACBD5 is dispensable for aggrephagy and nonselective autophagy. (A) ACBD5 is not required for the autophagy of Htt-Q72 aggregates in HeLa cells. Cells expressed EGFP-Htt-Q72. Arrows point to the EGFP-Htt-Q72 aggregates. Bar, 10 µm. (B) Quantitation of data in A. The percentage of cells with EGFP-Htt-Q72 aggregates is shown as the mean + SD (error bars; n ≥ 50; *, P < 0.05 vs. siATG7). (C) ACBD5 does not affect SQSTM1 degradation and LC3 lipidation. Short, short exposure; Long, long exposure; β-Actin, loading control. (D) ACBD5 is dispensable for LC3-positive vesicle formation in HeLa cells expressing fluorescently tagged LC3. Cells were treated with 20 µM chloroquine in EBSS medium for 3 h and permeabilized with 0.025% digitonin to enrich for the vesicle-bound LC3 (indicated by arrows). Bar, 10 µm. (E) Quantitation of data in D. The percentage of cells with the vesicle-bound LC3 is shown as the mean + SD (error bars; n ≥ 75; *, P < 0.05 vs. siATG16L1)."
      }
    ]
  },
  {
    "id": "PMC3990157_multi",
    "image": [
      "images/PMC3990157-f1.png",
      "images/PMC3990157-f2.png",
      "images/PMC3990157-f3.png",
      "images/PMC3990157-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"X-linked adrenoleukodystrophy: very long-chain fatty acid metabolism is severely impaired in monocytes but not in lymphocytes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomal ABCD transporters are differentially expressed in the main immune cells. The mRNA levels of ABCD1, ABCD2 and ABCD3 were measured by qRT-PCR in the indicated immune cell types in (A) healthy controls and (B) AMN patients. Absolute copy numbers of mRNA were normalized to the reference gene hypoxanthine phosphoribosyltransferase (HPRT). Values represent means ± SEM. The number of individuals (n) is indicated below the graphs.\n\nFigure 2: Figure 2. There is neither compensatory feedback regulation of ABCD1 nor up-regulation of ABCD2 or ABCD3 mRNAs in immune cells of AMN patients. Statistical analysis of the fold change of ABCD1, ABCD2 and ABCD3 mRNA levels normalized to HPRT for AMN versus healthy control revealed no statistically significant differences. ABCD2 mRNA levels in monocytes and granulocytes were close to the detection limit in both, controls and AMN patients, therefore apparent differences in their expression levels are not considered relevant. F-test showed no significant difference for the population factor (AMN; healthy controls) in all investigated cell types with the exception of NKT cells. However, further analysis of NKT cells with Student's t-test did not confirm a significant difference.\n\nFigure 3: Figure 3. Fatty acid levels in immune cells of healthy controls and AMN patients. The concentrations of C26:0, C24:0, C22:0 and C16:0 were determined by GC–MS in the indicated immune cell types. The relative amounts of (A) C26:0, (B) C24:0, (C) C22:0 normalized to C16:0 are shown. The statistical analysis of the accumulation of VLCFA is described in (D) as fold change of FA levels for AMN versus healthy control. Values represent means ± SEM. For all panels, the number of individuals (n) is indicated in the inset of (D). Note the different scaling (Student's t-test, ***P < 0.001; **P < 0.01).\n\nFigure 4: Figure 4. β-Oxidation in immune cells of healthy controls and AMN patients. The activity of (A) peroxisomal C26:0 and (B) mitochondrial C16:0 β-oxidation were measured in monocytes (CD14+), B cells (CD19+) and T cells (CD3+). The rate of β-oxidation is expressed as fmol 14C-labeled acetate released/min/106 cells. Values represent means ± SEM. The number of individuals (n) is indicated below the graphs (Student's t-test, ***P < 0.001; n.s., not significant)."
      }
    ]
  },
  {
    "id": "PMC4003245_multi",
    "image": [
      "images/PMC4003245-f1.png",
      "images/PMC4003245-f2.png",
      "images/PMC4003245-f3.png",
      "images/PMC4003245-f4.png",
      "images/PMC4003245-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"PINK1 phosphorylates ubiquitin to activate Parkin E3 ubiquitin ligase activity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Mutation of conserved serine/threonine residues of Parkin does not completely inhibit Parkin translocation or activity. (A) YFP-Parkin is normally cytosolic (left panels), but upon mitochondrial damage (10 µM CCCP for 2.5 h), YFP-Parkin translocates to mitochondria and causes the ubiquitination proteins (right panels). Cells were stained for Tom20 (mitochondria, blue) and Ub (red). (B) ParkinΔUBL, as well as alanine mutants of Ser/Thr residues previously reported to be phosphorylated, were all capable of translocating to damaged mitochondria (10 µM CCCP for 2.5 h). Fewer cells expressing ParkinS65A displayed mitochondrial translocation than any other mutant (see Table S1). Cells were stained for Parkin (green) and Tom20 (mitochondria, red). For quantification and references of observed phosphorylation, see Table S1. (C) CCCP-treated (10 µM CCCP for 3 h) PINK1 KO cells expressing the indicated Parkin mutants showed that Parkin translocation is PINK1 dependent. (D) Phos-tag and SDS-PAGE gels revealed a shift of WT Parkin on Phos-tag gels after CCCP treatment (arrow), indicating it is phosphorylated (lane 2 vs. lane 3), and this phosphorylation was removed by phosphatase (CIP, lane 1). ParkinΔUBL, S65A, and S65E displayed no observable shift. (E) Parkin in vitro ubiquitination assay revealed that Parkin mutants are capable of ubiquitinating Mfn1 (bottom arrow). Cytosolic extracts from cells expressing the indicated Parkin mutants were incubated with mitochondria from cells not expressing Parkin (±CCCP). Ubiquitination of Mfn1 was observed (arrow + Ub and polyUb) only in the presence of mitochondria from CCCP-treated cells. Bars: (A–C) 10 µm.\n\nFigure 2: Figure 2. Proteomics search for PINK1 substrates revealed that PINK1 phosphorylates ubiquitin. (A) Workflow of the sample preparation for the PINK1 substrate search. (B) Identification of Ub in mitochondria from CCCP-treated PINK1 WT or KO cells. (C) Extracted ion chromatogram of the m/z 737.38 form of the Ub phosphopeptide TLSDYNIQKEpSTLHLVLR from endogenous PINK1 WT (red) and KO (blue) samples as prepared in A. (D) Extracted ion chromatograms of the Ub phosphopeptide TLSDYNIQKEpSTLHLVLR as observed with m/z 553.29, 737.38, and 1105.57 for the in vitro–phosphorylated His-Ub incubated with either CCCP-treated (red) or untreated (blue) mitochondria. Insets in C and D represent zoomed sections surrounding the phosphopeptide peak (asterisks). (E and F) Representative spectra for the Ub phosphopeptide TLSDYNIQKEpSTLHLVLR from in vitro–phosphorylated His-Ub from electron-transfer dissociation (panel E, ETD) and higher-energy collisional dissociation (panel F, HCD) fragmentation methods. ETD and HCD spectra obtained for this peptide from PINK1 WT mitochondria samples prepared as in A were almost identical to the spectra shown in E and F. (G) Alignment of Ub and the UBL domain of Parkin with the conserved S65 (bold) and unique Ub peptide observed by MS (red). Bold-type pS, phospho-Ser.\n\nFigure 3: Figure 3. Phos-tag gels and 32P radiolabeling of in vitro phosphorylation of ubiquitin by PINK1. (A) Recombinant MBP-TcPINK1 WT, but not MBP-TcPINK1 KD, causes HA-Ub to shift on Phos-tag gels (top, lanes 7–10, phospho-Ub) but not SDS-PAGE (bottom). This shifted band is removed by phosphatase treatment (+CIP, lane 11). MBP-TcPINK1 WT is also shifted on Phos-tag gels, indicating auto-phosphorylation. (B) Radiolabeled phosphate was incorporated into recombinant Ub during incubation with γ-[32P]ATP and WT (but not KD) MBP-TcPINK1.\n\nFigure 4: Figure 4. Phospho-ubiquitin activates Parkin. (A) YFP-ParkinWT translocates to damaged mitochondria in cells expressing high levels of WT HA-Ub (red, HA immunostaining, 10 µM CCCP for 1 h). Cells expressing high levels of HA-UbS65A have impaired YFP-Parkin translocation. Bars, 10 µm. (B) Quantification of A shown as averages ± SD from n = 3 experiments, 100 cells/experiment. (C) Immunoprecipitation of HA-Ub WT, S65D, S65E, and S65A from cells stably expressing YFP-Parkin revealed a stronger interaction between activated YFP-Parkin and HA-UbS65D and HA-UbS65E than WT or S65A. In the absence of HA-Ub, some YFP-Parkin bound to the HA IP beads (†), and this was consistent in all immunoprecipitations. The higher molecular weight form of YFP-Parkin was found only in the HA-Ub and was bound to a much larger extent to the HA-UbS65D and S65E. (D) Quantification of C shown as averages ± SD from n = 3 experiments. (E) ParkinC431S forms an oxyester-bound Ub intermediate upon activation with CCCP, which is cleaved by NaOH (lanes 1 and 2). The oxyester was not detected in cells without CCCP, with overexpressing HA-UbWT (lane 9), but was detected with overexpression of HA-UbS65D for both YFP-ParkinC431S and YFP-ParkinS65A/C431S (lanes 13 and 15). (F and G) HA-Ub was in vitro phosphorylated by (F) incubation with mitochondria from control or CCCP treated cells or (G) recombinant MBP-TcPINK1 WT or KD using the same protocol as used for the Phos-tag gels in Fig. 3 A. This HA-Ub was then added to an in vitro reaction (at 4 ng and 20 ng) with recombinant Parkin, E1, E2, untreated Ub (to a total of 1 µg), and ATP. In both cases the addition of phospho-Ub to the reaction caused an increase in Parkin activity (Ubn). (H) To ensure activation in F was due to S65 phospho-Ub, the experiment was repeated with WT, S65A, and no Ub (−). Activation was only observed with WT His-Ub (top). MBP-TcPINK1 was removed from the His-Ub phosphorylation reaction by binding to amylose beads (bottom). The “†” symbol in G and H represents a nonspecific band. *, P < 0.01; ***, P < 0.001.\n\nFigure 5: Figure 5. A model of PINK1 phosphorylation of ubiquitin to activate Parkin and the conservation of S65 among UBL proteins and domains. (A) A model of the cyclical activation of Parkin by PINK1 phosphorylation and amplification of the cascade via PINK1 phosphorylation of ubiquitin. (B) Alignment of the ubiquitin-like domains of several small ubiquitin-like proteins shows several conserved serines at the sites homologous to ubiquitinS65. (C) Alignment of other UBL domain–containing proteins with Parkin’s UBL revealed that other proteins contain a homologous serine or threonine at the S65 position. Arrow indicates the position of Ub S65 in UBL proteins (B) and UBL domain–containing proteins (C)."
      }
    ]
  },
  {
    "id": "PMC4015298_multi",
    "image": [
      "images/PMC4015298-f1.png",
      "images/PMC4015298-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Next generation sequencing with copy number variant detection expands the phenotypic spectrum of HSD17B4-deficiency\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MRI at age 35 demonstrating cerebellar volume loss with preservation of cerebral hemispheres. A-D) FLAIR axial; E-H) T2 axial; I-J) Coronal T1; K-L) Sagittal T1.\n\nFigure 2: Figure 2. Compound heterozygous variants in HSD17B4. A) Schematic of HSD17B4 (NP_000405) with multiple sequence alignment. SCP2, sterol carrier protein 2; #, cleavage site. B) Pedigree denoting genotypes. C) Normalized depth of coverage at each exon (“x”); lines represent smoothed data from proband (red) and controls (black). Below, reads showing deletion-spanning mate pairs. D) Sanger trace of c.587C > T. E) DNA gel indicating genotypes at deletion site, schematic of primers, and Sanger trace across deletion in proband. Abbreviations: wt, wildtype; nd, no data; del, deletion; norm, normalized."
      }
    ]
  },
  {
    "id": "PMC4021871_multi",
    "image": [
      "images/PMC4021871-f1.png",
      "images/PMC4021871-f2.png",
      "images/PMC4021871-f3.png",
      "images/PMC4021871-f4.png",
      "images/PMC4021871-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Role of the Transmembrane RING Finger Proteins in Cellular and Organelle Function\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic representations of the ubiquitination reaction and the RNF domain structures. (A) The biochemical steps in ubiquitination are illustrated. Ub is activated at its C-terminal glycine residue (Gly76) in an ATP-dependent manner by E1. In an ATP-hydrolyzing reaction, a Ub adenylate intermediate is formed, followed by the binding of Ub to a specific cysteine residue of E1. Ub is then transferred to an active site cysteine residue of E2, preserving the high energy thioester bond. The substrate is recognized by E3, which also recruits the E2–Ub complex. Finally, Ub is linked by its C-terminus in an isopeptide linkage to an ε-amino group of lysine residues on the substrate protein. (B) A simple comparison of the cross-brace arrangements of the RING-H2, RING-HC and RING-CH finger motifs. C and H indicate the conserved Zn2+-coordinating cysteine and histidine residues.\n\nFigure 2: Figure 2. Phylogenetic analysis of putative human transmembrane RNF proteins. The tree was constructed by the neighbor-joining method with ClustalW [22] and MEGA4 [23] using 5,000 bootstrap resamplings. The scale bar indicates 0.2 amino acid substitutions per each amino acid position. Members of the TRIM, PA-TM-RING, MARCH and RBR families are indicated in green, red, blue and purple fonts, respectively.\n\nFigure 3: Figure 3. Comparison of the domain structures of putative human transmembrane RNF proteins. Information on the domain structure of each RNF protein was obtained from the ENSEMBL (http://www.ensembl.org [28]) and NCBI (http://www.ncbi.nlm.nih.gov [29]) databases. Abbreviations: PA, protease-associated domain; TM, putative transmembrane domain; CUE, coupling of Ub conjugation to ER degradation; SAM, sterile alpha motif; DED, death effecter domain.\n\nFigure 4: Figure 4. Schematic diagram of the organization of organelles and the intracellular transport pathways. The major membrane-bound organelles and the main routes of protein transport are indicated, with the secretory pathway in green, the endocytic degradation pathway in black, the recycling pathway in red and the retrograde pathway in blue.\n\nFigure 5: Figure 5. Proposed roles of the transmembrane RNF proteins in mitochondrial dynamics and mitophagy. MARCH5 may regulate mitochondrial fusion and fission by ubiquitinating MFN1 and DRP1. MAPL SUMO ligase stabilizes DRP1 and therefore promotes mitochondrial fission. RNF185-mediated ubiquitination triggers mitophagy."
      }
    ]
  },
  {
    "id": "PMC4047095_multi",
    "image": [
      "images/PMC4047095-f1.png",
      "images/PMC4047095-f2.png",
      "images/PMC4047095-f3.png",
      "images/PMC4047095-f4.png",
      "images/PMC4047095-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"C3HC4-Type RING Finger Protein NbZFP1 Is Involved in Growth and Fruit Development in Nicotiana benthamiana\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. We selected twenty-five typical C3HC4-type RING finger genes with high similarity from different species, and we analyzed the similarity of their RING finger domains and full-length sequences with NbZFP1. Phylogenetic trees were generated by the maximum likelihood (ML) method using MEGA4. Bootstrap values from 1000 replicates are indicated at each branch. (a) A maximum likelihood (ML) tree of NbZFP1 and genes from other species was constructed based on RING finger domain sequences. (b) A maximum likelihood (ML) tree of NbZFP1 and genes from other species was constructed based on full-length nucleotide sequences.\n\nFigure 2: Figure 2. The NbZFP1 protein was expressed in E. coli and purified with affinity chromatography (GSTrap™ HP column) and ion exchange chromatography (HiTrap Q HP column). The purified protein showed a single band on SDS-PAGE stained with Coomassie Brilliant Blue R-250. (a) Ion exchange chromatography of a concentrated solution loaded onto a HiTrap Q HP column. (b) SDS-PAGE analysis of the recombinant protein. Lane 1, GST protein after affinity chromatography purification. Lane 2, protein peak II as designated in (a). Lane 3, protein marker.\n\nFigure 3: Figure 3. Laser-scanning confocal micrographs showing the fluorescence of leaf cells following infiltration with Agrobacteria carrying pGDG, pGDG-Rac1, or pGDG-NbZFP1 plasmids expressing GFP, Rac1-GFP, and NbZFP1-GFP proteins, respectively. Scale bar = 10 µm. (a) and (b) GFP expressed from pGDG; (c) and (d) GFP expressed from pGDG-Rac1; (e), (f), (g), and (h) Fluorescence expressed from pGDG-NbZFP1. (a), (c), (e), and (g) show the green channel; (b), (d), and (f) show an overlay of the bright-field and green channels; (h) shows an overlay of the bright-field, green, and red channels.\n\nFigure 4: Figure 4. (a) Effect of VIGS on NbZFP1 (in this graph, NbA) transcription in N. benthamiana. TRV: The expression level of NbZFP1 in plants infected with TRV alone; TRV-A1: The expression level of NbZFP1 in plants infected with TRV-A1 (A1 is the C3HC4-type RING finger domain gene NbZFP1); TRV-A2: The expression level of NbZFP1 in plants infected with TRV-A2 (A2 is NbZFP1 lacking the C3HC4-type RING finger domain). (b) The phenotype of VIGS-silenced NbZFP1 and wild type strains. b1, NbZFP1-silenced plant at 20 days after the four-leaf stage; b2, wild type plant at 20 days after the four-leaf stage; b3, NbZFP1-silenced plant at 40 days after the four-leaf stage; b4, wild type plant at 40 days after the four-leaf stage. (c) The fruit phenotype of NbZFP1-silenced plants compared with controls. c1, c2, and c3: The fruit phenotype of non-silenced control plants. c4, c5, and c6: The fruit phenotype of NbZFP1-silenced plants.\n\nFigure 5: Figure 5. Fresh leaves (100 mg) from T1 plants were collected, and genomic DNA was extracted. A specific fragment of the gus gene (approximately 1000 bp in length) was amplified to identify the transgenic lines. (a) PCR identification of transgenic tobacco plants. M, DL8000 marker; 1, positive control; 2–10, transgenic tobacco lines. (b) Southern blot analysis of transgenic tobacco plants. 2, Transgenic line 2; 5, Transgenic line 5; 6, Transgenic line 6."
      }
    ]
  },
  {
    "id": "PMC4117577_multi",
    "image": [
      "images/PMC4117577-f1.png",
      "images/PMC4117577-f2.png",
      "images/PMC4117577-f3.png",
      "images/PMC4117577-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Evaluation of Retinoids for Induction of the Redundant Gene ABCD2 as an Alternative Treatment Option in X-Linked Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Activation and inhibition of the ABCD2 gene are indicated. Nucleotide positions relative to the translational start site are indicated below the sequence. SREBP = sterol regulatory element (SRE)-binding proteins; LXR = liver X receptor; TR = thyroid hormone receptor; RXR = retinoid X receptor; RAR = retinoic acid receptor; TCF-4 = T-cell factor 4; Sp-1/3 = specificity protein 1/3; DR = direct repeat spaced by 1/2/4 or 5 nucleotides; TBE 1/3 = TCF binding element; 22R-HC = 22(R)-hydroxycholesterol; 9/13CRA = 9/13-cis-retinoic acid; T3 = triiodothyronine; 4-PBA = 4-phenylbutyrate; SAHA = suberoylanilide hydroxamic acid.\n\nFigure 2: Figure 2. The mRNA levels of ABCD2 and the reference gene HPRT were determined by qRT-PCR after 24-h-treatment with the indicated concentrations of (A) 9CRA, (B) 13CRA, (C) ATRA and (D) Adapalene. The receptor-selectivity of each ligand is indicated below the panels. (E) Dose-response curve for 13CRA. Values represent means ± SEM of treated cells as fold-induction relative to solvent (DMSO)-treated cells. Each column represents three independent treatments. qRT-PCR analyses were performed in 2–3 technical replicates. ** p<0.01; *** p<0.001; ns, not significant.\n\nFigure 3: Figure 3. ABCD1, ABCD2, ABCD3 and HPRT mRNA levels were measured by qRT-PCR in (A) monocytes (CD14+) and (B) B cells (CD19+) of healthy controls and acne patients before and after oral treatment with 13CRA for a period of about 3 months. HPRT was used for normalization of the absolute mRNA copy numbers. Values represent means ± SEM; qRT-PCR analyses were performed in technical duplicates. The number of individuals (n) is indicated in the inserts.\n\nFigure 4: Figure 4. (A) ABCD1, ABCD2, ABCD3, and, as a reference for normalization, HPRT mRNA levels were detected by qRT-PCR after treatment of in vitro differentiated macrophages with 2.5, 5 and 7 µM of 13CRA for 24 h. The results are shown as fold-induction of ABCD1-3/HPRT relative to solvent (DMSO)-treated cells. (B) As a control for the differentiation of monocytes into macrophages, LXRα expression was quantified and depicted as copy numbers of LXRα mRNA normalized to HPRT mRNA levels. (C) ABCD2 mRNA levels were similar in monocytes and M-CSF-differentiated macrophages. Values represent means ± SEM of three independent treatments. qRT-PCR analyses were performed in two technical replicates. * p<0.05; ** p<0.01; *** p<0.001; ns, not significant."
      }
    ]
  },
  {
    "id": "PMC4148619_multi",
    "image": [
      "images/PMC4148619-f1.png",
      "images/PMC4148619-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Evolving models for peroxisome biogenesis☆\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Model of peroxisomal matrix protein import. (I) Proteins harboring a peroxisomal targeting signal of type 1 (PTS1) are recognized and bound by the import receptor Pex5 in the cytosol. (II) The cargo-loaded receptor is directed to the peroxisomal membrane and binds to the docking complex (Pex13/Pex14/Pex17). (III) The import receptor assembles with Pex14 to form a transient pore and (IV) cargo proteins are transported into the peroxisomal matrix in an unknown manner. Cargo release might involve the function of Pex8 or Pex14. (V) The import receptor is monoubiquitinated at a conserved cysteine by the E2-enzyme complex Pex4/Pex22 in tandem with E3-ligases of the RING-complex (Pex2, Pex10, Pex12). (VI) The ubiquitinated receptor is released from the peroxisomal membrane in an ATP-dependent manner by the AAA-peroxins Pex1 and Pex6, which are anchored to the peroxisomal membrane via Pex15. As the last step of the cycle, the ubiquitin moiety is removed and the receptor enters a new round of import. The designation is based on the yeast nomenclature.\n\nFigure 2: Figure 2. Schematic representation of models for peroxisome multiplication. The vesicle fusion model proposes that all PMPs enter the ER, where they segregate and exit the ER in distinct vesicles: vesicles containing the docking complex proteins Pex13,14 (blue) fuse with vesicles containing the RING-finger complex proteins Pex2,10,12 (green) forming a preperoxisomal membrane structure (black). As this membrane structure now contains a complete importomer, matrix protein import commences. Subsequent fission results in peroxisomes of final size and membrane protein composition (red). The growth and division model proposes that peroxisomes (red) are derived from existing peroxisomes by fission. A small subset of PMPs (Class 2) insert into the ER and exit it in a transport vesicle (blue) that fuses with existing peroxisomes, where it provides the docking site for Pex19-mediated import of Class 1 PMPs (Class 1). Since Pex3 can only be detected in peroxisomes in wild type cells it cannot be excluded that it inserts directly into peroxisomes. Reintroduction of Peroxisomes. In the absence of pre-existing peroxisomes, the ER-derived Pex3-containing vesicle matures slowly into a peroxisome, with Pex3 again providing a docking site for Pex19/Class I PMPs complexes; this vesicle is thus slowly converted into a membrane structure containing all PMPs (black), finally becoming import-competent for matrix proteins (red). These newly formed peroxisomes will further multiply by growth and division. Whether Pex13 and Pex14 traffic via the ER or insert directly into a membrane structure distinct from the ER is not established."
      }
    ]
  },
  {
    "id": "PMC4177892_multi",
    "image": [
      "images/PMC4177892-f1.png",
      "images/PMC4177892-f2.png",
      "images/PMC4177892-f3.png",
      "images/PMC4177892-f4.png",
      "images/PMC4177892-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Abcd2 Is a Strong Modifier of the Metabolic Impairments in Peritoneal Macrophages of Abcd1-Deficient Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Structure of the 5′ region of the Abcd2 gene, the targeting construct and the disrupted gene. Exons (Ex) 1–3 are depicted as boxes with the protein coding region in gray. After homologous recombination, 1.24 kb of the Abcd2 gene, including the transcription and translation start sites and most of exon 1, is replaced by the neomycin resistance gene cassette (Neo) of the targeting construct. Positions of the PCR primers (P1, P2) and the Southern blot probe (****) used in genotyping to detect homologous recombination are indicated. Restriction sites used for cloning or analysis are marked: H, HindIII; N, NdeI; Not, NotI; S, ScaI; Sp, SphI and X, XhoI. (B) Southern blot analysis of ScaI-digested DNA from Abcd2 −/−, Abcd2 +/+ and Abcd2 +/− mice. Chemiluminescent detection of a digoxygenin-labelled probe from the 5′ flanking DNA verified homologous recombination based on deletion of a ScaI-site in exon 1 of Abcd2 resulting in 3.9-kb and 4.4-kb fragments from the wild-type (WT) and knock-out (KO) alleles, respectively. (C) Northern blot analysis of mRNA from brain and skeletal muscle of adult Abcd2 −/− and Abcd2 +/+ mice. A 32P-labelled Abcd2 cDNA probe hybridized to the major 4.2 kb Abcd2 mRNA and minor (5.5 and 2.8 kb) variants in both tissues of wild-type mice, but not in Abcd2 −/− mice. As a loading control, the blot was re-probed with β-actin cDNA, which in skeletal muscle detects a shorter, more abundant mRNA than in brain. (D) Reverse transcription-coupled PCR analysis of Abcd2 mRNA expression in primary peritoneal macrophages from two Abcd2 +/+ and two Abcd2 −/− mice. Abcd2-specific primers amplified the expected 1,051-bp product in Abcd2 +/+ but not in Abcd2 −/− macrophages. As a positive control, amplification of Iba1 cDNA (310-bp fragment) was confirmed in all samples.\n\nFigure 2: Figure 2. (A) The Abcd1 and Abcd2 mRNA copy numbers in C57BL/6J wild-type MPMΦ were determined by qRT-PCR. (B) Comparison of Abcd2 mRNA levels in wild-type (WT) and Abcd1-deficient (KO) MPMΦ. The numbers of samples (n) are indicated below the graphs. The graphs indicate mean values ± SD after normalization to the level of Hprt mRNA in each sample; n.s., no statistically significant difference.\n\nFigure 3: Figure 3. The concentrations of the VLCFA species C26∶0, C24∶0 and C22∶0 and the LCFA C16∶0 were determined by GC-MS. The relative amounts of fatty acids, expressed as ratios: (A) C26∶0/C22∶0; (B) C26∶0/C16∶0; (C) C24∶0/C22∶0 and (D), C22∶0/C16∶0 were analyzed in mouse peritoneal macrophages of wild-type (WT), Abcd1-deficient (Abcd1 KO), Abcd2-deficient (Abcd2 KO) and Abcd1/Abcd2 double-deficient (DOKO) mice after 5 days in culture (n = 3). The graphs indicate geometric means ± SD (asymmetrical). Statistically significant differences are indicated: * p<0.05, ** p<0.01, *** p<0.001; n.s., no statistically significant difference.\n\nFigure 4: Figure 4. The Elovl1 mRNA copy numbers were determined by qRT-PCR in total RNA from mouse peritoneal macrophages of wild-type (WT), Abcd1-deficient (Abcd1 KO), Abcd2-deficient (Abcd2 KO) and Abcd1/Abcd2 double-deficient (DOKO) mice. The graphs indicate mean values ± SD after normalization to the level of Hprt mRNA in each sample (n = 3).\n\nFigure 5: Figure 5. The rates of β-oxidation for radiolabelled C26∶0 and C16∶0 fatty acid substrates were measured in wild-type (WT), Abcd1-deficient (Abcd1 KO), Abcd2-deficient (Abcd2 KO) and Abcd1/Abcd2 double-deficient (DOKO) cell preparations. The results are shown as mean values ± SD of the ratio between C26∶0 and C16∶0. The numbers of samples (n) are indicated below the graphs. Statistically significant differences are indicated; *** p<0.001."
      }
    ]
  },
  {
    "id": "PMC4198684_multi",
    "image": [
      "images/PMC4198684-f1.png",
      "images/PMC4198684-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The first patient with a pure 1p36 microtriplication associated with severe clinical phenotypes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clinical photographs of the patient with 1p36 triplication. (A) Front view of the face. (B) Lateral view of the face. The major facial phenotype included strabismus, hypertelorism, low hairline, ear malformations, broad nasal bridge, wide mouth, thick lips and prominent incisors.\n\nFigure 2: Figure 2. Copy number variants analysis of the patient: (A) “Normal” high-resolution karyotype. (B) A SNP microarray analysis detected an approximately 5.28-Mb triplication in the short arm of chromosome 1. (C) MLPA result using SALSA kit P147-B1 of MRC Holland, showing a triplication included all probes from ISG15 up to AJAP1(RPH are approximately 2.0). (D) FISH results of the patient. Two red signals with the similar strength were presented in the long arm of chromosome 1 by the control probe TelVysion 1q. However, by the testing probe TelVysion 1p, the green hybridization signal in one 1p was obviously stronger than that in the other 1p, and in interphase nucleus, four green signals could be seen. (E) FISH image of the parents of the patient showed normal appearance, indicating that the 1p partial triplication is de novo (the FISH image of mother didn’t shown). (F) Quantitative PCR analysis showed the patient had 3 to 6 times as higher expression levels than control for the four genes B3GALT6, MIB2, PEX10, PANK4 in the blood."
      }
    ]
  },
  {
    "id": "PMC4207609_multi",
    "image": [
      "images/PMC4207609-f1.png",
      "images/PMC4207609-f2.png",
      "images/PMC4207609-f3.png",
      "images/PMC4207609-f4.png",
      "images/PMC4207609-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ribosomal Readthrough at a Short UGA Stop Codon Context Triggers Dual Localization of Metabolic Enzymes in Fungi and Animals\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) 3′ sequence of the U. maydis tpi1 gene and its translation. PTS1 is highlighted. (B) Tpi1 with indicated C-terminal extensions was fused to GFP and analyzed by Western blot. (C) A reporter construct consisting of mCherry and gfp interrupted by a stop codon was expressed. Stop codon readthrough was analyzed by detection of GFP by Western blot. The termination codon TGA was replaced by TAA or TAG and tested in combination with the downstream sequence CTA for ribosomal readthrough. (D) Nucleotides downstream of TGA were exchanged as indicated and tested as described in (C) for stop codon readthrough. (E) Tpi1 including TGA CTA was fused to GFP. Cells were incubated with different amounts of G418 and analyzed for readthrough by Western blotting. (F) TGA CTA was inserted between mCherry and gfp of the reporter construct. Cells were incubated with different amounts of G418 and analyzed for readthrough by Western blotting. Filled arrows indicate readthrough products while blank arrows indicate products terminated at the first stop codon.\n\nFigure 2: Figure 2. (A) 3′ sequences of U. maydis genes art1 and rpe1 together with their derived polypeptide sequence. PTS1 and readthrough elements are highlighted. All accession numbers are from MIPS Ustilago maydis DataBase (MUMDB). (B) The PTS1 motifs of Art1 and Rpe1 were fused to GFP and co-expressed with the peroxisomal marker mCherry-SKL in U. maydis cells. BF indicates bright field. Scale bars represent 10 µm. (C) Conservation of readthrough derived peroxisomal isoforms of Art1 and Rpe1 orthologs in fungi. Predictions were carried out with a PTS1 predictor [66]. In some organisms the PTS1 is part of the original open reading frame indicated by no readthr. and …NNN*.\n\nFigure 3: Figure 3. (A) A reporter construct consisting of gfp and myc interrupted by a stop codon was expressed in HeLa cells. Stop codon readthrough was analyzed by detection of the myc-epitope by Western blot. The termination codon TGA was replaced by TAA or TAG and tested in combination with the downstream sequence CTA for ribosomal readthrough. (B) Nucleotides downstream of TGA were exchanged as indicated and tested as described in (A) for stop codon readthrough.\n\nFigure 4: Figure 4. (A) 3′ sequences of the human MDH1 and its translation. The readthrough element and the predicted PTS1 motifs are highlighted. Enzymatic reactions catalyzed by MDH1 is indicated. NCBI Gene IDs is shown. (B) Human LDHB and its translation as in (A). (C) Phylogenetic conservation of readthrough derived MDH1 and LDHB peroxisomal isoforms is indicated by colouring. PTS1 predictions were carried out with PTS1 predictor [66]. PTS1 motifs of MDH1 homologs encoded by the original open reading frame are indicated by no readthr. and …NNN*.\n\nFigure 5: Figure 5. (A) Western blot analysis of LDHB derivatives fused to HA and Myc. (B) The stop codon of the LDHB construct described in (A) was exchanged by TAA and TAG. (C) Western Blot analysis of LDHB fused to HA and Myc in dependence on Gentamicin (+). (D) GFP-LDHB and GFP-LDHBΔPTS1 were co-expressed with the peroxisomal marker mCherry-SKL. (E) LDHB*-GFP-PTS1 was co-expressed with mCherry-SKL. (F) MDH1*-GFP-PTS1 was co-expressed with mCherry-SKL. Asterisks mark the positions of stop codons. PTS1 indicates the peroxisomal targeting signal downstream of the conventional stop codon of LDHB and MDH1, respectively. Intracellular localization was followed by fluorescence microscopy before and after repeated photobleaching. Magnified areas are indicated and shown below the micrographs. Scale bars represent 10 µm."
      }
    ]
  },
  {
    "id": "PMC4228450_multi",
    "image": [
      "images/PMC4228450-f1.png",
      "images/PMC4228450-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The neurology of rhizomelic chondrodysplasia punctata\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A patient with RCDP type 1. Anterior aspect of a patient with the severe phenotype at age 4 years. The clinical phenotype of RCDP is characterized by facial dysmorphic features, bilateral rhizomelia and arthrogenic contractures. Growth is severely impaired. Patients achieve hardly any developmental milestones.\n\nFigure 2: Figure 2. Change in EEG pattern in a patient with the severe phenotype of RCDP. EEG recordings of patient 3. Normal for age at 10 months. Development of background pattern at 3 years. Deterioration of background pattern and runs of spike wave complexes in the frontal regions at 8 years."
      }
    ]
  },
  {
    "id": "PMC4322494_multi",
    "image": [
      "images/PMC4322494-f1.png",
      "images/PMC4322494-f2.png",
      "images/PMC4322494-f3.png",
      "images/PMC4322494-f4.png",
      "images/PMC4322494-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Approach to Neurometabolic Diseases from a Pediatric Neurological Point of View\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Abnormally high signal intensity in white matter regions around the anterior and posterior horns of both lateral ventricles and brain atrophy in phenylketonuria\n\nFigure 2: Figure 2. Single proton MR spectroscopy shows the presence of branched-chain amino acids resonating at 0.9–1.0 ppm\n\nFigure 3: Figure 3. Abnormal Signal in Bilateral Basal Ganglia and Brain Atrophy in an MRI from a 4-year-old boy with propionic-acidemia\n\nFigure 4: Figure 4. Severe brain atrophy in a patient with biotinidase deficiency\n\nFigure 5: Figure 5. MRS in a patient with Canavan disease shows a markedly increased level of N-acetylaspartic acid (NAA)"
      }
    ]
  },
  {
    "id": "PMC4322494_multi_2",
    "image": [
      "images/PMC4322494-f6.png",
      "images/PMC4322494-f7.png",
      "images/PMC4322494-f8.png",
      "images/PMC4322494-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Approach to Neurometabolic Diseases from a Pediatric Neurological Point of View\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Cranial MRI and MRS in a patient with glutaric aciduria type I and Axial MRI shows an abnormal signal in bilateral basal ganglia with bilateral prominent sylvian fissures\n\nFigure 7: Figure 7. Burst suppression patterns in a 4.5-month-old infant with early myoclonic encephalopathy\n\nFigure 8: Figure 8. Hypsarrhythmia patterns with mixed asynchronous slow waves and spike waves in an 8.5-month-old infant with West syndrome\n\nFigure 9: Figure 9. Slow spike waves with fast spike components in a 13-year-old boy with Unverricht-Lundborg Syndrome"
      }
    ]
  },
  {
    "id": "PMC4378301_multi",
    "image": [
      "images/PMC4378301-f1.png",
      "images/PMC4378301-f2.png",
      "images/PMC4378301-f3.png",
      "images/PMC4378301-f4.png",
      "images/PMC4378301-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Deletion of mouse FXR gene disturbs multiple neurotransmitter systems and alters neurobehavior\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Experimental paradigm of the behavioral tests.\n\nFigure 2: Figure 2. FXR KO mice showed less depressive-like behavior. In comparison with wild-type controls, FXR KO mice did not have reduced immobility time in the FST (B), but exhibited significantly decreased immobility time in the TST (A). N = 12/group; ** p < 0.01.\n\nFigure 3: Figure 3. FXR KO mice had low levels of anxiety-related behavior. In comparison with wild-type controls, FXR KO mice had high ratio of central distance/total distance in the OFT (A). Moreover, the KO mice had a greater tendency to explore (B) and to stay in the open arm in the EPMT (C). N = 12/group; *p < 0.05; **p < 0.01.\n\nFigure 4: Figure 4. FXR KO impaired cognitive ability of the mice. In comparison with wild-type controls, FXR KO mice displayed decreased latency (A) but increased number of errors (B) in PAT. N = 12/group; * p < 0.05.\n\nFigure 5: Figure 5. FXR KO altered motor performance of the mice. In comparison with wild-type controls, FXR KO mice fell from the rod more often in the RRT (A) but seemed to be hyperactive in the OFT (B). N = 12/group; ** p < 0.01."
      }
    ]
  },
  {
    "id": "PMC4378301_multi_2",
    "image": [
      "images/PMC4378301-f6.png",
      "images/PMC4378301-f7.png",
      "images/PMC4378301-f8.png",
      "images/PMC4378301-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Deletion of mouse FXR gene disturbs multiple neurotransmitter systems and alters neurobehavior\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. FXR KO down-regulated hippocampal GAD65 of the mice. (A) Western blotting analysis of GAD65, GAT1, GABAARα5, and GABAARβ2/3; (B) Gray intensity comparison. N = 8/group; * p < 0.05.\n\nFigure 7: Figure 7. FXR KO increased cerebellar GAT1. (A) Western blotting analysis of GAD65, GAT1, GABAARα5, GABAARβ2/3, 5-HT1A, and SLC6A2. (B) Gray intensity comparison. N = 8/group; +p < 0.1.\n\nFigure 8: Figure 8. FXR KO on BAs in serum. In comparison with wild-type controls, FXR KO mice showed higher concentrations of THDCA, TCA, Tω MCA, and TαMCA in T-BAs in serum (A); higher concentrations of GCA, HDCA, and DCA in U-BAs in serum (B). N = 16/group; * p < 0.05; ** p < 0.01.\n\nFigure 9: Figure 9. FXR KO on BAs in brain. In comparison with wild-type controls, FXR KO mice displayed higher concentrations of TCA, TCDCA, Tω MCA, and DCA (A) but lower concentrations of TβMCA and LCA in brain (B). N = 7–10/group; * p < 0.05; +p < 0.1."
      }
    ]
  },
  {
    "id": "PMC4426667_multi",
    "image": [
      "images/PMC4426667-f1.png",
      "images/PMC4426667-f2.png",
      "images/PMC4426667-f2-2.png",
      "images/PMC4426667-f2-3.png",
      "images/PMC4426667-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin ligase TRIM23 regulates adipocyte differentiation via stabilization of the adipogenic activator PPARγ\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Real-time PCR analysis of mRNA expression of Trim23 during 3T3-L1 differentiation. Total RNA was isolated from 3T3-L1 cells on the indicated days. Trim23 mRNA was normalized to that of Gtf2b. (B) Immunoblot analysis of TRIM23 and PPARγ protein during 3T3-L1 cell differentiation. (C) Real-time PCR analysis of mRNA expression of Trim23 in mouse adipose tissue. Trim23 mRNA was normalized to that of Gtf2b. (D) Subcellular localization of TRIM23. Nuclear extracts and cytoplasmic S100 fraction were prepared from 3T3-L1 cells, and immunoblot analysis of TRIM23, HDAC1, and GAPDH was performed. DOI: http://dx.doi.org/10.7554/eLife.05615.003\n\nFigure 2: Figure 2. (A) Immunoblot analysis of TRIM23 knockdown before induction of adipogenesis is shown. (B) Cells were stained with Oil Red O to visualize the accumulation of lipid droplets at day 6. (C) The amounts of intracellular triacylglyceride (TG) were quantified at day 6. (D) RNA levels of Gtf2b and Fabp4 were determined by real-time PCR at days 0, 2, 4 and 6. Expression level of each gene was normalized to that of the Gtf2b. (E) Schematic representation of the Fabp4 gene. The locations of the sequences amplified in the ChIP are shown at the bottom in base pairs relative to the Fabp4 transcriptional start site. (F, G and H) ChIP analysis of PPARγ (F), MED1 (G), and Pol II (H) on the Fabp4 gene during adipocyte differentiation. Ct values of each ChIP were normalized to that of input. All data represent means ± s.d. from three independent experiments. The p values for the indicated comparisons were determined by Student's t test (*, p < 0.05; **, p < 0.01). DOI: http://dx.doi.org/10.7554/eLife.05615.004\n\nFigure 2: Figure 2. mRNA levels of Trim23, Cidec, Klf15, Adipoq and Retn were determined by real-time PCR at days 0, 2, 4, and 6. Expression level of each gene was normalized to the level of Gtf2b. DOI: http://dx.doi.org/10.7554/eLife.05615.005\n\nFigure 2: Figure 2. Short interfering RNAs targeting TRIM23 (siTRIM23) and a non-targeting control siRNA (siControl) were introduced into human primary visceral preadipocytes, and the preadipocytes were differentiated to mature adipocytes. Adipocytes were stained with Oil Red O to visualize the accumulation of lipid droplets at day 10. DOI: http://dx.doi.org/10.7554/eLife.05615.006\n\nFigure 3: Figure 3. RNA levels of Pparg, Cebpa, Cebpb and Cebpd were determined by real-time PCR at days 0, 2, 4 and 6. Expression level of each gene was normalized to that of the Gtf2b. The data represent means ± s.d. from three independent experiments. The p values for the indicated comparisons were determined using Student's t-test (*, p < 0.05; **, p < 0.01). DOI: http://dx.doi.org/10.7554/eLife.05615.007"
      }
    ]
  },
  {
    "id": "PMC4426667_multi_2",
    "image": [
      "images/PMC4426667-f4.png",
      "images/PMC4426667-f5.png",
      "images/PMC4426667-f5-2.png",
      "images/PMC4426667-f6.png",
      "images/PMC4426667-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin ligase TRIM23 regulates adipocyte differentiation via stabilization of the adipogenic activator PPARγ\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 4: Figure 4. (A) RNA levels of Trim23, Cebpb and Cebpd were determined by real-time PCR at 0, 6, 12, 24 and 48 hr. Expression level of each gene was normalized to that of Gtf2b. (B) Schematic representation of the Pparg promoters. The locations of the sequences amplified in the ChIP are shown at the bottom in base pairs relative to the Pparg1 and Pparg2 transcriptional start sites. (C) Occupancy of C/EBPβ and C/EBPδ on a subset of target genes at 4 hr. Ct values of each ChIP were normalized to that of input. (D) Cell proliferation analysis of 3T3-L1 cells during adipocyte differentiation. 3T3-L1 cells were counted at each time point. The data represent means ± s.d. from three independent experiments. The p values for the indicated comparisons were determined by Student's t test (*, p < 0.05; **, p < 0.01). DOI: http://dx.doi.org/10.7554/eLife.05615.008\n\nFigure 5: Figure 5. (A and B) ChIP analysis of H3K4me3 (A) and H3K27ac (B) at the Pparg promoters during adipocyte differentiation. Ct values of each ChIP were normalized to that of input. (C) Formaldehyde-assisted isolation of regulatory elements (FAIRE) analysis during adipocyte differentiation. The enrichment of fragmented genomic DNA in the FAIRE samples was analyzed and normalized to that of input. (D, E and F) ChIP analysis of PPARγ (D), MED1 (E), and Pol II (F) at the Pparg promoter during adipocyte differentiation. Ct values of each ChIP were normalized to that of input. All data represent means ± s.d. from three independent experiments. The p values for the indicated comparisons were determined by Student's t test (*, p < 0.05; **, p < 0.01). DOI: http://dx.doi.org/10.7554/eLife.05615.009\n\nFigure 5: Figure 5. (A) Control IgG ChIP does not occupy a subset of gene promoters during adipogenesis. Ct values of each ChIP were normalized to that of input. (B and C) ChIP analysis of H3K9me2 (B) and H4K20me1 (C) at the Pparg promoter during adipocyte differentiation. Ct values of each ChIP were normalized to that of input. All data represent means ± s.d. from three independent experiments. The p values for the indicated comparisons were determined by Student's t test (*, p < 0.05; **, p < 0.01). DOI: http://dx.doi.org/10.7554/eLife.05615.010\n\nFigure 6: Figure 6. (A) TRIM23 does not affect PPARγ-mediated transcriptional activity in HEK293T cells. The peroxisome proliferator-activated receptor response element firefly luciferase reporter vector (PPRE–Luc), pGL4.74 renilla luciferase reporter plasmid, and expression vectors encoding TRIM23 and Pparg were transfected into HEK293T cells and the cells were incubated in culture medium containing 10% charcoal-treated fetal bovine serum for 24 hr. Cells were incubated with or without troglitazone (2 μM) for 24 hr, harvested, and quantified firefly luciferase and renilla luciferase mRNA with real-time PCR. The data represent means ± s.d. from three independent experiments. (B) TRIM23 does not promote SUMOylation of PPARγ2. An in vivo assay for SUMOylation of PPARγ2 by TRIM23 was performed. Expression vectors encoding FLAG-PPARγ2, Myc-TRIM23, and HA-SUMO1 were transfected into HEK293T cells. Cell lysates were immunoprecipitated with anti-FLAG antibody and then immunoblot analysis was performed to detect modifications of PPARγ2. DOI: http://dx.doi.org/10.7554/eLife.05615.011\n\nFigure 7: Figure 7. (A) Immunoblot analysis of C/EBPα, C/EBPβ, C/EBPδ and PPARγ proteins during 3T3-L1 cell differentiation. (B) The intensity of the immunoreactive bands of PPARγ2 obtained by immunoblot analysis with anti-PPARγ antibody was determined relative to that obtained with anti-β-actin antibody. (C) Immunoblot analysis of PPARγ protein in the absence and presence of MG132. 3T3-L1 cells with stable knockdown of TRIM23 or the corresponding control cells were differentiated by the differentiation cocktail for 48 hr and subsequently treated with 10 μM of MG132 for 6 hr (D) 3T3-L1 cells with stable knockdown of TRIM23 or the corresponding control cells were differentiated by the differentiation cocktail for 48 hr and subsequently treated with 10 μM of MG132 for 6 hr, followed by cycloheximide (CHX) treatment (5 μM) for 0, 1, 2 or 4 hr. The cell lysates were subjected to immunoblot analysis with an anti-PPARγ, anti-TRIM23 or anti-β-actin antibody. β-actin is shown as a loading control. The result is representative of two independent experiments. (E) The intensity of the PPARγ1 and PPARγ2 bands was normalized to that of the corresponding β-actin bands shown in (D) and is indicated as a percentage of the normalized value at 0 hr. DOI: http://dx.doi.org/10.7554/eLife.05615.012"
      }
    ]
  },
  {
    "id": "PMC4426667_multi_3",
    "image": [
      "images/PMC4426667-f7-2.png",
      "images/PMC4426667-f8.png",
      "images/PMC4426667-f9.png",
      "images/PMC4426667-f10.png",
      "images/PMC4426667-f10-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin ligase TRIM23 regulates adipocyte differentiation via stabilization of the adipogenic activator PPARγ\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. Immunoblot analysis of PPARγ protein in the absence and presence of MG132. 3T3-L1 preadipocytes with stable knockdown of TRIM23 or the corresponding control cells were treated with MG132 (10 mM) for 6 hr. DOI: http://dx.doi.org/10.7554/eLife.05615.013\n\nFigure 8: Figure 8. (A) In vivo assay for interaction between TRIM23 and PPARγ2. FLAG-TRIM23 and HA-PPARγ2 were transfected into HEK293T cells. Lysates were immunoprecipitated with anti-FLAG antibody and immunoblotted with anti-FLAG and anti-HA antibodies. (B) In vivo assay for interaction between TRIM23 and PPARγ2 with or without troglitazone (1 μM). FLAG-TRIM23 and HA-PPARγ2 were transfected into HEK293T cells. Coimmunoprecipitation assays were performed using the cell extract from these cells with anti-FLAG antibody in the presence or absence of 1 μM troglitazone. (C) In vivo assay for interaction between TRIM23 and PPARγ2. 3T3-L1 cells stably expressing FLAG-TRIM23 were generated, differentiated, and harvested at day 6. Whole cell lysates were immunoprecipitated with anti-FLAG antibody and then immunoblot analysis was performed with anti-FLAG and anti-PPARγ antibodies. (D) In vivo assay for ubiquitination of PPARγ2 by TRIM23. FLAG-PPARγ2, Myc-TRIM23, and HA-ubiquitin (HA-Ub) were transfected into HEK293T cells. Cell lysates were immunoprecipitated with anti-FLAG antibody and then immunoblot analysis was performed to detect ubiquitination of PPARγ2. (E) Promotion of in vitro PPARγ2 polyubiquitination by TRIM23. An in vitro ubiquitination assay was performed with the indicated combinations of ATP, HA-Ub, His6-E1, His6-E2 (UbcH5B), His6-GST-TRIM23-FLAG, and GST-PPARγ2. Reaction mixtures were subjected to immunoblot analysis with anti-PPARγ (top), anti-HA (middle) or anti-FLAG (bottom). The positions of GST-PPARγ2 or His6-GST-TRIM23-FLAG modified by various numbers of HA-Ub moieties are indicated. (F) Schematic representation of TRIM23 deletion mutants is shown. Protein motifs are indicated. RING, ring-finger domain; B-box, B-box domain; CC, coiled-coil domain; ARF, ADP ribosylation factor domain. (G) Immunoblot analysis of ectopic expression of TRIM23 deletion mutants in TRIM23-knockdown 3T3-L1 cells before induction of adipogenesis. (H) Cells were stained with Oil Red O to visualize the accumulation of lipid droplets at day 6. DOI: http://dx.doi.org/10.7554/eLife.05615.014\n\nFigure 9: Figure 9. (A) PPARγ2 polyubiquitination by TRIM23 leads to reduced recognition by the proteasomal ubiquitin receptor S5a. HEK293T cells transiently transfected with plasmids encoding FLAG-PPARγ2 and/or HA-TRIM23 were lysed. GST, GST-HR23B, and GST-S5a were resuspended with cell lysates, followed by pull-down with glutathione Sepharose beads. Samples were separated by SDS-PAGE, followed by immunoblotting using the indicated antibodies. (B) In vitro PPARγ2 polyubiquitination by TRIM23. An in vitro ubiquitination assay was performed with the indicated combinations of ATP, various ubiquitin mutants, His6-E1, E2 (UbcH5C), His6-GST-TRIM23-FLAG, and GST-PPARγ2. Reaction mixtures were subjected to immunoblot analysis with anti-PPARγ (top), anti-TRIM23 (middle) or anti-Ub (bottom) antibodies. The positions of GST-PPARγ2 or His6-GST-TRIM23-FLAG modified by various numbers of ubiquitin moieties are indicated. (C and D) Conjugation of PPARγ2 with M1- and/or K27-linked polyubiquitin chains leads to reduced recognition by the proteasomal ubiquitin receptor S5a. An in vitro ubiquitination assay was performed with the indicated combinations of ATP, ubiquitin mutants, His6-E1, E2 (UbcH5C), TRIM23-FLAG, and PPARγ2. Reaction mixtures were subjected to GST pull-down assay. PPARγ2-ubiquitin conjugates were incubated with GST-S5a (C) or GST-HR23B (D) prebound to glutathione Sepharose beads. Samples were separated by SDS-PAGE, followed by immunoblotting using a PPARγ antibody. Equivalent amounts of bound and unbound fractions were loaded in each lane. DOI: http://dx.doi.org/10.7554/eLife.05615.015\n\nFigure 10: Figure 10. (A) Immunoblot analysis of ectopic PPARγ2 expression before induction of adipogenesis is shown. (B) Changes in Trim23 mRNA during adipocyte differentiation in 3T3-L1 cells. Total RNA was isolated from 3T3-L1 cells on the indicated days of differentiation. Trim23 mRNA was determined by real-time PCR and normalized to that of Gtf2b. (C) Cells were stained with Oil Red O to visualize the accumulation of lipid droplets at day 6. (D) RNA levels of Fabp4, Cebpa, and Pparg were determined by real-time PCR at days 0, 2, 4 and 6 of differentiation. Expression level of each gene was normalized to the level of Gtf2b. The data represent means ± s.d. from three independent experiments. The p values for the indicated comparisons were determined using Student's t-test (*p < 0.05; **p < 0.01). (E) Model for TRIM23 function in PPARγ abundance during adipocyte maturation. Several adipogenic stimuli activate early adipogenic activators such as C/EBPβ, C/EBPδ, glucocorticoid receptor (GR) and signal transducer and activator of transcription 5a (STAT5a). These activators then induce late adipogenic activators including PPARγ and C/EBPα. TRIM23 mediates atypical polyubiquitin conjugation to PPARγ and may stabilize the PPARγ protein. TRIM23 plays a critical role in the switching from early to late adipogenic enhanceosomes by regulating the abundance of PPARγ. DOI: http://dx.doi.org/10.7554/eLife.05615.016\n\nFigure 10: Figure 10. (A) Immunoblot analysis of PPARγ and C/EBPα protein during 3T3-L1 differentiation. (B) RNA levels of Cidec, Klf15, Cebpb, Adipoq, Retn and Cebpd, were determined by real-time PCR at days 0, 2, 4, and 6. Expression level of each gene was normalized to that of Gtf2b. The data represent means ± s.d. from three independent experiments. The p values for the indicated comparisons were determined using Student's t-test (*p < 0.05; **p < 0.01). DOI: http://dx.doi.org/10.7554/eLife.05615.017"
      }
    ]
  },
  {
    "id": "PMC4496214_multi",
    "image": [
      "images/PMC4496214-f1.png",
      "images/PMC4496214-f2.png",
      "images/PMC4496214-f3.png",
      "images/PMC4496214-f4.png",
      "images/PMC4496214-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"FBXW7-mutated colorectal cancer cells exhibit aberrant expression of phosphorylated-p53 at Serine-15\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic representation of the coordinates of the pre-coated phospho-specific antibodies in duplicate in a nitrocellulose-membrane. Dashed red-circle highlights the antibody position for phospho-p53(Ser15). (B-E) Outcome overview of the HPKPA using human CRC-cells expressing and lacking FBXW7; FBXW7-deficient HCT116 (D) and DLD-1 (E) cells [FBXW7(−/−)], compared to parental HCT116 (B) and DLD-1 (C) cells [FBXW7(+/+)]. (F) The expression of phospho-p53(Ser15) protein was significantly increased. Scanned values obtained using transillumination scanner of phospho-p53(Ser15) and Positive Controls (PCs) spots as corresponding to HCT116 and DLD-1 cell lines in B-E. The results shown are representative of experiments performed at three independent times. (G) Phospho-p53(Ser15) expressions was analyzed by Western blotting analysis. Protein extracts isolated from HCT116 and DLD-1 cell lines with FBXW7(−/−) and FBXW7(+/+) alleles were Western blotted for phospho-p53(Ser15) antibody and Tubulin (loading control).\n\nFigure 2: Figure 2. (A) Schematic shows the floxed Fbxw7 allele (fbxw7fl/fl) before and after villin-Cre recombination to generate gut-specific conditional Fbxw7 inactivation (fbxw7ΔG) mice. (B) Western blot analysis of fbxw7fl/fl and fbxw7ΔG intestinal proteins using antibodies against Fbxw7, p53, phospho-p53(Ser15), and the loading control β-actin. Experiments were performed on at least two independent occasions.\n\nFigure 3: Figure 3. (A-L) Immunofluorescent staining of phospho-p53(Ser15) protein (red) in non-treated (A-F) and 50 kJ/m2 UV-treated (G-L) HCT116 cells. UV stimulated induction of phospho-p53(Ser15) protein in general (H & K). In both conditions, FBXW7-deficient cells (E & K) obtain higher expression levels of phospho-p53(Ser15) than the corresponding control cells (B & F). Nuclei were visualized with 4′, 6-diamidino-2-phenylindole (DAPI)-blue fluorescent stain (A, D, G, and J). Overlaid images (C, F, I, and L) showed nuclear localization of phospho-p53(Ser15). Arrows indicate phospho-p53(Ser15) distribution. Bars, 25 μm. Figures are representative of duplicate experiments performed on three separate occasions. (M) Quantification analysis of fluorescence intensity of IF images. (N) Western blotting analysis of phospho-p53(Ser15) expression; untreated and exposed to 50 kJ/m2 UV. β-actin served as a loading control. All experiments were repeated at least three times.\n\nFigure 4: Figure 4. (A-F) Representative images of chromogenic IHC-staining of paraffin-embedded FBXW7-wild-type (wt) and -mutated (mut) CRC-tissue sections for phospho-p53(Ser15) expression. Specimens of healthy small bowel (n = 1) (A and B), FBXW7-wt CRC (C and D), and FBXW7-mut CRC (E and F) show enrichment, annihilation, and remarkable increment of phospho-p53(Ser15) expression. Bars, 50 μm (A, C, E); 100 μm (B, D, F).\n\nFigure 5: Figure 5. (A) IHC for human CRC-tissues evaluated semi-quantitatively by two independent observers within 3-microscopic views in the individual slides. Expression scale of the phospho-p53(Ser15) protein was determined by the intensity of the staining, and thus scored using an ordinal scale: 0 = no staining, 1 = lowest staining, 2 = intermediate staining and 3 = extensive staining. (B) P value (***p < 0.0005; mean ± S.D.; mean for FBXW7WT group = 0.31 with S.D = 0.1945; and mean for FBXW7Mut group = 1.87 with S.D. = 0.3600) was gained from Student's t-test comparing phospho-p53(Ser15) expression in CRC-tissues with and without FBXW7-mutations."
      }
    ]
  },
  {
    "id": "PMC4496214_multi_2",
    "image": [
      "images/PMC4496214-f6.png",
      "images/PMC4496214-f7.png",
      "images/PMC4496214-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"FBXW7-mutated colorectal cancer cells exhibit aberrant expression of phosphorylated-p53 at Serine-15\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A-D) IHC for p53 in human CRC with (C, D) and without (A, B) FBXW7 mutations. Boxed line indicates magnified tissue area. Scale bars; 50 μm. (E) Western blotting analysis of p53 expression in HCT116 and DLD-1 cell lines expressing or lacking FBXW7. β-actin was blotted for loading control. All experiments were repeated for two times.\n\nFigure 7: Figure 7. After starvation overnight, synchronised HCT116FBXW7(+/+) and HCT116FBXW7(−/−) cells were treated with increasing concentrations of the oxaliplatin; for 72 h, IC50 (A) and cell viability (B) determined using SRB at 540 nm in a microplate reader. (C) An increased colony forming efficiency of FBXW7–/– HCT116 cells compared with parental FBXW7+/+ HCT116 cells and graphs show mean ± SEM of assay data, representative of six replicates in three independent experiments (*P < 0.05, **P < 0.01, ***P < 0.001). (D) phospho-p53(Ser15) protein expression measured at low (0.35) and IC50 dose (0.7 μM) oxaliplatin concentration in HCT116FBXW7(+/+) and HCT116FBXW7(−/−) cells by Western blotting. (E) p53-mediated genes expression was determined by qRT-PCR in HCT116FBXW7(−/−) cells (red), first normalized to GAPDH followed by normalization to HCT116FBXW7(+/+) cells (blue). Data are mean ± SEM (*P ≤ 0.05; **P < 0.01; ***P < 0.001). Experiments were performed in triplicate for each genotype and repeated at least on three independent occasions.\n\nFigure 8: Figure 8. (A) FLAG-tagged versions of the indicated p53 mutant and GFP-FBXW7 proteins were expressed in HEK293T cells, and lysates were subjected to immunoblotting with anti-FLAG, anti-p-p53(Ser15) and anti-GFP. β-actin was used as a loading control. (B) HEK293T cells were treated with cycloheximide (CHX) for the indicated time points. Lysates were examined by Western blotting anti-p-p53(Ser15) and anti-GFP. β-actin was used as a loading control. (C) Western blot analysis of whole-cell lysates (input) (left-panel) and immunoprecipitates (IP) with GFP (middle-panel) and FLAG-p53 (right-panel) derived from 293T cells transfected with GFP-FBXW7 together with the FLAG-p53 constructs. Thirty hours after transfection, cells were pretreated with 10 μM MG132 for 4 h to block the proteasome pathway before cell collection. Both IPs was probed by anti-GFP and anti-FLAG antibodies simultaneously. (D) HCT116 and DLD-1 cells lacking or expressing FBXW7 were subjected to immunoblotting with anti-CK1α, pChk2 (S516), pChk2 (T66), phospho-p44/42 MAPK (pERK1/2) and p44/42 MAPK (ERK1/2). β-actin was loaded as a loading control. All experiments were repeated at least three times. (E) Immunofluorescent staining of anti-CK1α of HCT116FBXW7(+/+) versus HCT116FBXW7(−/−) cells. (F) Schematic of molecular changes may occur in the HCT116FBXW7(−/−) compared with parental HCT116FBXW7(+/+) cells treated with the oxaliplatin."
      }
    ]
  },
  {
    "id": "PMC4508581_multi",
    "image": [
      "images/PMC4508581-f1.png",
      "images/PMC4508581-f2.png",
      "images/PMC4508581-f3.png",
      "images/PMC4508581-f4.png",
      "images/PMC4508581-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Hypoxia signaling pathways: modulators of oxygen-related organelles\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Regulation of HIF-α subunits. (A) Hypoxia-inducible factors (HIFs) are transcription factors composed of O2-regulated α subunits (HIF-1α or HIF-2α) and a constitutively expressed HIF-1β subunit. Together these subunits bind hypoxia response elements (HRE) to mediate adaptive responses to hypoxia. HIF-α activity is directly linked to oxygen partial pressure. Under normoxia, HIF-α is hydroxylated by prolyl hydroxylase domain protein (PHD) and targeted for proteasomal degradation by the von Hippel-Lindau (VHL) E3 ubiquitin ligase complex. Under hypoxia, hydroxylation is inhibited and HIF-α is stabilized, it dimerizes with HIF-1β and enters the nucleus to induce target gene transcription. (B) HIF-α can be stabilized irrespective of O2 tension due to inhibition of PHDs, a state defined as pseudohypoxia. Mutations in the Krebs cycle enzymes succinate dehydrogenase (SDH) and fumarate hydratase (FH) lead to accumulation of succinate and fumarate, respectively, whereas mutations in isocitrate dehydrogenases 1/2 (IDH1 and IDH2) lead to low levels of 2-oxoglutarate. Succinate and fumarate inhibit PHDs, while low levels of the co-substrate 2-oxoglutarate decrease the activity of PHDs. Decreased activity of PHDs leads to a low rate of HIF-α hydroxylation under normoxic conditions and stabilization of HIF-α.\n\nFigure 2: Figure 2. Regulation of mitochondrial function and abundance by HIF-α. (A) To adapt to low oxygen tension, cells undergo two HIF-1α-mediated alterations of cellular metabolism: O2-independent ATP production and reduction of mitochondrial O2 consumption. HIF-1α signaling also contributes to the Warburg effect of aerobic glycolysis—that is, an uncoupling of glycolysis from O2 levels—by stimulating the expression of the glucose transporter GLUT1 and glycolytic enzymes. Increased glycolysis generates increased levels of pyruvate, which is largely converted to lactate by HIF-inducible lactate dehydrogenase A (LDHA) and removed from the cell by the monocarboxylate transporter 4 (MCT4). HIF-1α induces pyruvate dehydrogenase kinase 1 (PDK1), which inhibits pyruvate dehydrogenase (PDH) and blocks conversion of pyruvate to acetyl-CoA, resulting in decreased flux through the tricarboxylic acid (TCA) cycle. Decreased TCA cycle activity attenuates oxidative phosphorylation and excessive mitochondrial ROS production. Under normoxia, COX4-1 is the predominant isoform of COX4 present in complex IV of the electron transport chain, which transfers electrons to O2. Under hypoxia, HIF-1α upregulates the expression of COX4-2 and the mitochondrial protease LONP1, which in turn degrades COX4-1. COX4-2 is more efficient at facilitating the electron transfer to O2 and thereby protects the cell from oxidative damage during hypoxia. (B) Control of mitochondrial biogenesis by HIF-α. HIF-1α induces the expression of MAX-interacting protein 1 (MXI1), a repressor of MYC activity, and thereby represses a subset of MYC target genes such as PGC-1β. HIF-1α-dependent activation of FOXO3a inhibits MYC activity by reducing MYC protein stability. Interaction between PGC-1 and transcription factors such as PPARα, ERR, and NRF-1/2 orchestrates the major functions of mitochondria. HIF-1α-mediated inhibition of MYC and PGC-1 results in reduced mitochondrial biogenesis.\n\nFigure 3: Figure 3. Receptor-mediated mitophagy. (A) Atg32-mediated mitophagy in S. cerevisiae. Atg32 is an outer mitochondrial membrane protein whose expression is induced upon mitophagy-inducing conditions. Atg32 interacts with Atg8 and Atg11 via distinct domains. Casein kinase 2 (CK2) phosphorylates Atg32 upon mitophagy-inducing conditions, which is essential for the Atg11 interaction without affecting Atg32-Atg8 binding. (B) NIX/BNIP3-mediated mitophagy in mammalian cells. NIX and BNIP3 are outer mitochondrial membrane proteins that interact with LC3 through LIR motifs in their N-terminal region. Upon hypoxia, NIX and BNIP3 are transcriptionally induced in a HIF-α-dependent manner. Phosphorylation of BNIP3 promotes its binding to LC3 and subsequent mitophagy. The kinase for BNIP3 phosphorylation is unknown. (C) FUNDC1-mediated mitophagy in mammalian cells. FUNDC1 is an outer mitochondrial membrane protein that interacts with LC3 through a LIR domain at its cytosol-exposed N-terminus. Under normal physiological conditions, FUNDC1 is phosphorylated by SRC and CK2, thereby preventing LC3 binding. Upon hypoxia or loss of mitochondrial membrane potential (Δψm), the expression of SRC is strongly suppressed and PGAM5 dephosphorylates FUNDC1. Dephosphorylation of FUNDC1 enhances the interaction between FUNDC1 and LC3 and promotes mitophagy. Phosphorylation of FUNDC1 by ULK1 enhances its binding to LC3.\n\nFigure 4: Figure 4. Model illustrating the relationship between hypoxia, ER stress, and activation of the unfolded protein response. Severe hypoxic stress perturbs and reduces O2-dependent protein folding capacity, resulting in the accumulation and aggregation of misfolded proteins in the ER lumen. Hypoxia increases intracellular ROS production and ROS stimulate multiple biological responses during O2 deprivation. Unfolded proteins and hypoxic ROS trigger ER stress which leads to HIF-α-independent activation of the UPR. The UPR is initiated by the stress-sensing ER transmembrane proteins PERK, IRE1, and ATF6. The chaperone GRP78 is normally bound to these ER stress sensors and keeps them inactive, but dissociates from them under ER stress conditions. This dissociation leads to the activation of the three UPR pathways. GRP78 dissociation allows PERK to homodimerize, which facilitates autotransphosphorylation and kinase domain activation. Activated PERK phosphorylates eIF2α which decreases general translation while increasing the preferential translation of specific proteins, such as the transcription factor ATF4. ATF4 triggers the activation of a gene expression program referred to as the integrated stress response. ATF4 induces the expression of GADD34, which acts as a negative regulator of the PERK pathway by dephosphorylating eIF2α. The integrated stress response promotes energy and redox homeostasis and is an important prosurvival mechanism under moderate hypoxia. IRE1 homodimerization, followed by autotransphosphorylation, triggers its RNase activity. IRE1-mediated splicing of full-length XBP1 mRNA generates XBP1s, which encodes an active transcription factor. ER stress leads to the translocation of ATF6 to the Golgi, where it is cleaved by regulated intramembrane proteolysis to produce the active transcription factor. Modified from Faust and Kovacs (2014).\n\nFigure 5: Figure 5. (A) The major metabolic pathways in peroxisomes of the mammalian liver. Various lipids are transported by PMPs (e.g., the ABC transporter proteins ABCD1, ABCD2, ABCD3) into the peroxisomal matrix, where they are oxidized by the β-oxidation enzymes. The products of the β-oxidation can serve as substrates for the biosynthesis of ether-linked phospholipids, cholesterol and bile acids or may exit the peroxisome for further oxidation in mitochondria. With regard to PUFAs, peroxisomes not only degrade these compounds but are also involved in their formation through retroconversion of PUFAs by catalyzing the chain-shortening steps. Peroxisomal function depends highly on molecular O2 due to its oxidative type of metabolism. Peroxisomal β-oxidation and the activity of other peroxisomal oxidases (e.g., UOX, DAO) result in the production of H2O2, which is decomposed by catalase. Modified from Schrader and Fahimi (2008). (B) Model for HIF-2α-mediated decrease in peroxisome abundance. Peroxisome homeostasis is achieved by balancing biogenesis and degradation of peroxisomes. HIF-2α signaling promotes degradation of peroxisomes by pexophagy. Reduced peroxisome abundance and the ensuing deficiency in peroxisomal function leads to major changes in the lipid profile, such as accumulation of VLCFAs. VLCFAs are activating ligands for the transcription factor PPARα. HIF-2α represses ligand-induced PPARα-mediated peroxisome proliferation and consequential restoration of peroxisome homeostasis. Thus, by simultaneously inducing pexophagy and counteracting PPARα, HIF-2α ensures efficient depletion of the peroxisome pool."
      }
    ]
  },
  {
    "id": "PMC4515942_multi",
    "image": [
      "images/PMC4515942-f1.png",
      "images/PMC4515942-f2.png",
      "images/PMC4515942-f3.png",
      "images/PMC4515942-f4.png",
      "images/PMC4515942-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Muscle ring finger-3 protects against diabetic cardiomyopathy induced by a high fat diet\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Role of MuRF3 in regulating PPAR isoform activity and its role in high fat diet cardiac hypertrophy in vivo. Isolation of cardiac nuclei from MuRF3−/− and sibling wildtype mouse hearts revealed increases in a. PPARα, PPARβ/δ, and PPARγ activity using PPRE-DNA as bait and ELISA detection of PPARα protein (N = 3-4/group as indicated in bars). b. Experimental design of high fat diet (60 %)-induced cardiomyopathy. c. High fat diet induces cardiac MuRF3 levels after 26 weeks HFD (N = 3/group). d. MuRF3−/− heart weights 26 weeks high fat diet normalized to body weight and tibia length (N = 3/group). e. MuRF3−/− body weight at baseline and after high fat diet for 26 weeks (N indicated below graph). Values expressed as Mean ± SE. Statistical analysis was performed using a Student’s t-test comparing MuRF3−/− and MuRF3+/+ groups. *p ≤ 0.001, **p < 0.01. #p < 0.05\n\nFigure 2: Figure 2. MuRF3−/− experience significant deficits in cardiac function after challenge with high fat diet. a qPCR analysis of heart failure associated fetal gene expression in MuRF3−/− mice at baseline and after 26 weeks high fat diet challenge. b Fasting blood glucose and fasting serum insulin levels. c Histological analysis of MuRF3−/− and wildtype hearts post-high fat diet challenge. d/e MuRF3−/− mice exhibit an accelerated heart failure by 6 weeks after the initiation of the high fat diet. Values expressed as Mean ± SE. N indicated in bars (a & b) or below graph (e). The significance of observed differences in grouped mean values was determined using a One Way ANOVA followed by Holm-Sidak pairwise post hoc analysis. *p < 0.001, #p < 0.05\n\nFigure 3: Figure 3. Histological analysis of cardiac fibrosis. a Cross-sectional analysis of myocytes reveal no differences between MuRF3−/− and wildtype hearts (Masson’s Trichrome). b Objective blinded computer analysis of fibrosis of MuRF3−/− and wildtype hearts after 26 weeks high fat diet reveals no significant differences. c Confocal immunofluorescence analysis of vimentin (fibroblasts) in cardiac cross-sections from MuRF3−/− mice after 26 weeks HFD. Values expressed as Mean ± SE. N = 3 WT and N = 3 MuRF3−/−. A Student’s t-test was performed comparing MuRF3−/− vs. MuRF3+/+ groups. #p < 0.05\n\nFigure 4: Figure 4. High fat diet-induced increases in PPAR-regulated gene (mRNA) levels in MuRF3−/− hearts. RT-qPCR analysis of cardiac a. Cardiac PPARα target gene expression, b. PPARβ-regulated mRNA target genes involved in glucose metabolism, c. PPARβ-regulated mRNA target genes involved in fatty acid metabolism. d PPARγ1-regulated mRNA target genes. Values expressed as Mean ± SE. The significance of observed differences in grouped mean values was determined using a One Way ANOVA followed by Holm-Sidak pairwise post hoc analysis. N per group indicated above graph. *p ≤ 0.001, **p < 0.01, #p < 0.05\n\nFigure 5: Figure 5. Analysis of tissue triglyceride, glycogen, and fat mass in MuRF3−/− mice after high fat diet challenge. a Triglyceride analysis of cardiac left ventricle (LV), liver, and skeletal muscle (gastrocnemius). b Glycogen analysis of cardiac LV, liver, and skeletal muscle (gastrocnemius). c Magnetic resonance imaging (MRI) analysis of fat mass, lean body mass, and free water at baseline, 6, 12, and 22 weeks HFD. Values expressed as Mean ± SE. A one-way ANOVA was performed to determine significance of cardiac LV triglyceride and glycogen concentrations, followed by a Holm-Sidak pairwise comparison to determine significance between groups. A Student’s t-test was performed comparing MuRF3−/− vs. MuRF3+/+ groups. Numbers above bars represent number of animals (N) included in each experiment (N = MuRF3+/+, MuRF3−/− in c). n.s. = not significant. *p < 0.001, **p < 0.01, #p < 0.05"
      }
    ]
  },
  {
    "id": "PMC4515942_multi_2",
    "image": [
      "images/PMC4515942-f6.png",
      "images/PMC4515942-f7.png",
      "images/PMC4515942-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Muscle ring finger-3 protects against diabetic cardiomyopathy induced by a high fat diet\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Western analysis of MuRF3−/− cardiac NF-κB, IRS-1, and cJun signaling. Immunoblot analysis of a. NF-κB, b. IRS-1, and c. cJun reveal no differences in MuRF3−/− and sibling wildtype mice. Values expressed as Mean ± SE. Statistical analysis was performed using a Student’s t-test. N = 3/group. n.s. = not significant. #p < 0.05\n\nFigure 7: Figure 7. MuRF3 inversely regulates steady state levels of PPARα and PPARγ1. a Immunoblot analysis of cardiac LV PPARα, PPARβ, and PPARγ1 levels normalized to βactin. b-d In vitro ubiquitination assays of MuRF3’s ability to ubiquitinate PPARα (b), PPARβ (c), and PPARγ1 (d), with all lanes having Ub, E1, E2, MuRF3, and PPAR (=full reaction), unless otherwise indicated. Immunoblot for MuRF3 illustrates auto-ubiquitination (=MuRF3 activity) present in the same reaction as mono-ubiquitination (PPARα) and poly-ubiquitiation (PPARγ1). Values expressed as Mean ± SE of three independent experiments. A one-way ANOVA was performed to determine significance, followed by a Holm-Sidak pairwise comparison to determine significance between groups. N = 3/group. #p < 0.05\n\nFigure 8: Figure 8. Non-targeted cardiac metabolomics of MuRF3−/− mice after 26 Weeks challenge with high fat diet. a Principal components analysis, t-test, and Variable Importance in the Projection Analysis/Partial Least Squares-Discriminant Analysis (PLS-DA), b Heat map of metabolites identified by non-targeted GC/MS analysis of cardiac tissue. N = 3/group. Significance determined as p < 0.05"
      }
    ]
  },
  {
    "id": "PMC4526192_multi",
    "image": [
      "images/PMC4526192-f1.png",
      "images/PMC4526192-f2.png",
      "images/PMC4526192-f3.png",
      "images/PMC4526192-f4.png",
      "images/PMC4526192-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MuRF2 regulates PPARγ1 activity to protect against diabetic cardiomyopathy and enhance weight gain induced by a high fat diet\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Role of MuRF2 in regulating PPAR isoform activity and its role in high fat diet cardiac hypertrophy in vivo. Isolation of cardiac nuclei from MuRF2−/− and sibling wild type mouse hearts revealed increases in a PPAR∝, PPARβ/δ, and PPARγ DNA binding activity using PPRE-DNA as bait and ELISA detection of PPARα protein (N = 4/group). b Experimental design of high fat diet (60%)-induced cardiomyopathy. c High fat diet induces cardiac MuRF2 levels after 26 weeks HFD (N = 3/group). d Endogenous MuRF2 inhibits HFD-induced LV Mass and heart wet weights, as MuRF2−/− hearts have a significant increase in heart weight normalized to body weight and tibia length (N = 5/group). e Endogenous MuRF2, found in skeletal muscle and the heart does not affect overall body weight (N indicated below graph). Values expressed as Mean ± SE. Statistical analysis was performed using a Student’s t-test comparing MuRF2−/− and MuRF2+/+ groups. *p ≤ 0.001, **p < 0.01. §p < 0.05 by One Way ANOVA, ¶p < 0.05 vs. MuRF2+/+ baseline by multiple comparisons. $p < 0.05 vs. time-matched MuRF2+/+ (Student’s t-test).\n\nFigure 2: Figure 2. Analysis of MuRF2−/− hearts by conscious echocardiograpy, morphometrics, and heart failure-associated gene expression. a MuRF2−/− exhibit an accelerated heart failure by 6 weeks after the initiation of the high fat diet. b Representative 2D echocardiographic images from MuRF2−/− hearts at baseline and high fat diet challenge. c Endogenous MuRF2 inhibits HFD-induced LV Mass and heart wet weights, as MuRF2−/− hearts have a significant increase in heart weight normalized to body weight and tibia length (N = 5/group). d Representative gross histological analysis of MuRF2−/− hearts, found to have wall thinning and increased LV diameters by echocardiological analysis (N = 11 MuRF2+/+, N = 12 MuRF2−/−, see Table 1 and panel a above). e RT-qPCR analysis of heart failure associated fetal gene expression in MuRF2−/− mice at baseline and after 26 weeks high fat diet challenge. Values expressed as Mean ± SE. A One Way ANOVA was performed on echocardiographic studies between all groups, followed by Holm-Sidak (Multiple Comparisons vs. MuRF2 +/+ baseline only). A Student’s t test was then run to compare MuRF2−/− to wildtype control at the same time point. §p < 0.05 by One Way ANOVA, ¶p < 0.05 vs. MuRF2+/+ baseline by multiple comparisons. $p < 0.05 vs. time-matched MuRF2+/+ (Student’s t test). Statistical analysis of heart weight/body weight was performed using a Student’s t test. RT-qPCR analysis analyzed by a One Way ANOVA followed by Holm-Sidak Multiple Comparisons (all pairwise comparisons) *p < 0.001, **p < 0.01, #p < 0.05.\n\nFigure 3: Figure 3. Histological analysis of cardiac fibrosis. a Fibrosis analysis of Masson’s Trichrome-stained heart sections of MuRF2−/− and wild type hearts after 26 weeks high fat diet reveals no significant differences. b Confocal immunofluorescence analysis of vimentin (fibroblasts) in cardiac cross-sections from MuRF2−/− mice after 26 weeks HFD (N = 3/group). Values expressed as Mean ± SE. Statistical analysis was performed using a Student’s t test. *p < 0.001, **p < 0.01, #p < 0.05.\n\nFigure 4: Figure 4. High fat diet-induced increases in PPAR-regulated gene (mRNA) levels are exaggerated in cardiac MuRF2−/− hearts. RT-qPCR analysis of cardiac mRNA of genes identified as PPAR isoform “specific” based on cardiac transgenic PPARα, PPARβ, and PPARγ1 studies as described in the text. a Cardiac PPARα target gene expression, b PPARβ-regulated mRNA target genes involved in glucose metabolism, c PPARβ-regulated mRNA target genes involved in fatty acid metabolism. d PPARγ1-regulated mRNA target genes. Values expressed as Mean ± SE. Values expressed as Mean ± SE. The significance of observed differences in grouped mean values was determined using a One Way ANOVA followed by Holm-Sidak pairwise post hoc analysis. N per group indicated above graph. *p ≤ 0.001, **p < 0.01, #p < 0.05.\n\nFigure 5: Figure 5. Analysis of tissue triglyceride, glycogen, and fat mass in MuRF2−/− mice after high fat diet challenge. a Triglyceride analysis of cardiac left ventricle (LV), liver, and skeletal muscle (gastrocnemius). b Glycogen analysis of cardiac LV, liver, and skeletal muscle (gastrocnemius). c Magnetic resonance imaging (MRI) analysis of fat mass, lean body mass, and free water at baseline, 6, 12, and 22 weeks HFD. Values expressed as Mean ± SE. A one-way ANOVA was performed to determine significance of cardiac LV triglyceride and glycogen concentrations, followed by a Holm-Sidak pairwise comparison to determine significance between groups. A Student’s t test was performed comparing MuRF2−/− vs. MuRF2+/+ groups in all other studies. Numbers above bars represent number of animals (N) included in each experiment (N = MuRF2+/+, MuRF2−/− in c). *p < 0.001, **p < 0.01, #p < 0.05."
      }
    ]
  },
  {
    "id": "PMC4526192_multi_2",
    "image": [
      "images/PMC4526192-f6.png",
      "images/PMC4526192-f7.png",
      "images/PMC4526192-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"MuRF2 regulates PPARγ1 activity to protect against diabetic cardiomyopathy and enhance weight gain induced by a high fat diet\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The ratio of MuRF2 to PPARγ1 determines the ubiquitin post-translational modification and ligand-dependent protein levels. a Immunoblot analysis of cardiac LV PPARα, PPARβ, and PPARγ1 levels normalized to GAPDH. N = 3/group. b Increasing MuRF2 results in a PPARγ1 ligand (Rosiglitazone)-dependent decrease in PPARγ1 in vitro 24 h after transfection. HEK293 cells were co-transfected with MuRF2 and PPARγ1 (as indicated below graph). After 24 h, 1 microM Rosiglitazone was added overnight and cells harvest at 48 h. *p < 0.05 vs. MuRF2:PPARγ1 ratio of 1:1 without Rosiglitazone. c Immunoprecipitation studies identifying MuRF2 interaction with PPARg1. HEK293 cells were transfected p3XFlag-PPARγ1 (or p3XFlag-Empty vector), pcDNA3.1-HA-MuRF2p50a (or HA-MURF2∆Ring) and immunoblotted for MuRF2 (anti-HA). d Left Proteasome inhibition with MG132 prevents MuRF2’s degradation of PPARγ1 in a Right ligase-dependent (Ring Finger-dependent) manner. HEK293 cells transfected with p3XFlag-PPARγ1, pcDNA3.1-HA-MuRF2p50a and treated with MG132 (50 μM) for 2.5 h before Rosiglitazone added (1 μm). e–g In vitro ubiquitination assays of MuRF2’s ability to ubiquitinate PPARα (e), PPARβ (f), and PPARγ1 (g), with all lanes having Ub, E1, E2, MuRF2, and PPAR (=full reaction), unless otherwise indicated. Immunoblot for MuRF2 illustrates auto-ubiquitination (=MuRF2 activity) present in the same reaction as mono-ubiquitination (PPARα) and poly-ubiquitination (PPARγ1). Values expressed as Mean ± SE of three independent experiments. A one-way ANOVA was performed to determine significance, followed by a Holm-Sidak pairwise comparison to determine significance between groups. #p < 0.05, **p < 0.01.\n\nFigure 7: Figure 7. MuRF2 alters nuclear localization of PPARγ1 in a ubiquitin ligase region (RING)-dependent manner without altering steady state protein levels (as found in vivo). Increased MuRF2 alters PPARγ1 localization from primarily nuclear a to increased cytosolic/perinuclear localization b in HL-1 cardiomyocyte-derived cells. MuRF2 lacking ubiquitin ligase activity (∆RING FingerMuRF2, c does not alter PPARγ1 localization compared controls (top row), indicating MuRF2’s dependence on its ubiquitin ligase activity in mediating these changes. Representative of three biological replicates. Right Percentages based on the number of cells analyzed (N = 58, 68, and 88 in FLAG-PPARγ1, FLAG-PPARγ1 + HA-MuRF2, and FLAG-PPARγ1 + HA-∆RING-MuRF2 groups, respectively).\n\nFigure 8: Figure 8. Non-targeted cardiac metabolomics of MuRF2−/− mice after 26 weeks challenge with high fat diet. a Principal components analysis, b Partial least squares-discriminant analysis (PLS-DA) and variable importance in the projection analysis, c Heat map of metabolites identified by non-targeted GC/MS analysis of cardiac tissue. d Enrichment by pathway-associated metabolite sets and e location-Based Metabolite sets determined from VIP significant and t test significant metabolites identified. N = 3/group. Significance determined as p < 0.05."
      }
    ]
  },
  {
    "id": "PMC4599673_multi",
    "image": [
      "images/PMC4599673-f1.png",
      "images/PMC4599673-f2.png",
      "images/PMC4599673-f3.png",
      "images/PMC4599673-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mutations in PIGY: expanding the phenotype of inherited glycosylphosphatidylinositol deficiencies\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Clinical features of patients with mutations in PIGY. Family A, Patient II-1 had proximal limb shortening, left hip dysplasia and contractures were present at the elbows, hips and knees (i). Dysmorphic features included bitemporal narrowing, upturned nares, depressed nasal bridge, deep-set eyes, a short neck (ii) and ears with thickened helices and fleshy earlobes (iii). Brachyphalange, fifth finger clinodactyly and adducted thumbs were present (v). Brachytelephalange was present on X-ray (iv). Family B Patient II-2 (v) and Patient II-3 (vi) had a milder phenotype, with soft dysmorphic features including long palpebral fissures, a bulbous tip to the nose and a wide mouth. Patient II-2 had a strabismus. (B) Pedigrees of Families A and B. Shading indicates affected individuals. The probands are indicated with an arrow. Proven heterozygote carriers are shown by a dot. Sanger sequencing validation from Family A confirms the homozygous missense variant c.137T>C (p.Leu46Pro) in the PIGY gene (NM_001042616.1) in the two affected sisters. Region shown corresponds to chr4: 89,442,795–813 (hg19). For Family B, Sanger validation and segregation testing of the PIGY promoter variant c.-540G>A is shown. The consensus SP1 binding motif is indicated with a black rectangle. Region shown corresponds to chr4: 89,444,938–958.\n\nFigure 2: Figure 2. (A) Analysis of patient tissue by flow cytometric analysis. Cultured skin fibroblasts from Patients II-1 and II-2 from Family A were labelled with anti-Human CD55-APC and anti-Human CD59-PE and analysed by flow cytometry. (A) Histograms showing the mean fluorescent intensity (MFI) are depicted for Patient II-1 and show a reduction in MFI for CD55-APC and CD59-PE (red) compared with control (blue). (B) Graphical representation of these data shows a statistically significant reduction in MFI for these GPI markers. Skin fibroblast biopsies were taken from Patient II-1 and Patient II-2 at 5 months and 8 days, respectively. Primary human fibroblast controls were used from three different individuals at ages 5.5 years, 6 months and 3.5 months. All experiments were performed in triplicate.\n\nFigure 3: Figure 3. (A) Daudi cells (a PIG-Y deficient human Burkitt's lymphoma cell line) were transiently transfected with normal (WT) or mutant (p.Leu46Pro) PIGY driven by minimum TATA box promoter in pTAL oriP puro PIGY (weak promoter). Restoration of the surface expression of CD59 and CD55 was assessed 2 days later by flow cytometry. WT-PIGY restored the surface expression of CD55 and CD59, but p.Leu46Pro mutant PIG-Y did not. (B) After transient transfection of Daudi cells with normal (WT) or mutant (p.Leu46Pro) PIGY driven by the strong promoter in pME-oriP HA-PIGY, restoration of surface expression of CD59 was achieved by WT and p.Leu46Pro constructs, indicating that the mutant has some residual activity (left panel). Cell lysates prepared from Daudi cells transfected with either WT-PIGY, mutant p.Leu46Pro PIGY, and empty vector were separated by SDS-PAGE and probed for anti-HA and anti-GAPDH antibodies. Normalization of the anti-HA signal compared with GAPDH showed a marked reduction in protein expression in the mutant (p.Leu46Pro) compared with WT. HA-tagged PIG-Y appeared as doublet bands on western blotting for an unknown reason. (C) In vivo labelling of 3H-mannose into transformed fibroblast cells derived from Patients II-1 and II-2 (Family A) was performed to enhance incorporation into GPI mannolipids. Fibroblasts derived from Patient 2 (Family A) had KOH-resistant alkyl-bond-containing GPI spots similar to fibroblasts from a healthy control 1 (spots in KOH lanes). Fibroblasts from Patient 1 and another healthy control were not efficiently labelled by mannose. DPM, dolichol-phosphate mannose; H3, B, H6 and H7, mannose-containing GPI precursors; H3′, B7, H6′ and H7′, GPI precursors converted from H3, B, H6 and H7, respectively, by KOH-treatment.\n\nFigure 4: Figure 4. Expression analysis in family B using qPCR. Expression analysis was performed using RPL30 as a control gene, and the results are normalized with respect to the first control individual. qPCRs were performed in triplicate and then the experiment was repeated three times. Error bars represent the standard deviations obtained across the three runs. The RNA used for this experiment was from whole blood samples extracted using the PAXgene blood RNA kit."
      }
    ]
  },
  {
    "id": "PMC4613317_multi",
    "image": [
      "images/PMC4613317-f1.png",
      "images/PMC4613317-f2.png",
      "images/PMC4613317-f3.png",
      "images/PMC4613317-f4.png",
      "images/PMC4613317-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Analysis of MicroRNA Expression Profiles in Weaned Pig Skeletal Muscle after Lipopolysaccharide Challenge\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Lipopolysaccharide (LPS)-induced acute inflammation and muscle protein degradation. (A) Plasma TNF-α concentrations in weanling pigs were measured 4 h after treatment with LPS or saline; and (B) TLR4, MyD88, TNF-α, MAFbx and MuRF1 mRNA expression were determined by qPCR in the skeletal muscles of weanling pigs 4 h after treatment with LPS or saline. *** p < 0.001 vs. saline control. TLR4: Toll-like receptor 4.\n\nFigure 2: Figure 2. Length distribution of sequencing reads in the six libraries.\n\nFigure 3: Figure 3. Distribution of total sequenced reads among various RNA classes in the six libraries.\n\nFigure 4: Figure 4. Top 10 most abundant miRNAs in the LPS-challenged and saline-treated groups, ordered by the average proportion of each miRNA read relative to total normalized miRNA reads.\n\nFigure 5: Figure 5. Predicted stem-loop secondary structures of four candidate novel pig miRNAs. Red: mature sequence; purple: star sequence with no reads cover; blue: star sequence with no reads covered; yellow: stem sequence."
      }
    ]
  },
  {
    "id": "PMC4613317_multi_2",
    "image": [
      "images/PMC4613317-f6.png",
      "images/PMC4613317-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Analysis of MicroRNA Expression Profiles in Weaned Pig Skeletal Muscle after Lipopolysaccharide Challenge\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. qPCR analysis of five selected miRNAs. qPCR was performed to verify expression of the five miRNAs in the same RNA samples used for RNA sequencing. Expression was normalized by U6. * p < 0.05, *** p < 0.001 vs. saline control.\n\nFigure 7: Figure 7. LPS upregulates the expression of miR-146a-5p and miR-221-5p in C2C12 myotubes. C2C12 myotubes were treated with 1000 ng/mL LPS for the indicated periods. Triplicate samples of cells were collected at each time point. RT-qPCR was performed to determine the time-dependent effects of LPS on the expression of TNF-α, IL-1β, MAFbx, MuRF1, miR-146a-5p and miR-221-5p. * p < 0.05, ** p < 0.01, *** p < 0.001 vs. 0 h."
      }
    ]
  },
  {
    "id": "PMC4633373_multi",
    "image": [
      "images/PMC4633373-f1.png",
      "images/PMC4633373-f2.png",
      "images/PMC4633373-f3.png",
      "images/PMC4633373-f4.png",
      "images/PMC4633373-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Ubiquitin Ligase Siah2 Regulates Obesity-induced Adipose Tissue Inflammation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Body weight (A), percent fat mass (B) and percent fat free mass (C) were measured in the Wild-type (WT) and Siah2KO mice fed a defined low (LFD) or high (HFD) fat diet over sixteen weeks. Food intake (D) and energy expenditure (E) were measured at twelve weeks on each diet. Dark bars indicate 7P-7A. (F) Regression analysis of energy expenditure (kcal/hr) related to body weight or fat free mass (lean mass) was carried out using the daily energy expenditure of each animal over 3 consecutive days. Activity and RER were also measured (Figure S1). Statistical significance compared to wild-type; *, p<0.05.\n\nFigure 2: Figure 2. (A) H&E staining of HFD Wild-Type and Siah2KO epididymal fat. (B) Adipocyte size (area) quantitated using Image J. iWAT, inguinal adipose tissue, eWAT, epididymal adipose tissue. (C) Adipocyte size distribution of epididymal adipocytes at two months on LFD or HFD analyzed using Coulter counting. (D) Wild-type (WT) and Siah2KO (KO) serum free fatty acids and triglyceride levels. (E) Insulin-dependent inhibition of lipolysis in isolated HFD Wild-type and Siah2KO epididymal adipocytes. Statistical significance compared to Wild-type; *, p<0.05; **, p<0.01; ***, p<0.001. LFD, low fat diet; HFD, high fat diet\n\nFigure 3: Figure 3. (A) Fasting blood glucose and (B) insulin levels assayed at 16 weeks on the LFD or HFD. (C) Glucose tolerance test and (D) GTT AUC and (E) insulin tolerance test and (F) ITT AUC at 12 weeks on each diet. Statistical significance compared to Wild-type; #, p<0.05 for low fat diet and *, p<0.05; **, p <0.01 for high fat diet.\n\nFigure 4: Figure 4. Wild-type (WT) and Siah2KO epididymal adipose tissue was evaluated using microarray analysis of gene expression. (A) Most significant biological functions affected by Siah2 determined by Ingenuity software analysis (B) Hierarchical clustering of the top 50 genes up or down-regulated by Siah2 in the low fat (LFD) or high fat (HFD) fed mice.\n\nFigure 5: Figure 5. Gene expression of markers of (A) inflammation, (B) cytokines and chemokines, and (C) T lymphocytes was assayed in the high-fat fed mice or (D) compared between the low fat and high fat fed mice using real-time qRT-PCR. Statistical significance compared to Wild-type; *, p<0.01; **, p <0.001."
      }
    ]
  },
  {
    "id": "PMC4633373_multi_2",
    "image": [
      "images/PMC4633373-f6.png",
      "images/PMC4633373-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The Ubiquitin Ligase Siah2 Regulates Obesity-induced Adipose Tissue Inflammation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Indicators of adipocyte dysfunction were assayed in epididymal adipose tissue from high-fat fed mice. (A) Extracellular matrix components were determined using real-time qRT-PCR. Statistical significance compared to Wild-type; *, p<0.05; **, p <0.01. (B) Fibrosis was determined using trichrome staining of collagen and crown-like structures were visualized using anti-Iba-1 immunostaining of macrophages. (C) Stress kinase activation was determined via western blot analysis. β-actin is included as a loading control.\n\nFigure 7: Figure 7. All measurements were carried out in epididymal adipose tissue from high-fat fed mice. (A) A subset of PPARγ target genes selected based on microarray analysis were analyzed via real-time qRT-PCR (B) Gene expression of PPARγ1, PPARγ2 or PPARγ1 and PPARγ2 combined. (C) Steady-state level of PPARγ proteins and selected Siah2 target proteins. (D) PPARγ protein levels from expanded number of mice. β-actin is included as a loading control in (C, D). (E) Quantification of PPARγ protein levels in (D). (F) Ubiquitin modification of PPARγ determined by western blot analysis of PPARγ (IP PPARγ, IB PPARγ) or ubiquitin (IP PPARγ, IB ubiquitin) after immunoprecipitation of PPARγ from Wild-type or Siah2KO epididymal adipose tissue. (G) Quantification of high molecular weight PPARγ ubiquitin conjugates. Statistical significance compared to Wild-type; *, p<0.05; **, p <0.01."
      }
    ]
  },
  {
    "id": "PMC4666198_multi",
    "image": [
      "images/PMC4666198-f1.png",
      "images/PMC4666198-f2.png",
      "images/PMC4666198-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Zellweger spectrum disorders: clinical overview and management approach\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic overview of main presenting symptoms in ZSDs per clinical group\n\nFigure 2: Figure 2. Craniofacial dysmorphic features in ZSD patients developing over time a. Photograph of a 6-month-old girl with typical craniofacial dysmorphia. Note the epicantal folds, high forehead, broad nasal bridge and hypoplastic supraorbital ridges. The anterior fontanel is drawn and enlarged. b-c. Girl with a ZSD at the age of 9 months (b) and at the age of 1 year and two months (c). Less pronounced facial dysmorphism is present: a high forehead is seen, a broad nasal bridge, hypoplastic supraorbital ridges, anteverted nares and more subtle epicantal folds. d-f. Photograph of a male with a ZSD at the age of 5 years (d), 10 years (e) and 15 years (f). No evident facial dysmorphic features can be recognized, although the ears seem to be slightly low-set. Written informed consent was obtained from the parents of all patients for publication of these images\n\nFigure 3: Figure 3. Diagnostic flow-chart for ZSDs. a Very long chain fatty acids: C26:0, C24:0/C22:0 ratio, C26:0/C22:0 ratio. b Single enzyme deficiency with phenotypical ZSD similarities like ACOX1 deficiency and DBP deficiency. c Next generation sequencing (NGS) of all PEX genes is advised when complementation analysis is not practicable"
      }
    ]
  },
  {
    "id": "PMC4673105_multi",
    "image": [
      "images/PMC4673105-f1.png",
      "images/PMC4673105-f2.png",
      "images/PMC4673105-f3.png",
      "images/PMC4673105-f4.png",
      "images/PMC4673105-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The biophysical properties of ethanolamine plasmalogens revealed by atomistic molecular dynamics simulations\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The chemical structures for the POPC, PE–plasmalogen, and PE–diacyl lipid species. The chain lengths and saturation degree of the sn-1 and sn-2 chains are marked below the chemical structures.\n\nFigure 2: Figure 2. Density profiles and simulation snapshots for each simulated system. (A) The density profiles for the lipid bilayer systems where whole lipid molecules are marked in black, water in blue, the phosphorous atoms of lipids in green, and the ester/ether oxygen atoms of lipids in red color. (B) Snapshot from the end of simulations. The coloring is the same as in the case of density profiles. The acyl chains of lipids are rendered using sticks, the phosphorous and ester/ether oxygen atoms are rendered as van der Waals spheres.\n\nFigure 3: Figure 3. Deuterium order parameters for the sn-1 and sn-2 chains as a function of acyl chain carbons. (top) The order parameters for the sn-1 chains. (bottom) The order parameters for the sn-2 chains. The errors are about the size of the markings.\n\nFigure 4: Figure 4. (A) The lipid head group and glycerol backbone orientations with respect to the bilayer normal. The vectors used in the analysis are shown on the right. (B) The lipid head group order parameters for the β, α, g1, g2 and g3 carbon hydrogens. The head group carbons analysed are shown in the right. The errors are about the size of the markings.\n\nFigure 5: Figure 5. The distances for the carbon pairs formed by the equivalent carbons of sn1- and sn-2 acyl chains. The carbon pairs are marked with numbers to the chemical structure of POPC displayed on the right."
      }
    ]
  },
  {
    "id": "PMC4726662_multi",
    "image": [
      "images/PMC4726662-f1.png",
      "images/PMC4726662-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Multiple Pathways for Protein Transport to Peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Model for import of peroxisomal matrix proteins containing a PTS1 in S. cerevisiae. (a) A newly synthesized PTS1-containing peroxisomal matrix protein is recognized in the cytosol by the receptor Pex5. (b) Cargo-loaded receptor docks onto the docking complex consisting of Pex13, Pex14 and Pex17. (c) Receptor inserts in the membrane in complex with Pex14 and cargo is released into the lumen. (d) The ubiquitin ligase complex (Pex2, Pex10 and Pex12) in conjunction with the ubiquitin conjugation complex (Pex4 and Pex22) modifies Pex5 on a cysteine residue. (e) Ubiquitinated Pex5 is extracted from the membrane by the extraction complex (Pex1, Pex6 and Pex15) and (f) subsequently deubiquitinated for another round of targeting.\n\nFigure 2: Figure 2. Models for PMP import pathways. PMPs are either inserted directly from the cytosol into the peroxisomal membrane (a–c) or inserted into the ER and subsequently sorted to peroxisomes (d–f). (a) The main mechanism of direct import of PMPs into peroxisomes dependent on Pex3 and Pex19. Pex19 acts as the cytosolic chaperone while Pex3 is the membrane anchor. Some PMPs have multiple mPTS sequences that likely bind multiple Pex19 to allow for the import of multi-membrane spanning PMPs. This mechanism seems universal. (b) Direct insertion of Pex3 into the peroxisomal membrane dependent upon Pex16 and Pex19 in mammals. (c) Similar to other PMPs, TA PMPs are inserted directly via the Pex3/Pex19 complex in mammals. (d) Insertion of Pex3 and other PMPs into the ER via the ER translocon. This process has been shown in S. cerevisiae. It is not known whether a cytosolic chaperone is required for this process. (e) In mammalian cells, Pex3 insertion into the ER requires Pex16. (f) TA PMPs in S. cerevisiae have been shown to use the Get complex. However, the mammalian homologue TRC40 complex is not involved in the import of TA PMPs."
      }
    ]
  },
  {
    "id": "PMC4729952_multi",
    "image": [
      "images/PMC4729952-f1.png",
      "images/PMC4729952-f2.png",
      "images/PMC4729952-f3.png",
      "images/PMC4729952-f4.png",
      "images/PMC4729952-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Metabolic Interplay between Peroxisomes and Other Subcellular Organelles Including Mitochondria and the Endoplasmic Reticulum\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic diagram showing the functional interplay between peroxisomes and mitochondria in the beta-oxidation of fatty acids in peroxisomes. See text for detailed discussion.\n\nFigure 2: Figure 2. Etherphospolipid biosynthesis and the important role of peroxisomes and the endoplasmic reticulum. (A) Schematic representation of the peroxisome and the enzymes and transporters involved in the peroxisomal synthesis of alkyl-DHAP. (B) Schematic representation of the peroxisome and the enzymes and transporters involved in the peroxisomal synthesis of alkyl-DHAP with special emphasis on the sub-peroxisomal localization of GNPAT and AGPS as peripheral peroxisomal membrane proteins joined together in a functional complex. (C) Overview of the reactions catalyzed by the three intraperoxisomal enzymes involved in etherphospholipid synthesis including GNPAT, AGPS, and ACSVL1 (SLC27A2). G3P, glycerol-3-phosphate; DHAP, dihydroxyacetonephosphate; GNPAT, glyceronephosphate O-acyltransferase; AGPS, alkyl-glyceronephosphate synthase; FAR1, fatty acyl-CoA reductase 1.\n\nFigure 3: Figure 3. Peroxisomes, fatty acid beta-oxidation and the human deficiencies of peroxisomal beta-oxidation. (A) Schematic diagram depicting the substrates known to be oxidized in peroxisomes exclusively and the transporters and enzymes involved in their degradation (see text for detailed information). (B) Schematic diagram depicting the substrates known to be oxidized in peroxisomes exclusively and the transporters and enzymes involved in their degradation and the human deficiencies in the peroxisomal beta-oxidation pathway so far identified (see text for more information).\n\nFigure 4: Figure 4. Schematic diagram depicting the peroxisomal enzymes involved in the degradation of very long-chain fatty acids (VLCFAs), pristanic acid, di- and trihydroxycholestanoic acid, and long-chain dicarboxylic acids. See text for detailed information.\n\nFigure 5: Figure 5. Functional interplay between peroxisomes and mitochondria with respect to the reoxidation of NADH produced within the peroxisomal beta-oxidation system. (A) S. cerevisiae (see text for detailed information). (B): H. sapiens. PYR, pyruvate; LAC, lactic acid; LDH, lactate dehydrogenase; GOT, glutamate oxaloacetate transaminase; ASP, L-aspartate, GLUT, L-glutamate; 2OG, 2-oxoglutarate; MDH1, mitochondrial malate dehydrogenase."
      }
    ]
  },
  {
    "id": "PMC4729952_multi_2",
    "image": [
      "images/PMC4729952-f6.png",
      "images/PMC4729952-f7.png",
      "images/PMC4729952-f8.png",
      "images/PMC4729952-f9.png",
      "images/PMC4729952-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Metabolic Interplay between Peroxisomes and Other Subcellular Organelles Including Mitochondria and the Endoplasmic Reticulum\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Functional interplay between peroxisomes and mitochondria in the oxidation of C26:0. See text for detailed information. ALDP, adrenoleukodystrophy protein; TE, acyl-CoA thioesterase; CrOT, carnitine octanoyltransferase; CrAT, carnitine acetyltransferase; CACT, mitochondrial carnitine: acylcarnitine translocase.\n\nFigure 7: Figure 7. Schematic diagram showing the key role of peroxisomes in the formation of C22:6 n-3. Doxosahexaenoic acid is synthesized from C18:3 n-3 which first undergoes a number of elongation and desaturation steps in the endoplasmic reticulum to produce C24:6-CoA which is then transported to the peroxisome and imported via a mechanism not yet resolved. Within peroxisomes C24:6-CoA undergoes one cycle of beta-oxidation to produce the corresponding C22:6-CoA which can then be exported out of the peroxisome for subsequent incorporation into lipids in the endoplasmic reticulum or may undergo additional sequential rounds of oxidation in peroxisomes and mitochondria. See text for more detailed information.\n\nFigure 8: Figure 8. Schematic diagram showing the unique and important role of peroxisomes in the formation of the primary bile acids cholic acid and deoxycholic acid. See text for detailed information.\n\nFigure 9: Figure 9. Functional interplay between mitochondria and peroxisomes in the alpha-oxidation of phytanic acid. See text for detailed information.\n\nFigure 10: Figure 10. The detoxification of glyoxylate in peroxisomes as catalyzed by the enzyme alanine glyoxylate aminotransferase (AGXT)."
      }
    ]
  },
  {
    "id": "PMC4762939_multi",
    "image": [
      "images/PMC4762939-f1.png",
      "images/PMC4762939-f2.png",
      "images/PMC4762939-f3.png",
      "images/PMC4762939-f4.png",
      "images/PMC4762939-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Sterol Carrier Protein-2, a Nonspecific Lipid-Transfer Protein, in Intracellular Cholesterol Trafficking in Testicular Leydig Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Confocal laser microscopy images of MA-10 cells stained with 22-NBD-cholesterol (left), transfected with mito-DsRed-pero (center), and the overlap of 22-NBD-cholesterol and mito-DsRed-pero staining (right). (B) Comparison of the fluorescence intensity profiles of the mitochondria and peroxisomes (P) in red, and of 22-NBD-cholesterol in green. 22-NBD-cholesterol (green) does not localize with the mito-DsRed-pero tagged peroxisomes, shown as the small high-intensity dots (red), in the MA-10 cell line. The areas where the fluorescence intensities of the 22-NBD-cholesterol and peroxisomes do not correlate are marked by red stars. (C) Colocalization of 22-NBD-cholesterol (green) with DsRed-pero (red), a peroxisomal marker. The panels on the right of the image show the highlighted region with overlapped green and red channels, the green channel only, and the red channel only (from top to bottom). (D) Colocalization of 22-NBD-cholesterol (green) with TSPO-DsRed (red), a mitochondrial marker. The panels on the right of the image show the highlighted region with overlapped green and red channels, the green channel only, and the red channel only (from top to bottom).\n\nFigure 2: Figure 2. The sequence alignment shows that the Scp2 gene encodes the SCPX and pro-SCP2 proteins, both of which contain the sequence for the SCP2 protein or domain at the C-terminal end. The predicted mitochondrial targeting sequences (mito-seqs or presequences), peroxisomal targeting PTS1 signal (PTS1 [P]), and CRAC motifs following a L/V-(X)1–5-Y-(X)1–5-R/K pattern in SCPX and SCP2 are indicated. The red upward arrow indicates the start of the predicted SCP2 sequence (GenBank ID: M62361 for mouse and M55421 for human), containing a proposed mito-seq highlighted in the dotted square.\n\nFigure 3: Figure 3. (A) RNA-Seq data show that the Scp2 and Scpx transcripts have low expression in the MA-10 cell line. (B) No transcripts were seen at the control locus for the Scp2d1 gene, used as a negative control in the RNA-seq. (C) A detailed look at the first exon of the Scp2 gene shows the low expression levels of this exon, and illustrates the B2-derived promoter located just prior to the gene. (D) A detailed look at the first exon of the Scpx shows the low expression levels of this exon.\n\nFigure 4: Figure 4. The analysis was performed to investigate the endogenous distribution of SCPX and SCP2 in the wild-type mouse testis. (A–B) SCPX is highly expressed in the interstitial connective tissue of the mouse testis, an area rich in Leydig cells, but is not expressed in the germ cells in the seminiferous tubules. (C–D) SCP2 was found to have the same distribution as SCPX, but with a lower level of expression. Scale bar, 50 μm.\n\nFigure 5: Figure 5. (A) Double immunofluorescent staining of endogenous SCPX in MA-10 cells (red), PMP70 (peroxisomal marker protein, painted in green), and VDAC1 (mitochondrial marker protein, painted in green). The nucleus was counterstained with DAPI (painted in green). Scale bar, 5 μm. (B) Immunoblot analysis of endogenous SCPX in subcellular fractions of MA-10 cell lysates. COXIV is used as a mitochondrial marker protein, and GAPDH is used as a whole cell lysate loading control. M, the protein marker, indicated in kDa; Total, whole cell lysate; Cyto, cytosolic fraction; Mito, mitochondrial-enriched fraction. (C) Double immunofluorescent staining of endogenous SCP2 in MA-10 cells (red), PMP70 (painted in green), and VDAC1 (painted in green). The nNucleus was counterstained with DAPI (painted in green). Scale bar, 5 μm. (D) Immunoblot analysis of endogenous SCP2 in subcellular fractions of MA-10 cell lysates. VDAC1 is used as a mitochondrial marker protein, and GAPDH is used as a whole cell lysate loading control. (E–F) Immunoblot analysis of the isolated MA-10 subcellular fractions identifying mitochondrial matrix protein HSP60 (E) and peroxisomal matrix protein catalase (CAT) (F). GAPDH is used as a loading control. M, the protein marker, indicated in kDa; Total, whole cell lysate; Cyto, cytosolic fractions; Mito, mitochondrial-enriched fraction."
      }
    ]
  },
  {
    "id": "PMC4762939_multi_2",
    "image": [
      "images/PMC4762939-f6.png",
      "images/PMC4762939-f7.png",
      "images/PMC4762939-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Sterol Carrier Protein-2, a Nonspecific Lipid-Transfer Protein, in Intracellular Cholesterol Trafficking in Testicular Leydig Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A–H) Both ECFP–SCPX (A–D) and ECFP–SCP2 (E–H) fusion proteins were co-transfected with the mito-DsRed-pero. a dual peroxisomal and mitochondrial marker. The overlap indicates the localization of the ECFP–SCPX and ECFP-SCP2 proteins in the peroxisomes (shown by white arrows). Scale bar, 5 μm. (I–J) Both SCPX–ECFP (I) and SCP2–ECFP (J) proteins were co-transfected with the mito-DsRed-pero. When the peroxisomal-targeting signal was blocked, both SCPX–ECFP and SCP2-ECFP become widespread in the cytosol, and SCP2–ECFP is also distributed in the nucleus. Scale bar, 2 μm. (K) Transfection of the ECFP-N1 vector alone with nucleic acid staining using Hoechst 33342. Scale bar, 5 μm. (L–M) Immunofluorescent staining of the endogenous SCPX and SCP2 in MA-10 cells using SCPX- and SCP2-specific antibodies, where the nuclear staining of SCP2 is indicated by white arrows. (N) Colocalization of the mito-DsRed-pero fluorescent fusion protein with a peroxisomal membrane marker AmCyan-Pex11α, indicating the peroxisomal localization of mito-DsRed-pero, in addition to its mitochondrial localization.\n\nFigure 7: Figure 7. (A) Sequence alignment of the predicted mitochondrial targeting sequences of SCPX (SCPX-mito) and SCP2 (SCP2-mito) compared to ACBD2 (ACBD2-mito), a known mitochondrial protein. (B-E) Live-cell imaging of the subcellular localization of SCPX-mito-EGFP (B-C) and SCP2-mito-EGFP (D-E) fluorescent fusion proteins (green) with ACBD2-mito-DsRed as a positive control (red). White arrow, indicating unstained mitochondria in B and D and the same mitochondria stained with ACBD2-mito-DsRed in C and E, respectively. Scale bar, 5 μm.\n\nFigure 8: Figure 8. (A–B) Molecular docking study using homology models based on the X-ray crystallography structure of the rabbit SCP2 (PBD: 1C44). (C–D) Molecular docking study using homology models based on the NMR structure of the human SCP2 (PBD: 1QND). (E–F) Molecular docking study using homology models based on the X-ray crystallography structure of the ligand-bound SCP2-like domain of human peroxisomal multifunctional enzyme type 2 (MFE-2; PDB: 1IKT). Cholesterol (Chol), 22-NBD-cholesterol (22-NBD-Chol), the Trp70 residue responsible for binding cholesterol, and the peroxisomal-targeting PTS1 signal (-AKL) are indicated. The calculated docking affinity (kcal/mol) from Autodock-Vina is indicated under each corresponding conformation."
      }
    ]
  },
  {
    "id": "PMC4784967_multi",
    "image": [
      "images/PMC4784967-f1.png",
      "images/PMC4784967-f2.png",
      "images/PMC4784967-f3.png",
      "images/PMC4784967-f4.png",
      "images/PMC4784967-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogen Augmentation Reverses Striatal Dopamine Loss in MPTP Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Effect of MPTP and PPI-1011 treatment on striatal A) dopamine (DA) contents (F4,46 = 5.91, p = 0.0006) and its metabolites B) 3,4-dihydroxyphenylacetic acid (DOPAC) (F4,46 = 6.17, p = 0.0005), C) 3-methoxytyramine (3-MT) (F4,46 = 3.90, p = 0.008), and D) homovanillic acid (HVA) (F4,46 = 9.32, p < 0.0001), as well as E) DOPAC/DA (F4,46 = 1.16, p = 0.34), and F) 3-MT/DA (F4,46 = 3.03, p = 0.03) and G) HVA/DA (F4,46 = 3.08, p = 0.02) ratios. Values shown are the means (ng/mg of proteins) ± S.E.M. of 9–12 mice per group. * p < 0.05, ** p < 0.01 and *** p < 0.001 vs control; † p < 0.05, †† p < 0.01, ††† p < 0.001 and †††† p < 0.0001 vs MPTP.\n\nFigure 2: Figure 2. Effect of MPTP and PPI-1011 treatment on striatal A) serotonin (F4,46 = 4.04, p = 0.007) contents and its metabolite B) 5-hydroxyindoleacetic acid (5-HIAA) (F4,46 = 19.83, p < 0.0001), as well as C) 5-HIAA/serotonin (F4,46 = 7.04, p = 0.0002) ratio. Values shown are the means (ng/mg of proteins) ± S.E.M. of 9–12 mice per group. * p < 0.05, ** p < 0.01, *** p < 0.001 and **** p < 0.0001 vs control; † p < 0.05, †† p < 0.01 ††† p < 0.001 and †††† p < 0.0001 vs MPTP.\n\nFigure 3: Figure 3. Examples A) and effect of MPTP and PPI-1011 treatment in mice on DAT ([125I]-RTI) specific binding in B) striatum (F4,44 = 5.51, p = 0.001) and C) substantia nigra (F4,44 = 1.15, p = 0.35) as well as VMAT2 ([3H]-TBZ-OH) specific binding in D) striatum (F4,44 = 4.05, p = 0.007) and E) substantia nigra (F4,44 = 0.24, p = 0.91). Values shown are the means (fmol/mg of tissue) ± S.E.M. of 9–12 mice per group. ** p < 0.01 and *** p < 0.001 vs control; † p < 0.05 vs MPTP.\n\nFigure 4: Figure 4. Correlations between dopamine (DA) contents and A) DAT and B) VMAT2 specific binding, as well as C) between DAT and VMAT2 specific binding in mice treated with MPTP and PPI-1011.\n\nFigure 5: Figure 5. Effect of MPTP and PPI-1011 treatment in mice on total serum levels of A) 16:0 plasmalogens (F4,46 = 5.29, p = 0.001) and B) 18:0 plasmalogens (F4,46 = 4.15, p = 0.006) as well as in brain tissue of C) 16:0 plasmalogens (F4,53 = 0.78, p = 0.78) and D) 18:0 plasmalogens (F4,53 = 0.40, p = 0.89). Values shown are the means (relative to controls) ± S.E.M. of 9–12 mice per group. * p < 0.05 and ** p < 0.01 vs control; † p < 0.05, †† p < 0.01and ††† p < 0.001 vs MPTP."
      }
    ]
  },
  {
    "id": "PMC4784967_multi_2",
    "image": [
      "images/PMC4784967-f6.png",
      "images/PMC4784967-f7.png",
      "images/PMC4784967-f8.png",
      "images/PMC4784967-f9.png",
      "images/PMC4784967-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogen Augmentation Reverses Striatal Dopamine Loss in MPTP Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Correlations between the levels of serum plasmalogens A) 16:0/22:6, B) 18:0/18:1 and C) 18:0/20:4 and striatal dopamine (DA) concentrations as well as D) correlation between total serum plasmalogen levels and DA content.\n\nFigure 7: Figure 7. Effect of MPTP and PPI-1011 treatment on striatal A) DA contents (F4,49 = 15.76, p < 0.0001) and its metabolites B) DOPAC (F4,49 = 10.53, p < 0.0001), C) 3-MT (F4,49 = 5.59, p = 0.0009) and D) HVA (F4,49 = 6.20, p = 0.0004), as well as E) DOPAC/DA (F4,49 = 4.87, p = 0.002), F) 3-MT/DA (F4,49 = 3.92, p = 0.008) and G) HVA/DA (F4,49 = 8.60, p < 0.0001) ratios. Values shown are the means (ng/mg of proteins) ± S.E.M. of 9–14 mice per group. * p < 0.05, ** p < 0.01, *** p < 0.001 and **** p < 0.0001 vs control; † p < 0.05 vs MPTP.\n\nFigure 8: Figure 8. Effect of MPTP and PPI-1011 treatment on striatal A) serotonin (F4,49 = 2.66, p = 0.04) contents and its metabolite B) 5-hydroxyindoleacetic acid (5-HIAA) (F4,49 = 3.52, p = 0.01), as well as C) 5-HIAA/serotonin (F4,49 = 7.05, p = 0.0001) ratio. Values shown are the means (ng/mg of proteins) ± S.E.M. of 9–14 mice per group. * p < 0.05, ** p < 0.01 and *** p < 0.001 vs control.\n\nFigure 9: Figure 9. Examples A) and effect of MPTP and PPI-1011 treatment in mice on DAT ([125I]-RTI) specific binding in B) striatum (F4,46 = 15.17, p <0.0001) and C) substantia nigra (F4,49 = 1.55, p = 0.20) as well as VMAT2 ([3H]-TBZ-OH) specific binding in D) striatum (F4,48 = 16.44, p < 0.0001) and E) substantia nigra (F4,47 = 0.27, p = 0.90). Values shown are the means (fmol/mg of tissue) ± S.E.M. of 8–14 mice per group. ** p < 0.01, *** p < 0.001 and **** p < 0.0001 vs control; †† p < 0.01 vs MPTP.\n\nFigure 10: Figure 10. Correlations between dopamine (DA) contents and A) DAT and B) VMAT2 specific binding, C) between DAT and VMAT2 specific binding in mice treated with MPTP and PPI-1011 as well as correlation D) between the serum level of plasmalogen 16:0/22:6 in serum and striatal DA contents."
      }
    ]
  },
  {
    "id": "PMC4787756_multi",
    "image": [
      "images/PMC4787756-f1.png",
      "images/PMC4787756-f2.png",
      "images/PMC4787756-f3.png",
      "images/PMC4787756-f4.png",
      "images/PMC4787756-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The ubiquitin ligase HERC3 attenuates NF-κB-dependent transcription independently of its enzymatic activity by delivering the RelA subunit for degradation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. HERC3 suppresses NF-κB transcriptional activity. (A) BAEC and RelA−/− 3T3 were transfected with κB-luciferase reporter (200 ng) and CMV-β-galactosidase control (40 ng) plasmids together with RelA (20 ng) and increasing amounts of HERC3 (BAEC: 80, 160 and 320 ng; RelA−/- 3T3: 35, 70 and 140 ng). Luciferase activities were measured 3 days after transfection and normalized to β-galactosidase activities. Bars represent mean + SEM (n = 9, derived from 3 independent experiments). RelA-induced reporter activity was set to 100 and activity of all other data sets was calculated relative to this value. (B) Assay was carried out in RelA−/− 3T3, transfected as in (A) with different NF-κB decameric consensus binding sites and constant amounts of HERC3. Sites were derived from the human IL8, ICAM1, IκBα and MHC class I enhancer sequences. (C) BAEC were transfected with reporter plasmids, control vector or HERC3, and either left untreated or 2 days later stimulated with TNF for 16 h. Bars represent mean + SEM (n = 12, derived from four independent experiments). TNF-induced reporter activity without HERC3 co-expression was set to 100. (D) BAEC transiently transfected with control, RelA or RelA plus HERC3 were harvested, RNA was isolated and expression levels of endogenous Icam1, Vcam1, Sele and IκBα were evaluated by qRT-PCR. Expression levels of control-transfected cells were set to 1, and relative induction for all other experimental groups was calculated. Bars represent mean + SEM (n = 5, derived from 5 independent experiments). In all experiments appropriate protein expression was monitored by Western Blotting (see Supplementary Figure S1A–D). Data were considered significant at *P < 0.05. RLU, relative luciferase units.\n\nFigure 2: Figure 2. HERC3 reduces NF-κB DNA-binding by limiting its nuclear import. (A) BAEC were transfected with control vector or myc-HERC3, stimulated for 0, 0.5 or 1 h with TNF or TNF/LMB and processed for immunofluorescence. Nuclei were stained with DAPI. Bar represents 10 μm. The graph shows ratios of cytosolic and nuclear fluorescence obtained by automatic quantification of RelA compared to DAPI staining (n = 61–147 cells, derived from 2–3 experiments). Values N/C > 1 indicate predominantly nuclear RelA. (B) Subcellular localization of GFP-LacZ harboring a SV40-derived nuclear localization sequence (NLS) was tested in absence and presence of myc-HERC3 in BAEC. GFP-LacZ, not containing an active NLS, was used as control. DAPI staining served as nuclear reference. Size bar = 10 μm. Data from 18–33 cells for each condition, derived from two independent experiments, were quantified. Percent of nuclear GFP staining was: for GFP-LacZ –HERC3 0 ± 0; +HERC3 0.12 ± 0.02, and for GFP-SV40NLS-LacZ –HERC3 100 ± 0; +HERC3 100 ± 0. (C) RelA DNA-binding in absence and presence of HERC3 was observed by electrophoretic mobility shift assay (EMSA). Total cell extracts from transfected BAEC were incubated with double-stranded purified γ-32P ATP-labeled Igκ light chain enhancer oligonucleotide. Protein–DNA complexes were separated on 5% Tris/glycine/EDTA-PAGE, bands were visualized by autoradiography and results from three experiments were quantified. Equal RelA protein expression with and without HERC3 was ensured by parallel observation of protein levels by Western Blotting (see Supplementary Figure S1E). (D) RelA binding was verified by competition with either non-labeled sense oligonucleotide (co Ig κB) or non-labeled scrambled oligonucleotide (co sc Ig κB), and by super-shift with RelA antibody. Experiments were performed in triplicates. The arrows in (C) and (D) indicate the specific NF-κB band. Values were considered significant at *P < 0.05. h, hours.\n\nFigure 3: Figure 3. HERC3 has no effect on IκBα degradation. (A) IκBα turnover was monitored in HEK293T cells transfected with empty vector, myc-HERC3 or flag-dnIKK2 after stimulation with 10 ng/ml TNF for 0, 20 or 60 min. Where indicated cells were pre-treated with 50 μM MG132. Presence of transfected proteins was verified by immunoblotting with myc- or flag-specific antibodies. (B) HEK293T cells were transfected with HA-IκBα together with either empty vector or myc-HERC3. Cells were treated with 10 ng/ml TNF for 20 min and where indicated pre-treated for 3 h with 50 μM MG132. IκBα was pulled down from cell lysates with HA-coupled agarose and its ubiquitination was assessed by detection with an anti-ubiquitin antibody. All experiments were carried out in triplicates. HC, heavy chain; IB, immunoblot; IP, immunoprecipitation; min, minutes.\n\nFigure 4: Figure 4. HERC3 interacts with RelA and mediates its ubiquitination. (A) RelA was precipitated with RelA antibody from total HEK293T cell lysates transfected with myc-RelA and myc-HERC3. RelA and HERC3 co-precipitation was assessed by Western Blotting with anti-myc antibody. (B) HEK293T cells were transfected with HA-RelA and myc-HERC3. HERC3 was pulled down from cell lysates with myc-specific antibody and RelA was detected in the precipitate with anti-RelA antibody. (C) HEK293T were transfected with myc-RelA, his-ubiquitin and myc-HERC3. Ubiquitinated RelA was detected by pull down of his-ubiquitin under denaturing conditions, followed by Western Blotting with RelA-specific antibody. (D) BAEC were transfected with his-ubiquitin and myc-HERC3. After 24 h cells were treated with TNF for 30 min and assay was performed as described in (C). All experiments were carried out in triplicates. IB, immunoblot; IP, immunoprecipitation.\n\nFigure 5: Figure 5. HERC3 mediates RelA K48 ubiquitination and protein destabilization. (A) His-ubiquitin, myc-RelA, with or without myc-HERC3 were transiently introduced into HEK293T cells. RelA was precipitated from whole cell lysates with RelA-specific antibody and the nature of RelA ubiquitination was examined by Western Blotting with anti-ubiquitin antibodies recognizing total, K48 or K63 ubiquitin, respectively. (B) HEK293T cells were transfected with myc-RelA with or without myc-HERC3. Twenty four hours after transfection, cells were pulse-labeled with [35S]-methionine for 1 h and chased for 0, 2, 4 and 8 h. RelA was precipitated from total cell extracts with myc-affinity agarose, and protein levels were detected by autoradiography. (C) RelA was precipitated from transfected BAEC total cell extracts after pulse-labeling with [35S]-methionine for 1 h and chasing for 0 and 8 h. Protein levels in precipitates were assessed by separation on SDS-PAGE and autoradiography. Average percent protein remaining before and after chase is indicated. All experiments were carried out at least in triplicates. h, hours; IB, immunoblot; IP, immunoprecipitation."
      }
    ]
  },
  {
    "id": "PMC4787756_multi_2",
    "image": [
      "images/PMC4787756-f6.png",
      "images/PMC4787756-f7.png",
      "images/PMC4787756-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The ubiquitin ligase HERC3 attenuates NF-κB-dependent transcription independently of its enzymatic activity by delivering the RelA subunit for degradation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. HERC3 affects RelA ubiquitination independently of its catalytic domains as part of a larger molecular weight complex. (A) Schematic representation of HERC3 constructs used in (B and C). (B) Transcriptional activity of RelA was examined in presence of different HERC3 constructs as described in Figure 1A. Bars represent mean + SEM (n = 9–18, derived from 3–6 independent experiments). Values were significant at *P < 0.05. (C) HEK293T cells were transfected with his-ubiquitin, myc-RelA and indicated myc-HERC3 wild type, mutant or truncation constructs. Ubiquitinated RelA was pulled down with Ni-agarose beads bound to his-tagged ubiquitin and detected in immunoblotting with a RelA-specific antibody. (D) HEK293T cells were transfected with flag-RelA alone, flag-RelA and myc-HERC3 or flag-HERC3 alone. Lysates were subjected to precipitation with flag-agarose beads, followed by flag-peptide elution. Eluates were loaded on 3–12% Native Bis-Tris Gels and separated by Blue Native Polyacrylamide Gel Electrophoresis (BN-PAGE). (E) HEK293T cell transfection, lysate precipitation and elution were performed as outlined in (D). Eluates were loaded on a Sephacryl S-300 HiPrep 16/60 column for size exclusion chromatography (SEC). Thyroglobulin, aldolase and ovalbumin with calculated relative molecular masses (Mr) of 669, 158 and 44, respectively, served as molecular weight indication. All experiments were carried out in triplicates. aa, amino acids; CA, cysteine to alanine; ev, empty vector; FR, fraction; IB, immunoblot; IP, immunoprecipitation; Mr, relative molecular mass; RLU, relative luciferase units; V0, column void volume; wt, wild type.\n\nFigure 7: Figure 7. HERC3/RelA associate with the ubiquitin-like protein UBQLN1 and the 26S proteasome. (A) List of ubiquitination/degradation-associated proteins found by MS/MS analysis to bind to HERC3/RelA. (B) HEK293T cells transfected with indicated constructs were lysed and immunoprecipitation was performed with myc-specific antibody to pull down HERC3. RelA, PSMC2 and PSMA4 co-association was detected with specific antibodies recognizing these proteins. (C) HEK293T cells were transfected with control, myc-RelA, myc-HERC3 or myc-RelA/myc-HERC3 together. The endogenous proteasomal subunit PSMD4 was precipitated with PSMD4 antibody and association of RelA and HERC3 was tested in Western Blotting with respective antibodies. (D) HA-RelA, flag-tagged UBQLN1 and myc-HERC3 were introduced into HEK293T cells. Association of HERC3 and RelA, as well as the proteasomal subunit PSMC2 with UBQLN1 was tested by immunoprecipitation of UBQLN1 with flag-beads, followed by Western Blot detection. All experiments were performed 3 times. The asterisks mark the heavy chain detected by Western Blotting after immunoprecipitation. IB, immunoblot; IP, immunoprecipitation.\n\nFigure 8: Figure 8. HERC3 and UBQLN1 conjointly affect NF-κB activity by linking RelA to the proteasome and promoting its degradation. (A) UBQLN1 expression was knocked down by siRNA transfection into HEK293T cells. At the same time myc-HERC3 and HA-RelA were introduced and interaction between these two proteins was studied by co-immunoprecipitation approach. Association of endogenous proteasomal subunits PSMC2 and PSMA4 was also tested. The asterisks point out the antibody heavy chains detected by Western Blotting after pull down. (B) HEK293T were transfected with siRNA targeting UBQLN1, myc-HERC3 and myc-RelA. Binding of proteins to RelA was examined by pull down with anti-RelA antibody and detection of HERC3 and PSMC2 by Western Blotting. (C) Stability of RelA protein in presence of HERC3 and absence of UBQLN1 was determined in HEK293T by metabolic labeling as described in Figure 5B. Results from 4 independent experiments were quantified. Average percent of protein before and after chase is noted on top of the respective graph columns. (D) Endogenous RelA protein stability was assessed in HUVEC exposed to siRNA targeting HERC3 and/or UBQLN1. Non-targeting siRNA was used as control. HUVEC were incubated in [35S]-methionine-containing growth medium for 2 h on day 3 after siRNA exposure. Pulse medium was removed and cells were left in culture for another 7 h in normal growth medium substituted with 10 ng/ml TNF. HUVEC were harvested and RelA was precipitated from total cell extracts with RelA-specific antibody. Data from four experiments were plotted on a graph. Average percent protein remaining before and after chase is indicated. (E) HUVEC transfected with non-targeting control or Herc3/Ubqln1-targeting siRNAs were stimulated with 10 ng/ml TNF for 0, 0.5 and 6 h. Protein levels of endogenous RelA, HERC3, UBQLN1 and β-actin were determined. Shown blots are representative of 2 independent experiments. (F) mRNA expression of three NF-κB-regulated genes Icam1, Vcam1 and Sele was examined in siRNA-treated HUVEC. Three days after siRNA exposure NF-κB-dependent transcription was stimulated with TNF for 6 and 16 h. RNA was isolated and gene expression was assessed by qRT-PCR. HERC3 and UBQLN1 knock down efficiency was tested in un-stimulated cells and plotted in the first two panels. Data were normalized to each group and represent mean +SEM from 5–9 independent experiments. Values were considered significant at *P < 0.05. IB, immunoblot; IP, immunoprecipitation; si, small interfering RNA."
      }
    ]
  },
  {
    "id": "PMC4792581_multi",
    "image": [
      "images/PMC4792581-f1.png",
      "images/PMC4792581-f2.png",
      "images/PMC4792581-f3.png",
      "images/PMC4792581-f4.png",
      "images/PMC4792581-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"PPARα induces cell apoptosis by destructing Bcl2\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A. Western blot analysis of SW480 cells transfected with control or PPARα shRNA. B. Bcl2 protein half-life was assayed by using CHX (30 μg/ml) in SW480 cells transfected with control or PPARα shRNA. The relative remaining Bcl2 protein levels following CHX treatment at each time point was calculated accordingly. C, D. HEK293T cells were transfected with plasmids as indicated. Cell lysates were subjected to Western blot. E. HeLa cells were transfected with vector, PPARα for 36 h. Cells were treated with or without 10 μM MG132 for 6 h before cell lysis. Cell lysates were subjected to Western blot. F. Bcl2 protein half-life was assayed by using CHX (30 μg/ml) in HEK293T cells transfected with vector or PPARα plasmid. The relative remaining Bcl2 protein levels following CHX treatment at each time point was calculated accordingly.\n\nFigure 2: Figure 2. A, B. HEK293T cells were transfected plasmids as indicated for 36 h. Cell lysates were subjected to denatured immunoprecipitation and Western blot. Cells were treated with MG132 (10 μM) for 6 h before cell lysis. C. SW480 cells were transfected with control or PPARα shRNA. Cell lysates were subjected to denatured immunoprecipitation and Western blot. D. In vitro polyubiquitin formation analysis was performed in reaction buffer contained different E2 (UbcH3, UbcH5a, b, c) with PPARα as indicated. Reactions were incubated at 30°C for 2 h. The ubiquitinated products were detected with ubiquitin antibody. E. Ni-NTA pull-down assay was performed to detect the interaction of PPARα with recombinant UbcH3. F. In vitro Bcl2 ubiquitination analysis was performed in the reaction buffer contained UbcH3, Bcl2 (10 μg) and 10 ng PPARα (WT or C102A) as indicated. Reactions were incubated at 30°C for 2 h. The ubiquitinated products were detected with Bcl2 antibody. G. HEK293T cells were transfected with vector, PPARα, or PPARα/C102A plasmids as indicated. Cell lysates were subjected to denatured immunoprecipitation and Western blot. Cells were treated with MG132 (10 μM) for 6 h before cell lysis. H. Bcl2 protein half-life was assayed by using CHX (30 μg/ml) in HEK293T cells transfected with PPARα or PPARα/C102A plasmids. The relative remaining Bcl2 protein levels following CHX treatment at each time point was calculated accordingly.\n\nFigure 3: Figure 3. A. Cell lysates were subjected to immunoprecipitation and Western blot. B. HEK293T cells were transfected with vector or PPARα plasmids. Cell lysates were subjected to immunoprecipitation and Western blot. C. up panel shows the construct of Bcl2 protein. HEK293T cells were transfected with vector, Bcl2 wild type (WT) or mutant plasmids as indicated. Cell lysates were subjected to immunoprecipitation and Western blot. Cells were treated with MG132 (10 μM) for 6 h before cell lysis. D. HEK293T cells were transfected with vector, PPARα, PPARα/C102A mutant for 36 h. Cell lysates were subjected to immunoprecipitation and Western blot. Cells were treated with MG132 (10 μM) for 6 h before cell lysis.\n\nFigure 4: Figure 4. A. construct of Bcl2 and the lysine sites. B. HEK293T cells were transfected with plasmids as indicated. Cell lysates were subjected to denatured immunoprecipitation and Western blot. Cells were treated with MG132 (10 μM) for 6 h before cell lysis. C. HEK293T cells were transfected with plasmids as indicated. Cell lysates were subjected to Western blot. D. Bcl2 protein half-life was assayed by using CHX (30 μg/ml) in SW480 cells transfected with Bcl2 or Bcl2/K22R plasmids. The relative remaining Bcl2 protein levels following CHX treatment at each time point was calculated accordingly.\n\nFigure 5: Figure 5. A. PPARα shRNA silenced SW480 cells were treated with chemotherapy drugs (camptothecin, taxol, etoposide, cisplatinum) as indicated for 24 h. Cell viability was assayed (see experimental procedures). Results are expressed as means ± SEM (n = 3). B. SW480 cells were transiently transfected with vector, PPARα, C102A plasmids as indicated. Cells were treated with chemotherapy drugs (camptothecin, taxol, etoposide, cisplatinum) for 24 h. Cell viability was assayed (see experimental procedures). Results are expressed as means ± SEM (n = 3). C. SW480 cells were transiently transfected plasmids as indicated. Cells were treated with camptothecin (60 μM), taxol (300 μM), etoposide (600 μM), and cisplatinum (30 μM) for 6 h. Cell lysates were subjected to Western blot. D. SW480 cells were transfected with control or PPARα shRNA as indicated. Cells were treated without or with etoposide for 24 h. Cell apoptosis was assayed (see experimental procedures)."
      }
    ]
  },
  {
    "id": "PMC4832922_multi",
    "image": [
      "images/PMC4832922-f1.png",
      "images/PMC4832922-f2.png",
      "images/PMC4832922-f3.png",
      "images/PMC4832922-f4.png",
      "images/PMC4832922-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Rad7 E3 Ubiquitin Ligase Attenuates Polyubiquitylation of Rpn10 and Dsk2 Following DNA Damage in Saccharomyces cerevisiae\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (a) Merged RFP and DAPI fluorescent images are shown (left) of a Ub-RFP cell 15 min following induction with UV-C (20 J/m2) followed by images containing only RFP and DAPI channels (middle) and a differential interference contrast (DIC) image (right). Bright cytosolic RFP foci are visible throughout the cell (green arrow indicates one focus). A nuclear-localized RFP focus is indicated (orange arrow); (b) Same as (a) except cell shown does not contain a nuclear-localized RFP focus. Bright cytosolic RFP foci are visible throughout the cell (green arrow indicates one focus); (c) Immunoblot of WCEs from the indicated yeast strains probed with an antibody to ubiquitin (Ub). Lower panel shows the same blot reprobed with an antibody to β-Actin. Lane 1: MagicMark™ protein standard, lane 2: wild-type (W1588-4C), lane 3 Ub-RFP PF038-1D); (d) The Ub-RFP Rad10-YFP strain (PF038-1D) was incubated with BPDE (10 μM, 1 h) and imaged as a single focal plane. Merged, RFP, YFP and DIC images are shown. A white arrow indicates a nuclear-localized RFP focus; (e) Same as panel (c), except the strain was Ub-RFP Rad14-CFP (PF040-3A) and the DNA damaging agent was AAAF. A nuclear-localized RFP focus is indicated with an orange arrow. In both (d) and (e), green arrows indicate examples of RFP foci that are not nuclear or colocalized; (f) Graph of nuclear Ub-RFP foci counts from 11-slice Z-stacks (rather than single focal plane images) acquired during experiments described/depicted in panel (d). Data are shown for Ub-RFP Rad10-YFP strain (PF038-1D) samples induced with BPDE (10 μM, 1 h) or controls mock-induced with tetrahydrofuran (THF). Error bars represent standard error.\n\nFigure 2: Figure 2. Timelapse experiments with the Ub-RFP Rad10-YFP strains following BPDE treatment and imaging at 5 minute intervals. Representative DIC and merged RFP/YFP images are shown from strains containing either the RAD7 (PF038-1D, upper images) or rad7SOCS (PF084-7A, lower images). Gold arrows indicate nuclear-localized Ub-RFP foci. Note in the lower panels a Ub-RFP focus is shown which persisted through two timepoints. (b) Quantification of timelapse experiments. (c) Representative images from RAD10-YFP and RAD14-CFP strains showing pan-nuclear YFP or CFP signal and a Rad10-YFP or Rad14-CFP focus. Gold arrows indicate nuclear-localized foci. (d) Quantification of Rad10-YFP foci observed at 15 min in timelapse experiments. In (b) and (d), the plotted values represent means (λ’s) from ideal Poisson distributions least squares fit to the observed distributions of foci per cell. The least squares deviations were propagated into the overall errors, which are depicted as the error bars in the graphs.\n\nFigure 3: Figure 3. Cells from strains PF038-1D, (“wild-type”, lanes 1 and 2), PF084-7A, (“rad7SOCS”, lanes 3 and 4), MGSC104, (“rad7Δ”, lanes 5 and 6) or PF097-2C, (“rad4Δ”, lanes 7 and 8, panel B only) were cell cycle-arrested at the G2/M boundary, released briefly back into cell cycle, treated with 10 μM BPDE (lanes 2, 4, 6 or 8 “+”) for 3 minutes or mock treated (lanes 1, 3, 5 and 7 “-”) and disrupted. Normalized protein quantities were analyzed by SDS-PAGE and immunoblotted with the indicated antibodies. “M” indicates MagicMark™ molecular weight marker. The expected native protein size is shown in parentheses next to the antibody name. (a) Protein candidates for which we observed HMW species that appeared in greater abundance in rad7SOCS, BPDE-treated extracts as compared to controls. Arrows indicate the observed HMW species. The second image panel from the top shows a portion of a Dsk2 immunoblot from a 3% – 8% Tris-Acetate gel which gave better resolution of the corresponding HMW bands than the corresponding 4% – 20% Tris-glycine gel shown immediately below. Glyceraldehyde phosphate dehydrogenase (GAPDH) is a loading control. (b) Control immunoblots showing: (top panel) the rad7SOCS polypeptide in the rad7SOCS strain, (second panel) the accumulation of Rad4 in the absence of polyubiquitylation and degradation of Rad4 in rad7SOCS (compare lane 4 with lanes 1 – 3), (third panel) Rpn1 and (bottom panel) GAPDH as a loading control. (c) Ni-NTA affinity capture experiments from cells transformed either with the empty vector (YEplac 195, “Control”, lanes 1 and 2) or with YEplac195 CUP1::His7-Ub (“His-Ub”, lanes 3 and 4), cell cycle-arrested, BPDE-treated and harvested under denaturing conditions prior to Ni-NTA affinity capture. Immunoblots for Rpn10 (top panel), or Dsk2 (bottom panel) are shown.\n\nFigure 4: Figure 4. Fluorescence microscopy in Dsk2-GFP/Ub-RFP/Rad10-YFP diploid strains [PF165 (RAD7), PF166 (rad7SOCS), PF167 (rad7Δ)], were cell cycle arrested and treated with BPDE. (a) Examples of nuclear colocalized and “close” Dsk2-GFP/Ub-RFP foci, which were grouped and tallied together as simply “colocalized” for the purposes of our data analysis. DIC, GFP and RFP images are shown as well as merged GFP/RFP images. (b) Examples of nuclear envelope signal in which Dsk2-GFP signal circling portions of the edge of the nuclear envelope was observed. Rad10-YFP pan-nuclear fluorescence shows the approximate location of the nucleus. (c) Examples of plasma membrane Dsk2-GFP foci. Yellow arrows indicate the locations of the foci. (d) Graph of foci counts observed in S, G2 and M phase cells in 3-slice Z-stacks acquired during experiments depicted in panels (a)-(c) (left graph) and corresponding foci counts in G1 phase (right graph). The plotted values represent means (λ’s) from ideal Poisson distributions least squares fit to the observed distributions of foci per cell. The least squares deviations were propagated into the overall errors, which are depicted as the error bars in the graphs. Statistical comparisons were carried out via a paired tcalc according to the NIST/SEMATECH e-handbook of Statistical Methods and then calculating p from integration of the single tail area beyond the paired tcalc in a Gaussian distribution. “***” indicates p < 0.001, “**” indicates 0.001 < p < 0.01, “*” indicates 0.01 < p < 0.05, “n.s.” indicates 0.05 < p.\n\nFigure 5: Figure 5. Increased levels of ubiquitylated proteins are observed in rad7SOCS cells following UV and increased monoubiquitylated Rpn11 is observed in rad7SOCS without damage. (a) Cells from strains PF038-1D, (“wild-type”, lanes 1 and 2), PF084-7A, (“rad7SOCS”, lanes 3 and 4) and MGSC104, (“rad7Δ”, lanes 5 and 6), were cell cycle arrested at the G2/M boundary, released briefly back into cell cycle, treated with 100 J/m2 UV-C (lanes 2, 4 or 6, “+”) for 3 minutes or mock treated (lanes 1, 3 or 5, “-”) and disrupted. Normalized quantities of protein from WCEs were analyzed on a NuPAGE Novex 4% – 12% Bis-Tris gel with MES SDS running buffer SDS-PAGE and immunoblotted with antibodies to Ub (upper panel) or GAPDH (lower panel) as a loading control. “M” indicates MagicMark™ molecular weight marker. (b) Same as upper panel of (a) except that extracts were analyzed on a NuPAGE Novex 3% – 8% Tris-Acetate Gel with Tris-Acetate running buffer. Arrows indicate ubiquitin; brackets indicate putative ubiquitin-conjugates. (c) The Rpn11-TAP strain (YFR004W) and an isogenic Rpn11-TAP/rad7SOCS derivative (PF168) were transformed with YEplac195 CUP1::His7-Ub, cell cycle arrested, released briefly back into cell cycle and disrupted. Denatured protein extracts were subjected to Ni-NTA affinity capture experiments. Lane 1, MagicMark™ molecular weight marker; lane 2, 10% input; lane 3, affinity capture in which Ni-NTA beads were omitted; lane 4, affinity capture from Rpn11-TAP, no UV; lane 5 affinity capture from Rpn11-TAP with UV; lane 6 affinity capture from Rpn11-TAP/rad7SOCS, no UV; lane 7 affinity capture from Rpn11-TAP with UV."
      }
    ]
  },
  {
    "id": "PMC4849772_multi",
    "image": [
      "images/PMC4849772-f1.png",
      "images/PMC4849772-f2.png",
      "images/PMC4849772-f3.png",
      "images/PMC4849772-f4.png",
      "images/PMC4849772-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"C26:0-Carnitine Is a New Biomarker for X-Linked Adrenoleukodystrophy in Mice and Man\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic presentation of the Rosa26CAG-STOPflox/flox-ELOVL1TG transgenic construct (black line). The grey line indicates the wild type Rosa26 gene. ELOVL1 transgene expression is prevented by the upstream floxed STOP element. The ELOVL1 transgenic construct consists of a loxP flanked STOP cassette positioned between the human ELOVL1 coding cDNA and the upstream ubiquitous CAG promoter. Crossing the transgenic mice with a Cre-driver strain activates ELOVL1 transgene expression. (B) ELOVL1 protein expression in total homogenates, organelle and cytosolic fractions and purified microsomes derived from livers from wild type mice (control) and wild type mice heterozygous (CMV-ELOVL1+/-) for the activated ELOVL1 transgene. (C) C16:0-CoA and C22:0-CoA elongation capacity in mouse liver microsomes (n = 5) derived from wild type mice (control) and wild types heterozygous (CMV-ELOVL1+/-) for the activated ELOVL1 transgene. (D) ELOVL1 protein expression in brain, adrenal gland and testis from wild type (WT), wild type heterozygous (CMV-ELOVL1+/-) or homozygous (CMV-ELOVL1+/+) for the activated ELOVL1 transgene, Abcd1y/- knockout and Abcd1y/- knockout heterozygous for the activated ELOVL1 transgene (Abcd1y/-;CMV-ELOVL1+/-) mice. (E) C26:0 levels (in nmol/mg protein) in tissues derived from wild type (n = 6), Abcd1y/- knockout (n = 6) and Abcd1y/-;CMV-ELOVL1+/- (n = 2) mice. Data are mean ± SD. ***p<0.001 by unpaired student’s t-test.\n\nFigure 2: Figure 2. (A) Distribution of the actual F1 genotypes of 4 independent crosses between Abcd1 knockout females (Abcd1-/-) with males heterozygous for the activated ELOVL1 transgene (CMV-ELOVL1+/-). Males are in blue and females in pink. The dashed lines indicate the expected percentages. (B) The actual male to female ratio in the F1 generation of 4 independent crosses between Abcd1 knockout females (Abcd1-/-) with males homozygous for the activated ELOVL1 transgene (CMV-ELOVL1+/+). (C) Untargeted metabolomics using bloodspots derived from Swiss and C57BL6/J wild type and Abcd1 knockout mice reveals strong differences in the metabolome between both background strains. The color in the heat map reflects the global metabolite abundance level according to the z-score. The 50 most significant different metabolites are shown (P < 0.05) as determined by a Welch’s t-test.\n\nFigure 3: Figure 3. (A) ELOVL1 protein expression in brain and spinal cord from wild type, Abcd1y/- knockout and Abcd1y/-;Cnp-ELOVL1+/-. (B) C26:0 levels in brain and spinal cord from wild type (n = 6), Abcd1y/- knockout (n = 6) and Abcd1y/-;Cnp-ELOVL1+/- (n = 6) mice. Data are mean ± SD. ***p<0.001 by unpaired student’s t-test.\n\nFigure 4: Figure 4. C22:0-lysoPC, C24:0-lysoPC and C26:0-lysoPC levels in brain and spinal cord from wild type (n = 6), Abcd1y/- knockout (n = 6) and Abcd1y/-;Cnp-ELOVL1+/- (n = 6) mice. Data are mean ± SD. *p<0.05, **p<0.01, ***p<0.001 by unpaired student’s t-test.\n\nFigure 5: Figure 5. C22:0-carnitine, C24:0-carnitine and C26:0-carnitine levels in brain and spinal cord from wild type (n = 6), Abcd1y/- knockout (n = 6) and Abcd1y/-;Cnp-ELOVL1+/- (n = 6) mice. Data are mean ± SD. **p<0.01, ***p<0.001 by unpaired student’s t-test."
      }
    ]
  },
  {
    "id": "PMC4852500_multi",
    "image": [
      "images/PMC4852500-f1.png",
      "images/PMC4852500-f2.png",
      "images/PMC4852500-f3.png",
      "images/PMC4852500-f4.png",
      "images/PMC4852500-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Neurodegeneration in a Drosophila model of adrenoleukodystrophy: the roles of the Bubblegum and Double bubble acyl-CoA synthetases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. bgm and dbb are duplicated genes that encode bona fide acyl-CoA synthetases. (A) Enzymology of VLCFA degradation in peroxisomes. When transport to the peroxisome is blocked by mutation of either the synthetase (ACSL) or the transporter (ABCD1), which is shown here as a dimer (oval pair) resident in the peroxisomal membrane, VLCFAs accumulate intracellularly (gray arrow). (B) A phylogenetic tree of all annotated mono-functioning acyl-CoA synthetase proteins in D. melanogaster. The tree was made using the software PhylOgenetic Web Repeater (POWER) by aligning amino acid sequences. Standard conditions were used, with the exception of the following: no outgroup was applied and bootstrapping was used to determine the best-fit tree. Colors indicate the number of times that line was established out of 100 assembled phylogenetic trees (bootstrapping). Teal indicates between 40-60 times, and green indicates between 60-80 times. (C) Organization of the bubblegum (bgm) and double bubble (dbb) genes on Drosophila chromosome 2. (D) Cerulenin renders yeast auxotrophic and dependent on imported fatty acids and the activity of FAA1. Both bgm and dbb restore growth to FAA1-deficient yeast when myristate is added to the growth medium. Only bgm complements FAA1 in the presence of oleate. YPD, yeast peptone dextrose.\n\nFigure 2: Figure 2. Generation of dbb and bgm dbb mutant animals. (A) Schema showing the ends-out gene-targeting strategy employed for generation of dbb single- and bgm dbb double-mutant animals, as well as the positions of primers used for analytical PCR. (B) Verification of the putative dbb1 and bgm1 dbb1 alleles by PCR. M denotes the marker lane and includes bands corresponding to 10, 8, 6 and 5 kb lengths. (C) Verification of loss of dbb expression in dbb1 and bgm1 dbb1 knockout animals by RT-PCR. wt, wild type.\n\nFigure 3: Figure 3. Degeneration of the CNS in acyl-CoA synthetase mutants. (A) Labeled schematization of a Drosophila brain horizontal section. (B-F) H&E-stained brain sections representative of wild-type, bgm1, bgm1/Df(2L)b87e25, dbb1 and bgm1 dbb1 animals, respectively. In C-F, retinal degeneration is marked by black arrows and laminal degeneration by white arrows. (G) Labeled schematization of a horizontal section of the Drosophila retina. (H) Magnified fenestrated membranes from animals shown in B-F. Note the enlarged portals (dashed boxes, containing in the case of the bgm dbb double mutant displaced retinal nuclei). (I-K) Degeneration in (I) lamina and (J) retina, as well as (K) defects in the fenestrated basement membrane, were quantified. For these plots, data obtained from analysis of H&E brain sections were analyzed by ANOVA and by the Welch two-sample t-test. Each point represents the mean score per animal; horizontal lines represent the mean score per genotype. Statistical significance determined by ANOVA followed by Student's t-test: ***P<0.001, **P≤0.015. wt, wild type.\n\nFigure 4: Figure 4. Neuronal death and pigment cell defects in Acyl-CoA synthetase mutants. Ultrastructural analysis of heads from 18-day-old (A) wild-type (wt), (B) dbb1, (C) bgm1 and (D) bgm1 dbb1 flies. In wild-type animals, the fenestrated membrane appears as membrane with pores (boxed in panel A). Only a thinned or barely visible membrane is visible in mutant animals (boxed in panels B-D). Also, lytic death of monopolar neurons is evident in the lamina of mutant, but not wild-type, animals. In A-D, monopolar neurons are indicated by arrows; R denotes the retinal domain; L denotes the laminal domain. Ultrastructural analysis of retinas from 18-day-old (E) wild-type and (F) bgm1 dbb1 flies. Loss of the ommatidial structure (outlined) in the bgm dbb double-mutant retina is correlated with loss of secondary pigment cells; these surround each ommatidial cluster of photoreceptor neurons and in these images appear as empty white structures due to pigment loss associated with processing (Cagan and Ready, 1989; Wolff and Ready, 1991).\n\nFigure 5: Figure 5. Neurodegeneration is associated with laminal deposits. Ultrastructural analyses of lamina in (A) wild-type, (B) dbb1 and (C) bgm1 mutant animals reveal the lamina of mutants to be highly disorganized. Note the parallel organization of photoreceptor axons in wild-type brains, and their misorientation in dbb mutants (outlined in black in A and B). These structures are absent from bgm mutants in which densely stained inclusions are abundant (e.g. boxed region in C). (D) The boxed region from panel C was imaged at higher magnification, and inclusions are indicated with arrows. (E) In wild-type animals, monopolar neurons (outlined in white) are distinguished by their nucleolar content. In bgm dbb double mutants (F,G), however, monopolar neurons are distinguished by cytoplasmic swelling and lytic cell death. Lysing monopolar neurons are oftentimes found in association with extracellular precipitates (arrow in F and boxed in G). (H) The precipitate from panel G was imaged at higher magnification, revealing it to be granular and thus structurally identical to previously described fatty acid precipitates."
      }
    ]
  },
  {
    "id": "PMC4852500_multi_2",
    "image": [
      "images/PMC4852500-f6.png",
      "images/PMC4852500-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Neurodegeneration in a Drosophila model of adrenoleukodystrophy: the roles of the Bubblegum and Double bubble acyl-CoA synthetases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. bgm dbb mutants recapitulate adrenoleukodystrophy (ALD) phenotypes. Gas chromatography-mass spectrometry analysis (GC-MS) of (A) C24:1 and (B) C26:1 in bgm dbb mutant heads; *P=0.04. C19:0 is an experimentally spiked standard and is used to normalize samples. (C) Locomotor activity in wild-type and mutant flies. (A-C) Student's t-test, with s.e.m. shown; *P<0.05, **P<0.01, ***P<0.001. (D) Kaplan–Meir survival estimates for wild-type and mutant flies (n≥150/genotype). wt, wild type.\n\nFigure 7: Figure 7. Identification of a leukodystrophy patient with mutations in SLC27a6. (A) MRI scan of an 18-month-old boy presenting with epilepsy. Arrowhead points to one of the expanded lateral ventricles, diagnostic of leukodystrophy; the paired structural defect is evident on the right side as well. (B) Pedigree shows family-member phenotypes: PRRT2-dependent benign familial infantile epilepsy (vertical hatching); leukodystrophy (horizontal hatching). The proband is designated as #1038. (C) Sequence data for SLC27a6 and PRRT2, respectively. Carriers of the SLC27a6 mutant allele have a C>T transition; the resultant nonsense mutation leads to premature termination of the protein. Carriers of the PRRT2 mutant allele have a C duplication at position 649; this frameshift leads to premature termination of the protein."
      }
    ]
  },
  {
    "id": "PMC4874348_multi",
    "image": [
      "images/PMC4874348-f1.png",
      "images/PMC4874348-f2.png",
      "images/PMC4874348-f3.png",
      "images/PMC4874348-f4.png",
      "images/PMC4874348-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Trim37-deficient mice recapitulate several features of the multi-organ disorder Mulibrey nanism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Weight and bone parameters in Trim37−/− mice. (A) Weight development in Trim37−/− and control mice, age 1 to 18 months; mean±s.d. and group size (n) at given age points 1, 6, 12 and 18 months. M+/+: 15.0±2.9, n=17; 31.4±3.7, n=16; 38.3±5.0, n=4; 41.7±6.3, n=4; M−/−: 15.1±2.5, n=12; 29.3±2.8, n=15; 32.8±7.9, n=6; 32.5±5.3, n=4; F+/+: 12.6±1.5, n=21; 23.1±2.2, n=14; 29.9±4.1, n=8; 32.5±4.8, n=8; F−/−: 12.3±1.6, n=21; 24.3±2.4, n=15; 28.9±3.3, n=8; 29.4±2.6, n=7. Early weight development of Trim37−/− mice is normal in both males and females. The males start losing weight at the age of 6 months and the females at the age of 12 months. (B) CT scan images of skull and femurs showing the measurement of sagittal (yellow line) and coronal (green line) skull width and femur length (blue and orange lines). (C) Skull size of six-month-old Trim37−/− mice is significantly smaller compared to control mice: sagittal width 9.6±0.1 mm vs 9.8±0.1 ng/ml and coronal width 13.7±0.2 mm vs 14.0±0.2 mm (mean±s.d.; P=0.01; t-test; n=10/genotype). No difference in the lengths of humeri, ulnae and femurs could be detected between Trim37−/− and control mice. M, male; F, female.\n\nFigure 2: Figure 2. Testicular findings in Trim37−/− males. (A) Testicles of a 1.5-year-old Trim37−/− mouse and a wild-type littermate. The size of Trim37−/− testicles is reduced to approximately 30% of that of wild-type mice. (B) HE-stained sections demonstrating degeneration of germ cells and Leydig cell hyperplasia in Trim37−/− mouse testis, starting at P13. Total germ cell aplasia is evident in one-month-old mice. (C) Adult Trim37−/− mice show total germ cell aplasia and Leydig cell hyperplasia that is increasing with age. Leydig cells are marked with white arrowheads. (D) ORO stained testicular sections from 1.5-year-old mice, showing excessive intracellular and intercellular lipid accumulation around the area of Leydig cells in the Trim37−/− mice testis. Scale bars: 20 µm.\n\nFigure 3: Figure 3. Ovarian histology in Trim37−/− females. (A) HE-stained sections demonstrating reduced number of oocytes in ovaries of Trim37−/− mice at P30. Scale bars: 20 µm. (B) HE-stained sections of ovaries in adult mice showing germ cell aplasia and hilus cell hyperplasia in the Trim37−/− mouse. One cyst (C) is visible in the 6-month-old Trim37−/− female. Scale bar 100 µm. (C) Some Trim37−/− mice presented with ovarian lipid cell (L) hyperplasia. Scale bars: 20 µm.\n\nFigure 4: Figure 4. Non-compaction cardiomyopathy in Trim37−/− mice. (A) HE-staining of heart sections show hypertrabeculation of the heart in six-month-old Trim37−/− mice. Scale bars: 500 µm. (B) Endothelial staining (anti-CD34 immunostaining) is present in the trabeculations of the ventricular wall in Trim37−/− mice indicative of non-compaction cardiomyopathy (arrowheads). Scale bars: 20 µm.\n\nFigure 5: Figure 5. Hepatomegaly and fatty liver in Trim37−/− mice. (A) Enlarged liver and difference in the liver color in a 22-month-old Trim37−/− female (F) mouse observed in gross pathological examination. (B) HE-staining of liver sections demonstrating sinusoidal dilatation (white arrowheads) and vacuolization of Trim37−/− liver. (C) Accumulation of neutral lipids in Trim37−/− liver visualized by ORO staining. Scale bars: 50 µm."
      }
    ]
  },
  {
    "id": "PMC4880039_multi",
    "image": [
      "images/PMC4880039-f1.png",
      "images/PMC4880039-f2.png",
      "images/PMC4880039-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomes in brain development and function☆\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic drawing linking peroxisomal disease-related proteins to individual metabolic pathways. Upper part: Proteins are grouped according to their function in biosynthetic or degradative metabolic pathways, ROS homeostasis, proteolytic activity, transport of metabolites across the peroxisomal membrane (ABCD and PMP proteins), and the import of matrix and membrane proteins (PEX proteins). Ovals represent proteins that are involved in peroxisomal functions (not complete); gray ovals, proteins for which mutations have been linked to a human disease (for full name see Table 1). The degradation of various fatty acids and bile acid precursors is symbolized by the frame depicting the homodimeric transporters (ABCD1–3) and the terms α- and β-oxidation, illustrated in more detail below. Lower part: Proteins are grouped into the degradation pathways for different activated fatty acids (fatty acyl-CoA: saturated, unsaturated, dicarboxylic, branched-chain) and the side chain shortening of di- and trihydroxycholestanoic acid (DHCA/THCA) during bile acid biosynthesis (all via β-oxidation) and the oxidative removal of one carbon unit from branched-chain fatty acids (α-oxidation). Several proteins are involved in the subsequent modification of the β-oxidation products, either by thiolytic cleavage (thioesterases, ACOT), substitution of CoA for carnitine (carnitine transferases, CRAT and CROT) or amidation of the CoA-activated side chain of bile acids (amino transferase, BAAT). FALDH*, two isoforms are known residing in peroxisomes and the ER, respectively, which precludes attribution of the linked disease, Sjögren–Larsson syndrome, to a particular variant. Synthetase, CoA-activation is essential for the link between α- and β-oxidation, but the exact enzyme has not yet been assigned. PEX, peroxin; cargo-PTS1 and PTS2-cargo, representative peroxisomal matrix proteins harboring a PTS1 or PTS2 motif, respectively; mPTS-cargo, representative peroxisomal membrane protein harboring a motif for targeting of peroxisomal membrane proteins (mPTS). 4,8-DMN-CoA, 4,8-dimethylnonanoyl-CoA. Proteins not included in Table 1: 2-HACL, 2-hydroxyacyl-CoA lyase; ABCD2, ATP-binding cassette transporter D2; ACAA1, acetyl-CoA acyltransferase 1; ACOT4, acyl-CoA thioesterase 4; ACOT8, acyl-CoA thioesterase 8; ACOX2, acyl-CoA oxidase 2; CRAT, carnitine O-acetyltransferase; CROT, carnitine O-octanoyltransferase; DDO, D-aspartate oxidase; DECR2, dienoyl-CoA reductase 2; ECH1, enoyl-CoA hydratase 1; EPHX2, epoxide hydroxylase 2; GSTK1, glutathione S-transferase kappa-1, IDE, insulin-degrading enzyme; LONP2, lon peptidase 2; PAO, polyamine oxidase; PIPOX, pipecolic acid oxidase; PECI, peroxisomal D3,D2-enoyl-CoA isomerase; PMP22, peroxisomal membrane protein of 22 kDa; PMP34, peroxisomal membrane protein of 34 kDa; PRDX1, peroxiredoxin 1; PRDX5, peroxiredoxin 5; SOD1, superoxide dismutase 1; TYSND1, trypsin domain-containing 1\n\nFigure 2: Figure 2. Schematic representation of neuronal migration defects in peroxisomal biogenesis disorders. (A) In the cerebral cortex (neocortex) of a healthy individual (left panel), the cell bodies of cortical neurons are localized in discrete layers. In comparison, the cortical lamination is severely disturbed and the border to the white matter in microgyric (middle panel) and pachygyric (right panel) brains of cases with Zellweger Syndrome is indicated (horizontal line). Similar abnormalities can also be found in cases of severe D-bifunctional protein deficiency. Roman numerals to the left correspond to normal cortical layers. WM, white matter. (B) In the cerebellum of a healthy individual (left panel), the Purkinje cells (blue triangles) are strictly arranged into a single cell-thick layer at the border of the molecular (outermost) layer and the thick granule cell layer. In Zellweger patients (right panel), many Purkinje cells are mislocalized to the granule cell layer and cerebellar white matter.\n\nFigure 3: Figure 3. Schematic representation of abnormalities of myelinated axons and synaptic transmission in peroxisomal deficiencies. (A) The left panel shows a myelinated axon at the level of a node of Ranvier in a healthy control. The myelin sheath of oligodendrocytes (in the CNS) or Schwann cells (in the PNS) surrounds and isolates the axon, except at the node of Ranvier allowing depolarization of the neuronal membrane and propagation of electrical signals. Note that a multitude of ion channels and Na+/K+-ATPases (not indicated) are located at the node of Ranvier and entail a high energy demand. In the right panel, different pathological features are indicated that may contribute to the axonal degeneration frequently observed in peroxisomal disorders, for example, adrenomyeloneuropathy (the late-onset variant of X-ALD). A scenario can be envisaged, where peroxisomal dysfunction and abnormal accumulation of lipid metabolites in myelinating cells lead to unstable paranodal loops and a loss of axonal support resulting in energy deficits and oxidative damage in the axons and progressive axonal degeneration. (B) A normal synapse with the surrounding astrocytes is depicted (left panel), representative for a synapse of any neurotransmitter. D-Amino acid oxidase is indicated for its role in D-serine degradation at e.g. glutamatergic synapses. The right panel shows several possible disturbances of synaptic function (red text) that could lead to altered neurotransmission, as predominantly described in ether lipid deficiency. NT, neurotransmitter; DAO, D-amino acid oxidase"
      }
    ]
  },
  {
    "id": "PMC4910150_multi",
    "image": [
      "images/PMC4910150-f1.png",
      "images/PMC4910150-f2.png",
      "images/PMC4910150-f3.png",
      "images/PMC4910150-f4.png",
      "images/PMC4910150-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"F-box only protein 9 is an E3 ubiquitin ligase of PPARγ\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. FBXO9 interacts with PPARγ. (a) COS7 cells were seeded in a 60-mm dish. The next day, HA-PPARγ2 (1 μg) and FLAG-FBXO9 (1 μg) were co-transfected for 20 h. Whole-cell lysates were subjected to immunoprecipitation with anti-HA antibody-conjugated beads and blotted with anti-FLAG or anti-PPARγ antibody. As a loading control, γ-tubulin was detected using anti-γ-tubulin antibodies. (b) COS7 cells were co-transfected with HA-PPARγ (100 ng) and FLAG-FBXO9 (100 ng, 300 ng) or an empty vector (CMV) as a negative control. The protein levels of PPARγ, FBXO9 or γ-tubulin were detected using anti-HA, anti-FLAG or anti-γ-tubulin antibodies, respectively.\n\nFigure 2: Figure 2. The domain of PPARγ involved in the interaction with FBXO9. (a) Structure of the deletion mutants of PPARγ. (b) pHA-PPARγ AF1 (3 μg), pHA-PPARγ DBD (4 μg) or pHA-PPARγ LBD (3 μg) was overexpressed with pFLAG-FBXO9 (1 μg) for 24 h and treated with MG132 (10 μM) for 5 h before harvesting. The deletion mutants of PPARγ were immunoprecipitated using anti-HA antibody-conjugated beads and immunoblotted using anti-FLAG and anti-HA antibodies. (c) GST-FBXO9 (1 μg) and PPARγ LBD (2 μg) were mixed and incubated. Co-precipitates were immunoblotted using anti-PPARγ or anti-FBXO9 antibodies.\n\nFigure 3: Figure 3. FBXO9 decreases the levels of PPARγ protein by induction of ubiquitination. (a) The day before transfection, COS7 cells were plated in 12-well plates. CMV (100 ng) or FLAG-FBXO9 (100 ng) was co-transfected with HA-PPARγ (100 ng) for 24 h, and cycloheximide (5 μM) was added for the indicated times. Whole-cell lysates were then analyzed using western blotting. Stars indicate non-specific bands. (b) The densities of the PPARγ bands at time point 0 were set to 100%, and the remaining densities were expressed as relative values. Data represent the mean±s.e.m. of three independent experiments. *P<0.05 vs CMV. (c) COS7 cells were subcultured in 60 mm dishes one day before transfection. HA-PPARγ (1 μg), His-Ub (0.2 μg) and FLAG-FBXO9 (0.5 μg) or CMV (0.5 μg) were overexpressed for 12 h and treated with DMSO or MG132 (10 μM) 5 h before harvesting. PPARγ was precipitated with anti-HA antibody-conjugated beads and immunoblotted with anti-Ub, anti-PPARγ, anti-FLAG or anti-γ-tubulin antibodies.\n\nFigure 4: Figure 4. The requirement for the F-box motif on the effect of FBXO9 on PPARγ stability. (a) Structure of FBXO9. (b) COS7 cells were seeded in 12-well plates. The next day, cells were transfected with pHA-PPARγ2 (100 ng) and pFLAG-FBXO9 WT (100 ng, 300 ng) or pFLAG-FBXO9 ΔF (25 ng, 50 ng) for 24 h. The amount of transfected DNA of FBXO9 WT and ΔF was determined by similarly expressed protein levels. Whole-cell lysates were then subjected to western blot analysis. (c) COS7 cells were transfected with pFLAG-FBXO9 WT or pFLAG-FBXO9 ΔF in the presence of pPPRE-Tk-Luc (1 μg), pHA-PPARγ (0.3 μg) and pCMV-βgal (0.5 ug) for 18 h. Luciferase activities were normalized to β-galactosidase activity. The relative values for the luciferase activity were calculated from three independent experiments (mean±s.e.m.). *P<0.05 vs the transfection of HA-PPARγ alone.\n\nFigure 5: Figure 5. The effect of FBXO9 overexpression on endogenous PPARγ protein levels in adipocytes. (a) Control adenovirus (Ad-GFP) or adenovirus-expressing FLAG-FBXO9 (Ad-Flag-FBXO9) was infected into 3T3-L1 adipocytes using the indicated multiplicity of infection (MOI). Whole-cell lysates were prepared 48 h after infection. Endogenous PPARγ, FLAG-FBXO9, GFP or γ-tubulin was detected by specific antibodies. Stars indicate non-specific bands. (b) The intensity of PPARγ bands in (a) was normalized to γ-tubulin. The mean value was calculated from six independent experiments (mean±s.e.m.). *P<0.05 vs control."
      }
    ]
  },
  {
    "id": "PMC4928619_multi",
    "image": [
      "images/PMC4928619-f1.png",
      "images/PMC4928619-f2.png",
      "images/PMC4928619-f3.png",
      "images/PMC4928619-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Neurometabolic Diagnosis in Children who referred as Neurodevelopmental Delay (A Practical Criteria, in Iranian Pediatric Patients)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Distribution of patient’s age in our study\n\nFigure 2: Figure 2. A 6-month-old boy-with Glutaric aciduria type1 with sylvian fissure widening in axial brain MRI\n\nFigure 3: Figure 3. An 8-yr old-girl with metacromatic leuckodystrophia with periventricular white matter involvement (Butter-fly pattern) in imaging\n\nFigure 4: Figure 4. A 13-yr-old girl with wilson disease that showed basal ganglia involvement in brain imaging"
      }
    ]
  },
  {
    "id": "PMC4961474_multi",
    "image": [
      "images/PMC4961474-f1.png",
      "images/PMC4961474-f2.png",
      "images/PMC4961474-f3.png",
      "images/PMC4961474-f4.png",
      "images/PMC4961474-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Hul5 HECT Ubiquitin Ligase Plays A Major Role in The Ubiquitylation and Turn Over of Cytosolic Misfolded Proteins\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Heat-shock stress induces protein misfolding and poly-ubiquitylation. (a) BY4741 cells were subjected to heat-shock (HS; 15 min at 45°C) or not (noHS). Experimental triplicates were analyzed by Western (top) and dot blots (bottom) with anti-ubiquitin and anti-Pgk1 antibodies (left). The region above 70 kDa in the Western blot and the whole spotted signal in the dot blot were quantified (right). Ubiquitylation signals were normalized to Pgk1 levels and standard deviations are shown. (b) Ubiquitylation levels in total cell extract, soluble and pellet fractions after 16,000 g centrifugation from both unstressed and heat-shock treated (15 min 45°C) BY4741 cells are shown by anti-ubiquitin Western blot. (c) Schematic diagram of the proposed relationship between heat-shock and the increased ubiquitylation response. (d) Relative increase of Pgk1-normalized ubiquitylation levels after a 15 min 45°C heat-shock in the indicated E2 double deletion strains were quantified by dot blot and averaged values from three replicates are shown with standard deviations.\n\nFigure 2: Figure 2. Heat-shock mainly affects cytosolic proteins. (a) A schematic diagram of the workflow of the quantitative mass spectrometry analysis. (b) Percentage of proteins above the corresponding log2 values of the 14N heat-shock/15N no stress ratios for three independent experiments (I: light; II: medium; and III: dark). Analysis of proteins in the total cell lysate (grey: I, 486; II, 730; and III, 399) and of IMAC enriched ubiquitylated proteins (green: I, 302; II, 481; and III, 219) are shown. Proteins with a log2 ratio ≥ 0.5 are considered heat-shock affected. (c) Pin3TAP solubility was assessed prior to and after a 15 min 45°C heat-shock. An equal portion of each fraction (T: total; S: supernatant; P: pellet) was loaded on a SDS-PAGE for Western blot analysis with the anti-TAP antibody. (d) Subcellular localization of 155 proteins affected by heat-shock (green; identified as enriched in at least two of the three experiments in b) compared to the whole proteome (grey) - cytosol (C), nucleus (N), membrane (M) and mitochondria or peroxisome (M/P). Note that several proteins localize to more than one compartment.\n\nFigure 3: Figure 3. HUL5 is required for the full ubiquitylation response and cell fitness after heat-shock. (a) Ubiquitylation levels in unstressed (no HS) and heat-shocked (HS) cells are compared between wild-type and hul5Δ strains using the dot blot assay. HUL5 was deleted by two different cassettes (KanMX6 and NatMX4). Standard deviation is shown for three replicates and p values were calculated using an unpaired Student’s t-test. (b) TAP pull-down experiments with cells expressing or not Ubc4TAP (left panel) or Ubc5TAP (right panel) at endogenous levels with or without a plasmid expressing 13MycHul5 were analyzed by Western blot using 9E10 or anti-TAP antibodies. Inputs (1%) are shown below. (c) The OD600 of the first cell doubling following a 20 min incubation at 45°C heat-shock (HS; black) or at 25°C (no HS; grey) of HUL5 (round) and hul5Δ::NAT (square) cells. hul5Δ::NAT cells carrying a centromeric plasmid (dashed lines) with HUL5 (round) or hul5-C878A (square) are also compared. Growth delay is defined by the difference of the first doubling time between the corresponding unstressed and stressed cells. Each data point is averaged from three replicates. (d) hul5Δ cells carrying either wild-type HUL5 or the catalytically inactive Hul5 (C878A) were subjected to heat-shock (15 min at 42°C). The increase in ubiquitylation levels (with standard deviations) was measured by dot blots with anti-ubiquitin and anti-Pgk1 antibodies in three replicates. An unpaired Student’s t-test was used to assess the significance of the difference between both cell populations.\n\nFigure 4: Figure 4. Hul5 redistribution to the cytoplasm is important for its role in the heat-shock response. (a) Localization of Hul5GFP was assessed in a strain that carries Nic96mRFP as a nuclear periphery marker, in both unstressed and heat-shocked (30 min at 42°C) cells. Images were taken with a 40X objective and in focus z-stacks were flattened with the Wavelet extended function. The nuclear positions are marked by circles and the scale bar represents 5 μM. (b) Histograms of the mean Hul5GFP signal intensities (per pixel; with standard error) measured in a 0.7 μm2 area of the nuclei (N) and cytoplasm (C) of unstressed (25°C) and heat-shocked (30 min at 42°C) cells (n=100), after subtraction of the average background signal from untagged cells. (c) Levels of Hul5GFP in both nuclear (N) and cytosolic (C) fractions were analyzed by Western blot using anti-GFP, anti-Pgk1 and anti-Histone H3 antibodies after sub-fractionation of both unstressed (no HS) and heat-shocked (HS; 30 min at 42°C) cells. (d) The localization of GFPHul5 (upper panels) and GFP-NLSHul5 (lower panels) expressed from a plasmid was assessed in hul5Δ cells grown at 25°C and subjected to heat-shock (30 min at 42°C). DNA was stained with Hoechst (shown below GFP images), single-stack images were taken with a 63X objective, arrowheads point to the nucleus and scale bar is 5 μM. (e) The increase of ubiquitylation levels after heat-shock (15 min at 45°C) is compared using the dot blot assay between HUL5 and hul5Δ cells with an empty vector, and hul5Δ cells expressing GFPHul5 or GFP-NLSHul5 from a plasmid. Standard deviation is shown for three replicates and p values were calculated using an unpaired Student’s t-test (in black or in grey when comparing to HUL5 or GFPHul5 expressing cells, respectively). (f) OD600 following a 20 min heat-shock at 45°C (HS; black) or 20 min at 25°C (no HS; grey) of hul5Δ cells carrying a plasmid with GFPHul5 (round) or GFP-NLSHul5 (square) are compared. Each data point is averaged (with standard deviations) from three replicates.\n\nFigure 5: Figure 5. HUL5 is essential for the ubiquitylation of proteins misfolded in absence of SSA chaperone activity and for the degradation of pulse-labeled misfolded polypeptides. (a) Schematic diagram of the proposed model for the SSA hsp70 chaperone inactivation. (b) The bar graph shows Cdc28-normalized ubiquitylation levels in SSA1 and ssa1-45 cells (ssa2-4Δ) measured before and after shifting cells from 25°C to 37°C for 40 min. The ubiquitylation levels were quantified by dot blot assay from four replicates and shown with standard errors. (c) The increased ubiquitylation levels in ssa1-45 HUL5 or ssa1-45 hul5Δ cells (two independent strains) were compared using five replicates for each assessed strain as described for (b). The p values were determined by Student’s t-test. (d) Wild-type (BY4741) and hul5Δ cells were subjected to 35S-pulse labeling (5 min) followed by a 3 h chase. The graph shows the averaged percentage (with standard errors) of pulse-labeled proteins that were degraded at each time point from cells incubated at 25°C or 38°C from three replicates. (e) Histograms of averaged ubiquitylation signals measured by dot blots in unstressed (no HS; light grey) and heat-shocked (HS; dark grey) cells in three replicates are shown with standard deviations. Cells were grown at 25°C and pre-treated or not for 15 min with 100 μg/ml cycloheximide (CHX) prior to heat-shock (15 min at 45°C). Student’s t-test was used to assess the significance of the ubiquitylation level differences between the indicated strains."
      }
    ]
  },
  {
    "id": "PMC4961474_multi_2",
    "image": [
      "images/PMC4961474-f6.png",
      "images/PMC4961474-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Hul5 HECT Ubiquitin Ligase Plays A Major Role in The Ubiquitylation and Turn Over of Cytosolic Misfolded Proteins\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. HUL5 is required for ubiquitylation of low solubility cytosolic proteins. (a) 14N and 15N metabolic labeling was performed for wild-type and hul5Δ cells, respectively. Percentage of proteins above the corresponding log2 values of the 14N/15N ratios in three independent experiments (I: light; II: medium; and III: dark). Analysis of proteins in the total cell lysate (grey: I, 345; II, 346; and III, 240) and of IMAC enriched ubiquitylated proteins (green: I, 661; II, 430; and III, 267) are shown. Proteins with a IMAC-log2 ratio ≥ 1 are considered Hul5 candidate substrates. (b) Venn diagram representing all 95 proteins identified as more ubiquitylated in experiments I to III in a. Bold protein names are confirmed Hul5 substrates in Figure 7, S6. (c) Histogram showing the subcellular localization of the 99 (light green) and 95 (dark green) Hul5 candidate substrate proteins identified in heat-shock stressed and unstressed cells, respectively: cytosol (C), nucleus (N), membrane (M) and mitochondria or peroxisome (M/P).\n\nFigure 7: Figure 7. Hul5 targets proteins that are specifically ubiquitylated in the low solubility cellular fraction. (a–d) Validation of the Hul5 substrate candidates Lsm7 and Pin3 using TAP-tagged strains expressing H8-Ubi. IMAC was performed in denaturating conditions to pull down ubiquitylated proteins, and anti-TAP or anti-ubiquitin antibody was used for Western blot analysis. The asterisk denotes unspecific signal. Corresponding signal intensities for poly- and mono-ubiquitin were measured by subtracting the background signal in control cells (a, c). Solubility of ubiquitylated Lsm7TAP (b) and Pin3TAP (d) were assessed by comparing both soluble and pellet fractions subjected to IMAC and analyzed by Western blots with anti-TAP (b, d) and anti-ubiquitin (b). A 20 min 45°C heat-shock (HS) was also applied to Pin3TAP expressing cells (c, d). (e–f) Turnover of Slh1 is dependent on cytosolic Hul5. Protein levels of Slh1TAP were monitored by Western blot after the addition of 100 μg/ml cycloheximide to both HUL5 and hul5Δ cells grown at 25°C (e), and to hul5Δ cells expressing either GFPHul5 or GFP-NLSHul5 and shifted to 38°C (f). Relative averaged signal intensities (with standard deviations) were quantified and normalized to Pgk1 levels in three independent experiments."
      }
    ]
  },
  {
    "id": "PMC4966567_multi",
    "image": [
      "images/PMC4966567-f1.png",
      "images/PMC4966567-f2.png",
      "images/PMC4966567-f3.png",
      "images/PMC4966567-f4.png",
      "images/PMC4966567-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural and functional characterization of a novel gene, Hc-daf-22, from the strongylid nematode Haemonchus contortus\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Genomic structure of Hc-daf-22. The numbered boxes are exons; blank box is 5′-UTR; grey box is 3′-UTR. The four-point star indicates translation start codon ATG, and the five point star represents translation stop codon TAA\n\nFigure 2: Figure 2. Upstream domain of the Hc-daf-22 gene. The 5′-flanking region of Hc-daf-22 gene was obtained and analyzed for putative transcription factor binding sites using the Transcription Element Search System (TESS). The main predicted promoter elements are highlighted in different colors: TATA box (pink); GATA-1 binding sites (bright green); CAC-binding protein sites (green); CCAAT binding factor (red); Unc-86 (light grey); AP-1 (yellow); AP-2 (violet); NFγB (teal). The start codon ATG is highlighted in dark grey\n\nFigure 3: Figure 3. Characterization of Hc-daf-22 gene from H. contortus. a Alignment of the deduced amino-acid sequences of Hc-DAF-22 and other species. Protein sequences were aligned using CLUSTAL W and BoxShade. Shading in black indicates residues that are consistent. Red boxes represent thiolase acyl-enzyme intermediate signatures, the first box represents the thiolases aryl-enzyme intermediate signature and the second box represents the thiolase-2 thiolase signature. The accession numbers representing these sequences are: NP 496639.1 (C. elegans), EYC23922.1 (A. ceylanicum: Ancylostoma ceylanicum), XP 001902124.1 (B. malayi: Brugia malayi), CEF60652.1 (S. ratti: Strongyloides ratti), XP_013305621.1 (N. americanus: Necator americanus), KHJ80319.1 (O. dentatum: Oesophagostomum dentatum), KHN79232.1 (T. canis: Toxocara canis), XP_002065586.1 (D. willistoni: Drosophila willistoni), NP_957159.1 (D. rerio: Danio rerio), NP_001292129.1 (G. gallus: Gallus gallus), NP_035457.1 (M. musculus: Mus musculus), NP_001075504.1 (O. cuniculus: Oryctolagus cuniculus), NP_001007099.1 (H. sapiens: Homo sapiens). b Phylogenetic tree based on deduced amino acid sequences of Hc-DAF-22 and its homologues from other species. NP 496639.1, AAB06496.1 (C. elegans), EYC23922.1 (A. ceylanicum: Ancylostoma ceylanicum), XP 001902124.1 (B. malayi: Brugia malayi), CEF60652.1 (S. ratti: Strongyloides ratti), XP_013305621.1 (N. americanus: Necator americanus), XP_002065586.1 (D. willistoni: Drosophila willistoni), NP_957159.1 (D. rerio: Danio rerio), NP_001292129.1 (G. gallus: Gallus gallus), NP_035457.1 (M. musculus: Mus musculus), NP_001007099.1 (H. sapiens: Homo sapiens)\n\nFigure 4: Figure 4. Transcriptional profile of Hc-daf-22 at different developmental stages of H. contortus and genders. Data shown are mean values (± standard error of the mean, SEM) derived from three replicates in repeat experiments. All gene expression levels were normalized to those of the β-tublin gene. P-values are calculated by Dunnett’s test. There were significant differences between stages indicated by different letters (a, b, c) (P < 0.05)\n\nFigure 5: Figure 5. Expression pattern of Ce-daf-22 and Hc-daf-22 promoter GFP fusion in C. elegans. a1-a3 Total view of Ce-daf-22 promoter-derived worms showing pharynx (arrow a), intestine (arrow b) and hypodermis (arrow c) enrichment of GFP; b11-b13 Total view of Hc-daf-22 promoter- derived worm, b21-b43 Views at higher magnification: Hc-daf-22P::GFP protein localized mainly in the pharynx (arrow a), excretory cell (arrow d) and intestine (arrows e, f, g, h). Scale-bars: 200 μm"
      }
    ]
  },
  {
    "id": "PMC4966567_multi_2",
    "image": [
      "images/PMC4966567-f6.png",
      "images/PMC4966567-f7.png",
      "images/PMC4966567-f8.png",
      "images/PMC4966567-f9.png",
      "images/PMC4966567-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural and functional characterization of a novel gene, Hc-daf-22, from the strongylid nematode Haemonchus contortus\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Hc-DAF-22 is located in intestinal cells in C. elegans N2 worms using Ce-daf-22 promoter. The plasmid vector CeP-pPD95.77-Hc-daf-22 which contained the 2,061 bp region upstream of the Ce-daf-22 initiation codon and 1,105 bp region of the Hc-daf-22 coding sequence was constructed and injected into wild type N2 worms. The expression pattern of Hc-DAF-22 in the N2 strain is shown, GFP could be seen throughout the whole intestine in both larvae and adults with high intensity. a11-a33 L4 larvae; b11-b33 adult worms. Scale-bars: 200 μm\n\nFigure 7: Figure 7. Expression of Hc-daf-22 in C. elegans daf-22 (ok693). The plasmid vector CeP-pPD95.77-Hc-daf-22 was also injected into C. elegans daf-22 (ok693). The GFP was located in the intestine (arrow a) and tail (arrow b). a1-a3 L1 larvae. b1-b3 L2 larvae. c11-c23 Adult. Scale-bars: 200 μm\n\nFigure 8: Figure 8. Fat storage and fat granule phenotype in C. elegans N2, daf-22 (ok693), and rescued worms. a1-a3 Fat storage in N2. b1-b3 Fat storage and granules in daf-22 (ok693) strain. c1-c3 fat storage in rescued worms. Huge fat granules can be seen in the intestine of daf-22 (ok693) (arrows), while fewer or even none seen in N2 and the rescued worm. Fat staining was performed with young adults of N2, daf-22 (ok693), rescued worms using Oil red O. Scale-bars: 200 μm\n\nFigure 9: Figure 9. Post-embryonic developmental defects of C. elegans mutant was partially rescued by Hc-daf-22. a Brood size of N2, daf-22 (ok693), rescued worms. P-values were calculated by Dunnett’s test. Significant differences are indicated with different letters (a, b, c) (P < 0.05). b Developmental growth ratio of N2, daf-22 (OK693), rescued worms. Synchronized eggs were picked and the number of worms at each development stage was counted at 72 h. P-values were calculated by Dunnett’s test. c Body length of N2, daf-22 (ok693), rescued worms. P-values were calculated by Dunnett’s test. Significant differences are indicated with (a, b, c) (P < 0.05). d Body width of N2, daf-22 (ok693), rescued worms. P-values were calculated by Dunnett’s test. Significant differences are indicated with (a, b, c) (P < 0.05)\n\nFigure 10: Figure 10. Change in mRNA level of RNA interference with L4440-Hc-daf-22 in N2 C. elegans. The vector of L4440-Hc-daf-22 was constructed and transformed into HT115 cells. Wild type C. elegans were grown on NGM plates seeded with the transformed bacteria, while the empty vector of L4440 was used as a negative control. Relative quantification of Ce-daf-22 mRNA level of control N2 group and Hc-daf-22 RNAi group (P < 0.05)"
      }
    ]
  },
  {
    "id": "PMC5038976_multi",
    "image": [
      "images/PMC5038976-f1.png",
      "images/PMC5038976-f2.png",
      "images/PMC5038976-f3.png",
      "images/PMC5038976-f4.png",
      "images/PMC5038976-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"PARAQUAT TOLERANCE3 Is an E3 Ligase That Switches off Activated Oxidative Response by Targeting Histone-Modifying PROTEIN METHYLTRANSFERASE4b\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Confirmation of paraquat (PQ) tolerant phenotype. 7-day-old seedlings of wild type and pqt3 mutant were grown on MS medium supplemented with 0 or 2 μM paraquat. (B) Survival ratio of wild type and pqt3 mutant grown in (A). Values are mean ±SD (n = 30 plants, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (C) Multiple mutant alleles analysis of paraquat tolerance for the At4g17410 locus. Survival ratio of wild type, pqt3-1 and pqt3-2 (Salk_065409) grown in the 0, 0.5, 1, and 2 μM paraquat medium was counted. Values are mean ± SD (n = 30 plants, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (D) Late-flowering phenotype of pqt3-1 and pqt3-2 compared with wild type. Plants were grown under long day photoperiod (16 h light and 8 h dark). (E) The phenotype of 7-day-old pqt3-1, wild type, function complementation (FC), pqt3-2, and 35Spro:PQT3 seedlings under 0 μM (the top picture) or 2 μM (the bottom picture) paraquat treatment. Bar = 0.5 cm. (F) The survival ratio of pqt3-1, wild type, FC, pqt3-2, and 35Spro:PQT3 seeds germinated and grown on MS medium containing 0 μM or 2 μM paraquat for 7 days was counted. Values are mean ± SD (n = 30 plants, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (G-R) DAB staining. The leaves of wild type, pqt3-1, and pqt3-2 were treated without (H-J) or with 6 μM paraquat for 12 (L-N) or 24 h (P-R). 10 mM Na2HPO4 was used as the negative control to stain the leaves of wild type treated without (G) or with 6 μM paraquat for 12 (K) or 24 h (O). Bar = 0.5 cm.\n\nFigure 2: Figure 2. (A) GUS expression in 1-week-old seedling. Transgenic Arabidopsis plants expressing PQT3pro:GUS were generated and analyzed for GUS expression. Bar = 0.5 cm. (B) GUS expression in 3-week-old seedling. Bar = 0.5 cm. (C) GUS expression in root tissue of 7-week-old plant. (D) GUS expression in flower tissue. (E and F) GUS expression in silique tip (E) and junction (F). (G) GUS expression in 7-week-old adult Arabidopsis. (H-J) 35Spro:GFP was transiently expressed in onion epidermal cells as control. The GFP can be observed in both plasma membrane and nucleus. (K-M) Nucleus localization of the PQT3-GFP fusion protein in onion epidermal cell was observed. Bar = 20 μm. (N-P) The nucleus localization of PQT3-GFP fusion protein in the root tissue of stable transgenic seedlings expressing PQT3pro:PQT3-GFP. Bar = 20 μm.\n\nFigure 3: Figure 3. (A) The transcript level of PQT3 was down-regulated by paraquat treatment. 1-week-old seedlings were treated with 6 μM paraquat for the indicated times before RNA extraction for quantitative RT-PCR analysis. Values are mean ± SD (n = 3 experiments, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (B-F) The expression of PQT3 was down-regulated by other stress conditions. 1-week-old seedlings were treated by 10 mM H2O2 (B), 200 mM mannitol (C), drought (D), 200 mM CdCl2 (E), and 150 mM NaCl (F) for the indicated times before RNA extraction for quantitative RT-PCR analysis. Values are mean ± SD (n = 3 experiments, *P < 0.05, **P < 0.01, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (G-DD) GUS staining of 7-day-old PQT3pro:GUS transgenic lines without or with 6 μM paraquat, 10 mM H2O2, 200 mM mannitol, 200 mM CdCl2, 150 mM NaCl treatment for 3 h. GUS expressions were significantly reduced in primary root tip (G-L), root elongation zone (M-R), root maturation zone (S-X), root zone with LRP (Y-DD) under stress conditions. Bar = 50 μm.\n\nFigure 4: Figure 4. (A-J) Quantitative RT-PCR analysis of transcript levels of antioxidant enzyme genes. RNA samples were isolated from 7-day-old wild type and pqt3 seedlings for quantitative RT-PCR analysis. The transcript levels of APX (A), GPX (B), ACHT (C), FSD (D), CAT (E), GRXC (F), CSD (G), PRXQ (H), 2CPB (I) and MSD (J) were analyzed. Values are mean ± SD (n = 3 experiments, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (K and L) Enzyme activity of APX (K) and GPX (L) in wild type and pqt3 mutant. The pqt3 mutant has higher enzyme activity of APX and GPX than wild type. Values are mean ± SD (n = 3 experiments, ***P < 0.001). Asterisks indicate Student’s t-test significant differences.\n\nFigure 5: Figure 5. (A) Y2H assay. PQT3 and its four protein sections were used as the bait. PRMT4b was used as the prey. Krev1/RalGDS-wt act as strong positive control and Krev1/RalGDS-m1 act as weak positive control. Krev1/RalGDS-m2 was used for negative control. The yeast harboring various constructs was grown on SD-Leu-Trp medium (upper panel). The yeast was transferred to SD-Leu-Trp-His medium with 50 mM 3-AT (middle panel) or used for X-gal staining (lower panel). (B and C) The pull-down assay between PQT3 and PRMT4b. His-PRMT4b was incubated with amylose resin bound with recombinant MBP-PQT3-C66 protein. Pulled-down protein complex was detected by SDS-PAGE (B) and western blot using anti-His antibody (C). MBP protein was used as a negative control. (D) BiFC assay. Different plasmid combinations were expressed in epidermal cells of N. benthamiana leaves. Yellow fluorescence protein (YFP) was observed in epidermal cell expressing both NE-PQT3 (the N-terminal part of YFP fused with PQT3) and CE-PRMT4b (the C-terminal part of YFP fused with PRMT4b). No fluorescence was observed from the negative controls: NE-PQT3 / CE, NE / CE-PRMT4b, and NE / CE. The nuclei were stained by Hoechst and the fluorescence was detected by confocal. NE indicates pSPYNE vector and CE indicates pSPYCE vector."
      }
    ]
  },
  {
    "id": "PMC5038976_multi_2",
    "image": [
      "images/PMC5038976-f6.png",
      "images/PMC5038976-f7.png",
      "images/PMC5038976-f8.png",
      "images/PMC5038976-f9.png",
      "images/PMC5038976-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"PARAQUAT TOLERANCE3 Is an E3 Ligase That Switches off Activated Oxidative Response by Targeting Histone-Modifying PROTEIN METHYLTRANSFERASE4b\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) In vitro ubiquitination assay. GST-PQT3-N40 and GST-PQT3 were expressed in E. coli and purified. Nickel-HRP was used to detect His-tagged ubiquitin. The ubiquitination activity of PQT3 was observed only in the presence of E1 (from wheat), E2 (UBCh5b, from human), and 6×His-tagged ubiquitin (Ub). GST was used as negative control. The numbers on the left indicate the molecular masses of marker proteins. (B) In planta ubiquitination assay. Total protein samples were isolated from the infiltrated parts of N. benthamiana leaves 1 day after agroinfiltration. The total protein was analyzed via western blot using anti-HA antibody (upper panel). Immunoprecipitated samples were analyzed using western blot with anti-ubiquitin antibody subsequently (middle panel). Ponceau S staining of the Rubisco protein was shown as a loading control (lower panel). The numbers on the left indicate the molecular masses of marker proteins. (C and D) The effect of proteasome inhibitor MG132 on the protein level of PRMT4b in wild type and pqt3-1 mutant without or with paraquat treatment in time-course. Wild type and pqt3-1 mutant were grown for 14 days, then the seedlings were treated without or with 6 μM paraquat for 6 or 12 h in presence or absence of 50 μM proteasome inhibitor MG132. The total proteins were extracted. Western blot was performed using anti-PRMT4b antibody (C). Ponceau S staining of the rubisco protein serves as a loading control. Band densities were quantified using Quantity One software (Bio-Rad, USA) (D). Values are mean ± SD (n = 3 experiments, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (E) The survival ratio of wild type and pqt3 mutant germinated and grown on MS medium containing 0 μM or 1 μM paraquat without or with 15 μM MG132 for 7 days were counted. DMSO was used as control. Values are mean ± SD (n = 30 plants, *P < 0.05). Asterisk indicates Student’s t-test significant difference.\n\nFigure 7: Figure 7. (A) Paraquat tolerance assay. Survival ratio of wild type, pqt3-1 mutant, pqt3-2 mutant (Salk_065409), prmt4b mutant and 35Spro:PRMT4b grown on 0, 2, 3, or 5 μM paraquat medium were counted. The assay was repeated for three times. Values are mean ± SD (n = 50 plants, *P < 0.05, **P < 0.01, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (B) Primary root elongation of wild type and prmt4b mutant seedlings grown on MS without or with 150 μM CdCl2 was measured. Values are mean ± SD (n = 30 plants, **P < 0.01). Asterisks indicate Student’s t-test significant differences. (C-E) The phenotype of wild type, prmt4a, prmt4b, and prmt4aprmt4b grown on MS without (C) or with 1 μM paraquat (D). The survival ratio of wild type, prmt4a, prmt4b, and prmt4aprmt4b germinated and grown on MS medium containing 0 μM or 1 μM paraquat for 5 days were counted (E). Values are mean ± SD (n = 36 plants, *P < 0.05, **P < 0.01). Asterisks indicate Student’s t-test significant differences.(F) The transcript levels of APX1 and GPX1 in wild type, prmt4b mutant and 35Spro:PRMT4b. RNA samples were isolated from 7-day-old seedlings for quantitative RT-PCR analysis. Values are mean ± SD (n = 3 experiments, **P < 0.01, ***P < 0.001). Asterisks indicate Student’s t-test significant differences.\n\nFigure 8: Figure 8. (A and B) The illustration of APX1 and GPX1 chromatin. A to F represent different regions of APX1 chromatin (A). A to I represent different regions of GPX1 chromatin (B). Promoters (black lines), exons (white boxes), and introns (black lines) of APX1 and GPX1 were shown. (C and D) ChIP-PCR assay. Quantitative PCR was performed to verify each chromatin region of APX1 and GPX1 using specific primers. Fragments C, D and E in APX1 chromatin were enriched by anti-H3R17 antibodies in pqt3 mutant (C). Fragments C, D and I in GPX1 chromatin were enriched by anti-H3R17 antibodies in pqt3 mutant (D). UBQ5 was used as an internal control. Values are mean ± SD (n = 3 experiments, **P < 0.01, ***P < 0.001). Asterisks indicate Student’s t-test significant differences.(E-G) The enrichment of C fragment (E), D fragment (F) and E fragment (G) in APX1 chromatin was analyzed in wild type, pqt3 mutant, prmt4b mutant and pqt3prmt4b double mutants without or with paraquat treatment. UBQ5 was used as an internal control. Values are mean ± SD (n = 3 experiments, **P < 0.01, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (H-J) The enrichment of C fragment (H), D fragment (I) and I fragment (J) in GPX1 chromatin was analyzed in wild type, pqt3 mutant, prmt4b mutant and pqt3prmt4b double mutants without or with paraquat treatment. UBQ5 was used as an internal control. Values are mean ± SD (n = 3 experiments, **P < 0.01, ***P < 0.001). Asterisks indicate Student’s t-test significant differences.\n\nFigure 9: Figure 9. (A and B) The phenotypes of pqt3, pqt3prmt4b, wild type and prmt4b seedlings grown on MS without (A) or with 2 μM paraquat (B). (C) The survival ratio of pqt3, pqt3prmt4b, wild type and prmt4b under 2 μM paraquat treatment for 7 days were counted. Values are mean ± SD (n = 30 plants, **P < 0.01, ***P < 0.001). Asterisks indicate Student’s t-test significant differences. (D) The survival ratio of pqt3, pqt3prmt4a, wild type and prmt4a under 1 μM paraquat treatment for 7 days were counted. Values are mean ± SD (n = 30 plants, **P < 0.01). (E and F) The phenotypes of pqt3, pqt3prmt4a, wild type and prmt4a seedlings grown on MS without (E) or with 1 μM paraquat (F).\n\nFigure 10: Figure 10. Many environmental stresses cause oxidative stress in plants. Under oxidative stress, stress signaling up-regulates PRMT4b expression and down-regulates PQT3 expression, leading to higher PRMT4b activity that will activate APX1 and GPX1 and enhance antioxidation capacity of APX1 and GPX1. When oxidative stress is diminished, PRMT4b expression is decreased and PQT3 expression is increased. As a result, PQT3 activity is increased, leading to faster removal of PRMT4b via 26S proteasome. Together with decreased PRMT4b expression, PRMT4b activity will rapidly drop, leading to decreased expression of APX1 and GPX1. The activated response of oxidative stress is then switched off."
      }
    ]
  },
  {
    "id": "PMC5041579_multi",
    "image": [
      "images/PMC5041579-f2.png",
      "images/PMC5041579-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"SPATA5 mutations cause a distinct autosomal recessive phenotype of intellectual disability, hypotonia and hearing loss\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. a Pedigree and picture of family B. b Schematic structure of SPATA5 and identified alterations. Previously reported variants are indicated in black, the variants identified in this study c.1822_1824del; p.Asp608del, c.2081G > A; p.Gly694Glu and c.989_991delCAA; p.Thr330del are indicated in red\n\nFigure 3: Figure 3. Structure of the AAA ATPase domains of SPATA5. a Model of the hexameric quaternary structure of SPATA5 showing the individual subunits in different colours. ADP-molecules bound to the ATPase domains are shown in stick presentation and coloured according to their atom type. p.Asp608 and p.Gly608Glu are located at the subunit interface and are depicted as black and magenta balls, respectively. pThr330 is located N-terminally adjacent to the globular domain and is shown as brown ball. b Enlargement showing the stabilizing interactions of p.Asp608 (D608) with p.Lys517 (K517) of the adjacent subunit (both residues are shown in stick presentation). The salt-bridge between both residues is shown in green and the subunits are coloured in red and blue respectively. c Deletion of p.Asp608 (D608) results in a loss of the helical secondary structure (pink arrow) and of the intersubunit salt-bridge. d Enlargement showing the location of pGly694 (G694) at the subunit interface. e Replacement of p.Gly544 by glutamate (E694) results in electrostatic repulsion (black arrow) with p.Asp630 (D630) of the adjacent subunit"
      }
    ]
  },
  {
    "id": "PMC5053739_multi",
    "image": [
      "images/PMC5053739-f1.png",
      "images/PMC5053739-f2.png",
      "images/PMC5053739-f3.png",
      "images/PMC5053739-f4.png",
      "images/PMC5053739-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of UHRF1 by dual-strand tumor-suppressor microRNA-145 (miR-145-5p and miR-145-3p): inhibition of bladder cancer cell aggressiveness\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Expression levels of miR- 145- 5p and miR-145-3p in clinical specimens and BC cell lines were determined by qRT-PCR. Data were normalized to RNU48 expression. (B) Correlation of miR-145-5p and miR-145-3p expression. (C) Cell growth was determined by XTT assays 72 hours after transfection with 10 nM miR-145-5p or miR-145-3p. *P < 0.0001. (D) Cell migration activity was determined by the wound-healing assays. *P < 0.0001. (E) Cell invasion activity was determined using Matrigel invasion assays. *P < 0.0001.\n\nFigure 2: Figure 2. (A, C) Apoptosis assays were carried out using flow cytometry. Early apoptotic cells are in area R4 and apoptotic cells are in area R2. The normalized ratios of apoptotic cells are shown in the histograms. Cycloheximide (2 μg/mL) was used as positive control. *P = 0.0266 and **P < 0.0001. (B, D) Western blot analyses for apoptotic markers (cleaved PARP) in BC cell lines. GAPDH was used as a loading control.\n\nFigure 3: Figure 3. A total of 4,555 and 6,295 downregulated genes in expression analysis of miR-145-5p and miR-145-3p transfected BC cell lines, respectively, (T24 and BOY) were selected as putative target genes. Next we merged the data of those selected genes and the microRNA.org database. The analyses showed 398 common putative target genes between miR-145-5p and miR-145-3p. We then analyzed gene expression with available GEO data sets (GSE11783 + GSE31684). The analyses showed that 79 genes were significantly upregulated in BC specimens compared with NBE.\n\nFigure 4: Figure 4. (A) UHRF1 mRNA expression was evaluated by qRT-PCR in T24 and BOY 72 hours after transfection with miR-145-5p and miR-145-3p. GUSB was used as an internal control. *P = 0.0036 and **P < 0.0001. (B) UHRF1 protein expression was evaluated by Western blot analyses in T24 and BOY 72–96 hours after transfection with miR-145-5p or miR-145-3p. GAPDH was used as a loading control. (C) miR-145-5p and miR-145-3p binding sites in the 3′ UTR of UHRF1 mRNA. Dual Luciferase reporter assays using vectors encoding putative miR-145-5p and miR-145-3p target sites of the UHRF 3′ UTR (positions 1,179–1,198 and 287–292, respectively) for both wild-type and deleted regions. Normalized data were calculated as ratios of Renilla/firefly luciferase activities. *P < 0.0001.\n\nFigure 5: Figure 5. (A) UHRF1 mRNA expression was evaluated by qRT-PCR in T24 and BOY 72 hours after transfection with si-UHRF1-1 and si-UHRF1-2. GUSB was used as an internal control. (B) UHRF1 protein expression was evaluated by Western blot analysis in T24 and BOY 72 - 96 hours after transfection with miR-145-5p or miR-145-3p. GAPDH was used as a loading control. (C) Cell proliferation was determined with the XTT assays 72 hours after transfection with 10 nM si-UHRF1-1 or si-UHRF1-2. *P < 0.0001. (D) Cell migration activity was determined by wound-healing assays. *P < 0.0001. (E) Cell invasion activity was determined using Matrigel invasion assays. *P < 0.0001."
      }
    ]
  },
  {
    "id": "PMC5053739_multi_2",
    "image": [
      "images/PMC5053739-f6.png",
      "images/PMC5053739-f7.png",
      "images/PMC5053739-f8.png",
      "images/PMC5053739-f9.png",
      "images/PMC5053739-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of UHRF1 by dual-strand tumor-suppressor microRNA-145 (miR-145-5p and miR-145-3p): inhibition of bladder cancer cell aggressiveness\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A, C) Apoptosis assays were carried out using flow cytometry. Early apoptotic cells are in area R4 and apoptotic cells are in area R2. The normalized ratios of the apoptotic cells are shown in the histogram. Cycloheximide (2 μg/mL) was used as a positive control. *P < 0.0001 (B, D) Western blot analyses for apoptotic markers (cleaved PARP) in BC cell lines. GAPDH was used as a loading control.\n\nFigure 7: Figure 7. (A) Expression levels of UHRF1 in clinical specimens and BC cell lines were determined by qRT-PCR. Data were normalized to GUSB expression. (B) The correlated expression among miR-145-5p, miR-145-3p, and UHRF1. (C) Association of UHRF1 expression with clinicopathological parameters. Relationships between two variables were analyzed using the Mann-Whitney U test.\n\nFigure 8: Figure 8. Kaplan-Meier survival curves for cause specific survival rates based on UHRF1 expression in 57 BC patients. P-values were calculated using the log-rank test.\n\nFigure 9: Figure 9. UHRF1 was expressed more strongly in several cancer lesions than in noncancerous tissues. Left panel, original magnification ×40; Right panel, original magnification ×200. (A) Positively stained tumor lesion (High grade, T2bN0M0), (B) Positively stained tumor lesion (High grade, T1N0M0), (C) Positively stained tumor lesion (Low grade, T3N0M0), (D) Negative staining in normal bladder tissue.\n\nFigure 10: Figure 10. (A) A total of 2,222 and 1,512 downregulated genes in expression analyses of si-UHRF1 transfectants of BC cell lines (T24 and BOY, respectively) were selected. We then analyzed 533 common downregulated genes by using available GEO data sets (GSE11783 + GSE31684). The analyses showed that 104 genes were significantly upregulated in BC specimens compared with NBE. (B) A total of 2,665 and 2,434 upregulated genes in expression analysis of si-UHRF1 transfectants of BC cell lines (T24 and BOY, respectively) were selected. We then analyzed 704 common upregulated genes by using GEO data sets. The analyses showed that 62 genes were significantly downregulated in BC specimens compared with NBE."
      }
    ]
  },
  {
    "id": "PMC5059523_multi",
    "image": [
      "images/PMC5059523-f1.png",
      "images/PMC5059523-f2.png",
      "images/PMC5059523-f3.png",
      "images/PMC5059523-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"ABC Transporter Subfamily D: Distinct Differences in Behavior between ABCD1–3 and ABCD4 in Subcellular Localization, Function, and Human Disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Hypothesized structure of the ABCD transporter. The ABCD transporters are comprised of a half-size ABC transporter, with one transmembrane domain (TMD) and one nucleotide-binding domain (NBD). Six transmembrane domains are located in the NH2-terminal half of the transporter, and Walker A, Walker B, and ABC signature are located in the COOH-terminal half of the transporter.\n\nFigure 2: Figure 2. Targeting and localization of the ABCD transporters. For the trafficking of the ABCD transporters, an NH2-terminal H0 motif plays an important role. The ABCD1–3 forms possessing this H0 motif are selectively captured by Pex19p and destined for peroxisomes. In contrast, ABCD4 hardly interacts with Pex19p because of its lack of the H0 motif, and, as a result, ABCD4 is recognized by a signal recognition particle (SRP) and integrated into the ER membrane. Subsequently, ABCD4 is translocated to lysosomes through the association with LMBD1. GFP-tagged ABCD1 and ABCD3 were expressed in CHO cells. The distribution of ABCD1 and ABCD3 was compared with that of peroxisomes stained with anti-catalase [36]. The localization of ABCD2 was cited from [6] with some modification. HA-tagged ABCD2 was expressed in COS cells. The distribution of HA-ABCD2 was compared with that of catalase. HA-tagged ABCD4 was expressed in CHO cells stably expressing LMBD1-GFP [17]. The subcellular localization of ABCD4-HA and LMBD1-GFP was compared with that of lysosomes labeled with anti-LAMP1. Bar, 10 μm.\n\nFigure 3: Figure 3. Substrate specificity of the ABCD transporters. ABCD1–3 predominately exist as a homodimer. ABCD1 and ABCD2 have overlapping substrate specificities toward saturated and monounsaturated VLCFA-CoAs. However, ABCD1 has a higher specificity to C24:0-CoA and C26:0-CoA than ABCD2. In contrast, ABCD2 has a higher specificity for polyunsaturated C22:6-CoA and C24:6-CoA. ABCD3 is thought to be involved in the transport of LCFA-CoA, branched chain acyl-CoA, and the bile acid intermediates, THCA-CoA and DHCA-CoA. ABCD4 is deduced to be involved in the transport of cobalamin from lysosomes to the cytosol.\n\nFigure 4: Figure 4. Distribution of the missense mutations reported in X-ALD patients. 209 different amino acids with single amino acid substitutions have been identified. Based on the X-ALD database, G266R, R401Q, R518Q, R554H, P560L, E609K, R617H, and R660W are the most frequent. The mutant ABCD1 proteins, such as G266R, R401Q, and R554H, are unaffected in terms of protein stability. In contrast, mutant ABCD1 proteins with missense mutations (R518Q, P560L, E609K, R617H, and R660W) in COOH-terminal nucleotide-binding domains are decreased or not detected in the corresponding patient fibroblasts."
      }
    ]
  },
  {
    "id": "PMC5065608_multi",
    "image": [
      "images/PMC5065608-f1.png",
      "images/PMC5065608-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Cholic acid therapy in Zellweger spectrum disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Tuckey boxplots showing the effect of oral cholic acid (CA) therapy on plasma CA concentrations, 3α,7α,12α-trihydroxycholestanoic acid (THCA), 3α,7α-dihydroxycholestanoic acid (DHCA), fibroblast growth factor 19 (FGF19) and 7α-hydroxy-4-cholesten-3-one (C4) in the entire cohort of patients with a ZSD (n = 19). Run-in was defined as 2.5 and 2 years prior to treatment. The reference range of CA is 0.1–4.7 μmol/L and THCA <0.05–0.1 μmol/L. Levels of DHCA are undetectable (<0.05 μmol/L) in controls. No reference range for FGF19 and C4 in children exists. Statistical analyses were performed with a Wilcoxon matched-pairs signed-rank sum test. *P < 0.05; ***P < 0.005; ****P < 0.001. Abbreviation: ns not significant. b Tuckey boxplots showing the effect of oral cholic acid (CA) therapy on plasma CA concentrations, 3α,7α,12α-trihydroxycholestanoic acid (THCA), 3α,7α-dihydroxycholestanoic acid (DHCA), fibroblast growth factor 19 (FGF19) and 7α-hydroxy-4-cholesten-3-one (C4) in subgroups defined by baseline liver stiffness values. Run-in was defined as 2.5 and 2 years prior to treatment. The reference range of CA is 0.1–4.7 μmol/L and THCA <0.05–0.1 μmol/L. Levels of DHCA are undetectable (<0.05 μmol/L) in controls. No reference range for FGF19 and C4 in children exists. Statistical analyses were performed with a Wilcoxon matched-pairs signed-rank sum test. *P < 0.05; **P < 0.01; ***P < 0.005. Abbreviation: ns not significant\n\nFigure 2: Figure 2. Tuckey boxplots showing the effect of oral cholic acid (CA) therapy on plasma levels of aspartate transaminase (AST), alanine transaminase (ALT) and conjugated bilirubin in subgroups defined by baseline liver stiffness values. Run-in was defined as 2.5 and 2 years prior to treatment. The reference range (depicted as a dashed line in each boxplot) of AST is 0–45 U/L, of ALT 0–40 U/L and of conjugated bilirubin 0–5 μmol/L. Statistical analyses were performed with a Wilcoxon matched-pairs signed-rank sum test. CA supplementation had no significant effects on these parameters at any of the studied time points after start of therapy"
      }
    ]
  },
  {
    "id": "PMC5078786_multi",
    "image": [
      "images/PMC5078786-f1.png",
      "images/PMC5078786-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The use of targeted genomic capture and massively parallel sequencing in diagnosis of Chinese Leukoencephalopathies\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Flow diagram to exhibit workflow and results in this cohort. (B) Pie chart to exhibit the etiology composition of leukoencephalopathies in this cohort. MLD: metachromatic leukodystrophy, VWM: vanishing white matter disorder, AD: Alexander disease, PMD: Pelizaeus-Merzbacher Disease, X-ALD: X-linked adrenoleukodystrophy, MLC: megalencephalic leukoencephalopathy with subcortical cysts, GLD: globoid cell leukodystrophy.\n\nFigure 2: Figure 2. On FLAIR and T2-weighted sequences, abnormal hyperintense is seen in the splenium of corpus callosum, adjacent parieto-occipital white matter, posterior limbs of internal capsules extending to centrum oval, thalami and upper cervical spinal cord. Gadolinium enhancement is visible on T1-weighted sequences in internal capsules and anterior commissure. The child detected missense mutation on chr6:42932599(c.2735C > T) and nonsense mutation on chr6:42937459(c.1313insT), which were respectively inherited from the parents. (a) Brain MRI T1-weighted image. (b) Brain MRI T2-weighted image. (c) Brain MRI flare image. (d) Brain MRI enhanced image. (e–g) The electropherogram of Sanger sequencing of the probands (e), the father (f) and the mother (g) on chr6:42932599. (h–j) The electropherogram of Sanger sequencing of the probands (h), the father (i) and the mother (j) on chr6:42937459."
      }
    ]
  },
  {
    "id": "PMC5082900_multi",
    "image": [
      "images/PMC5082900-f1.png",
      "images/PMC5082900-f2.png",
      "images/PMC5082900-f3.png",
      "images/PMC5082900-f4.png",
      "images/PMC5082900-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"HIV-1 Tat Recruits HDM2 E3 Ligase To Target IRF-1 for Ubiquitination and Proteasomal Degradation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Tat affects IRF-1 stability. (A) HEK293 cells were transfected with a 3,500-bp fragment of the IRF-1 promoter linked to the luciferase reporter gene alone or in combination with increasing amounts of Tat-expressing vector. After 24 h, cells were treated for 4 h with 10 ng/ml of TNF-α (+), where indicated, and then processed for luciferase activity. Data shown are the means plus standard errors of the means (SEM) (error bars) from three separate experiments calculated after normalization with the Renilla activity. The values for untreated cells were set at 1. (B) HEK293 cells were transfected with increasing amounts of Tat-expressing vector. At 24 h after transfection, cells were harvested, and IRF-1 RNA levels were assessed using real-time RT-PCR. The levels were normalized to GAPDH mRNA abundance. The means plus SEM of three independent experiments are shown as relative expression units. The values for untreated cells were set at 1. (C) HEK293 cells were transfected with IRF-1 expression vector in the presence (+) or absence (−) of Flag-Tat expression vector. At 24 h posttransfection, the cells were treated with CHX for the indicated time. IRF-1 and Tat proteins were detected with anti-IRF-1 (α-IRF-1) and anti-Flag (α-Flag) antibodies, respectively. Data plotted in the graph represent the means ± SEM from three different assays of IRF-1 protein bands quantified from Western blots and normalized to actin protein levels as the loading control and presented as percentage values relative to those without CHX treatment set at 100%. (D) HEK293 cells were cotransfected with expression vectors for His6-Ub and IRF-1 in the presence or absence of Flag-Tat-expressing vector. His-Ub-conjugated proteins were captured by nickel-agarose beads, eluted, and analyzed by Western blotting with anti-IRF-1 antibody. Western blotting of cell lysates shows the expression of ectopically expressed proteins. (E) HEK293 cells were cotransfected with expression vectors for IRF-1 and Flag-Tat and then treated with MG132 for 2 h where indicated. IRF-1 and Tat expression was detected by Western blotting. Data plotted in the graph represent the means plus SEM from three different assays of IRF-1 protein bands quantified from Western blots and normalized to actin protein levels as the loading control. Results are presented as percentage values relative to basal IRF-1 expression set at 100. Blots are representative of at least three independent experiments with similar results.\n\nFigure 2: Figure 2. HDM2 E3 ligase mediates Tat-induced IRF-1 turnover. (A) HEK293 cells were transfected with expression vectors encoding IRF-1 alone or in combination with increasing amounts of GFP-tagged HDM2 (GFP-HDM2), as indicated. The cells were treated with CHX for the indicated time, and cell lysates were then subjected to immunoblotting. Data plotted in the graph represent the means ± SEM from three different assays of IRF-1 protein bands quantified from Western blots and normalized to actin protein levels as the loading control and presented as percentage values relative to those without CHX treatment set at 100. (B) HEK293 cells were transfected with expression vectors for IRF-1, Flag-Tat, and HDM2-GFP expression vector as indicated. The cells were then treated with CHX, and IRF-1 expression was assessed by immunoblotting. Data plotted in the graph are calculated and presented as in panel A. (C) HEK293 cells were transfected with expression vectors encoding IRF-1, GFP-HDM2, and wild-type Flag-Tat (Flag-Tatwt) or Flag-TatC22G. The cells were then treated with CHX, and IRF-1 expression was assessed as described above for panel A. (D) HEK293 cells were transfected with expression vectors for Flag-IRF-1 and Tat and/or GFP-HDM2, as indicated. Whole-cell extracts were incubated with anti-Flag (α-Flag)-conjugated resin or control IgG, and immunoprecipitated (IP) complexes were separated by SDS-PAGE and subsequently probed with anti-Tat, anti-GFP, or anti-IRF-1 antibodies, respectively. The levels of ectopically expressed proteins are shown in the INPUT blots.\n\nFigure 3: Figure 3. Tat increases HDM2-mediated K48 polyubiquitination of IRF-1. (A) IRF-1 ubiquitination in the presence of Flag-Tat, GFP-HDM2, or both was monitored as described in the legend to Fig. 1D. Western blots show the expression, in whole-cell extracts (WCE), of ectopically expressed proteins. (B) HEK293 cells were cotransfected with Flag-tagged IRF1, GFP-HDM2, and Tat alone or in combination, as indicated. Two-hour treatment with MG132 (lane 2) or IL-1β (lane 7) was used for positive internal controls. Immunoprecipitation (IP) with Flag-conjugated resin was performed, and the IRF1 ubiquitination forms were detected by Western blotting or immunoblotting (IB) with anti-K48-linked ubiquitin (α-K48-Ub) or anti-K63-linked ubiquitin (α-K63-Ub) or control IgG. Western blots show the expression, in whole-cell extracts, of ectopically expressed proteins.\n\nFigure 4: Figure 4. Tat-mediated IRF-1 degradation requires the IRF-1 C-terminal domain. (A) HEK293 cells were cotransfected with expression vectors for an IRF-1 mutant with the 34-aa COOH terminus deleted (IRF1291), Flag-Tat, and GFP-HDM2, alone or in combination. One day after transfection, the cells were treated with CHX for the indicated time points, and expression of IRF1291, Tat, and HDM2 was detected by Western blotting using specific antibodies, as indicated. (B) IRF1291 ubiquitination in the presence of Flag-Tat, GFP-HDM2, or both, was monitored as described in the legend to Fig. 3A. Western blots show the expression of ectopically expressed proteins in whole-cell extracts. (C) HEK293 cells were cotransfected with the indicated expression vectors, immunoprecipitated with anti-IRF-1 antibodies, and Tat and HDM2 were detected by Western blotting using the indicated antibodies. INPUT shows the level of ectopically expressed proteins.\n\nFigure 5: Figure 5. Inhibition of IRF-1-dependent transcription by HDM2 is accelerated in the presence of Tat. Transcription of the IRF-1-responding constructs pTA-ISRE-Luc (Luc stands for luciferase) (A) and the human p21 gene promoter linked to the luciferase reporter gene (B) was measured by dual-luciferase assay in whole-cell extracts from HEK293 cells 24 h after transfection with expression vectors for IRF-1, Tat, and HDM2 as indicated. Means plus standard deviations (SD) from three separate experiments were calculated after normalization with the Renilla activity are shown. Values that are significantly different are indicated by bars and asterisks as follows: *, P < 0.05; **, P < 0.01; ***, P < 0.001."
      }
    ]
  },
  {
    "id": "PMC5082900_multi_2",
    "image": [
      "images/PMC5082900-f6.png",
      "images/PMC5082900-f7.png",
      "images/PMC5082900-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"HIV-1 Tat Recruits HDM2 E3 Ligase To Target IRF-1 for Ubiquitination and Proteasomal Degradation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. IRF-1 degradation is increased in cells expressing Tat protein. (A) HEK293 cells were transfected with the indicated doses of expression vector encoding Flag-Tat, and one day after transfection, the cells were treated with 10 ng/ml of TNF-α for 4 h. Cell lysates were then subjected to immunoblotting using anti-IRF-1 and anti-Flag antibodies. Data plotted in the graph represent the means plus SEM from three different assays of IRF-1 and Tat protein bands quantified from Western blots and normalized to actin protein levels as the loading control. Results are presented as percentage values relative to IRF-1 expression in control TNF-treated cells and ectopically expressed Tat (2 µg) set at 100. (B) Jurkat A2 cells were induced by TNF-α for 48 h to express Tat, and the levels of IRF-1 and Tat proteins were determined by Western blotting analysis using specific anti-IRF-1 and anti-Tat antibodies, respectively. Means plus SD from three separate experiments calculated after normalization with actin and with the control set at 100% are shown (***, P < 0.001). (C) Endogenous IRF-1 protein was immunoprecipitated using anti-IRF-1 antibody from A72 and A2 Jurkat cell lines treated with TNF-α (+) or not treated with TNF-α (−). IRF-1 ubiquitination was detected upon blotting with anti-K48 ubiquitin antibody (α-K48). The levels of ectopically expressed proteins are shown in the INPUT blots.\n\nFigure 7: Figure 7. IRF-1 is downregulated and K48 polyubiquitinated in HIV-1-infected Jurkat T cells and during HIV-1 de novo infection of human primary CD4+ T cells when Tat is maximally expressed. (A, top) Tat/Rev RNA levels were measured by real-time RT-PCR as described in Materials and Methods. Means plus SD from three separate experiments calculated after normalization with GAPDH are shown (*, P < 0.05; ***, P < 0.001). (Bottom) WCE were prepared at the indicated time points from infected and uninfected Jurkat cells and then probed with anti-IRF-1, anti-HDM2, and anti-actin antibodies, respectively. Representative Western blots are shown. Data plotted in the graphs represent the means ± SEM from three different assays of IRF-1 and HDM2 protein bands quantified from Western blots and normalized to actin protein levels as the loading control (CTR). Results are presented as percentage values relative to basal IRF-1 and HDM2 expression set at 100. (B) WCE were prepared at the indicated time points from control and HIV-1-infected cells and immunoprecipitated with anti-IRF-1 antibody. IRF-1 ubiquitinated forms were detected using anti-K48 ubiquitin antibody (α-K48). The Western blot is representative of at least three independent experiments with similar results. (Bottom) The levels of IRF-1 in control cells, HIV-1-infected cells, and HIV-1-infected cells in the presence of MG132 are shown. Data plotted in the graphs are the means plus SD of IRF-1-specific bands quantified from Western blots normalized to actin from three independent experiments (*, P < 0.05; **, P < 0.01; ***, P < 0.001). (C) WCE as in panel A were probed with anti-p21 and anti-CDK2 antibodies, respectively. (Top) Quantification of p21 and CDK2 calculated as in panel A. (Bottom) Representative Western blots. (D) Purified human primary CD4+ T cells were infected with HIV-1 as described in Materials and Methods, and WCE were subjected to Western blot analysis with specific anti-IRF-1 antibody. Data plotted in the graph represent the means plus SD from three independent experiments (*, P < 0.05; **, P < 0.01). The time (in hours postinfection [hr p.i.]) is shown below the blot. (E) Total RNA was extracted at the indicated time points from cells as described above for panel D and analyzed by real-time RT-PCR for the doubly spliced (Tat/Rev) transcript as described in Materials and Methods (**, P < 0.01; ***, P < 0.001).\n\nFigure 8: Figure 8. Schematic representation of the dual effect of Tat on IRF-1 activity in the course of HIV-1 infection. In early phases of HIV-1 replication, IRF-1 is transcriptionally stimulated by viral infection, and it is recruited by small amounts of Tat on the viral promoter to drive, with NF-κB, initial transcription of the integrated provirus. Later, when discrete amounts of Tat are produced and IRF1 activity on LTR is dispensable for the virus to replicate, Tat nullifies the function of IRF-1, accelerating its proteasome-mediated degradation upon recruitment of the HDM2 E3 ligase, thus quenching its activity on target gene promoters."
      }
    ]
  },
  {
    "id": "PMC5137149_multi",
    "image": [
      "images/PMC5137149-f1.png",
      "images/PMC5137149-f2.png",
      "images/PMC5137149-f3.png",
      "images/PMC5137149-f4.png",
      "images/PMC5137149-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitin Ligase NEDD4 Regulates PPARγ Stability and Adipocyte Differentiation in 3T3-L1 Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Interaction between NEDD4 and PPARγ in 3T3-L1 adipocytes. Total lysates (500 μg) were immunoprecipitated with 1 μg of anti-PPARγ antibody (clone E-8). Normal mouse IgG served as negative control. (B) In vivo interaction between NEDD4 and PPARγ. Epididymal adipose tissue lysates (500 μg) were immunoprecipitated with 1 μg of anti-PPARγ antibody (clone E-8) and immunoblotted with anti-NEDD4 antibody. PPARγ immunoblot was performed with clone T.647.5. (C) Co-immunoprecipitation of NEDD4 and PPARγ in HEK293 cells transiently expressing plasmids containing T7-tagged NEDD4 and FLAG-tagged PPARγ2. The rabbit monoclonal anti-PPARγ antibody (clone T.647.5) was used for immunoprecipitation, and the mouse monoclonal anti-PPARγ antibody (clone E-8) was used for immunoblotting. Lysates pulled down with normal rabbit IgG served as negative control. Full-length blots are presented in Supplementary Fig. S4.\n\nFigure 2: Figure 2. (A) Schematic drawings of PPARγ protein domains and domain-deleted mutants. GAL4DBD-HA plasmid was fused with AF-1, DBD, Hinge, or LBD domain of mouse PPARγ2. (B,C) The PPxY motif is not required for NEDD4-PPARγ interaction. HEK293 cells were transiently co-transfected with T7‐tagged NEDD4 and FLAG‐tagged PPARγ2 or its mutants. The mouse anti-PPARγ antibody was used for immunoprecipitation. For immunoblotting, the mouse anti-PPARγ (clone E-8) antibody was used in panel B, while the rabbit anti-PPARγ (clone T.647.5) antibody was used in panel C. The IgG heavy chain was thus not detected in panel C. (D) NEDD4 interacts with the hinge and LBD domains of PPARγ. GAL4DBD-HA plasmids containing AF-1, DBD, Hinge, or LBD domain of PPARγ2 were co-expressed in HEK293 cells with T7‐NEDD4. Lysates were immunoprecipitated with anti-HA antibody. (E) Interaction between NEDD4 and domain-deleted FLAG-PPARγ2. HEK293 cells were transfected with T7-NEDD4 alone, or together with FLAG-PPARγ2, FLAG-PPARγ2∆Hinge (without amino acids 206–280), FLAG-PPARγ2∆LBD (without amino acids 281–505), or FLAG-PPARγ2∆∆ (without amino acids 206–505). Cells were harvested 48 hours after transfection. MG132 (10 μM) was added to the cells 16 hr before harvesting. Lysates were immunoprecipitated with anti-FLAG antibody. The rabbit anti-PPARγ (clone H-100) antibody against N-terminal PPARγ was used for immunoblotting. Arrowhead indicates expected size of the ∆∆ mutant. Full-length blots are presented in Supplementary Fig. S4.\n\nFigure 3: Figure 3. (A) Dose-dependent expression of NEDD4 does not reduce steady-state PPARγ protein abundance. Quantification of NEDD4 and PPARγ levels is on the right. Variable amounts of pRc-CMV-T7-NEDD4 expression vector from 1 to 3 μg were transfected with the PPARγ into HEK293 cells. NEDD4 plasmid expression saturates at 2 μg per well of a 6-well plate. (B) 1 μg of either FLAG-tagged SIAH1 or HA-tagged SIAH2, together with 1 μg of T7-tagged NEDD4, were transfected into CHO cells stably expressing FLAG-tagged PPARγ2. The relative PPARγ levels are quantified on the right. (C) NEDD4 overexpression enhances in vivo ubiquitination of PPARγ. T7-tagged NEDD4, FLAG-tagged PPARγ2, and HA-tagged ubiquitin (Ub) were transiently expressed in HEK293 cells at a ratio of 1.5:1:2 in combinations as indicated above the blots. (D) NEDD4 knockdown reduces in vivo ubiquitination of PPARγ. HEK293 cells seeded on 6-well plates were transfected with 1 μg of FLAG-tagged PPARγ2, 2 μg of HA-tagged Ub, along with 1.5 μg of plasmid containing NEDD4-targeting shRNA or non-targeting control shRNA per well. Cells were harvested for Western analysis 48 hr after the transfection. (E) NEDD4 overexpression enhances lysine-48 independent ubiquitination of PPARγ. T7-tagged NEDD4, FLAG-tagged PPARγ2, along with HA-tagged wild-type (WT) Ub or HA-tagged K48R Ub were transfected into HEK293 cells at a ratio of 1.5:1:2 in combinations as indicated above the blots. Western assays were performed at 48 hr after the transfection. (F) In vitro ubiquitination assay between NEDD4 and escalating amounts of recombinant His-GST tagged PPARγ2. (G) In vitro PPARγ2 ubiquitination by NEDD4 in the presence of wild-type ubiquitin (WT-Ub), K48-only ubiquitin (K48O-Ub), or K63-only (K63O-Ub). Data represent mean ± SEM of 3 independent experiments; *P < 0.05, **P < 0.01. Full-length blots are presented in Supplementary Fig. S4.\n\nFigure 4: Figure 4. (A,B) NEDD4 regulates PPARγ protein half-life. Representative western blot image of PPARγ protein levels during cycloheximide-chase experiment. CHO cells stably expressing FLAG-tagged PPARγ2 were transfected with indicated plasmids. Two days after transfection, cells were treated with cycloheximide for the indicated times. Quantification of data is shown below. (C) The human (h) or rat (r) NEDD4 cDNAs were expressed in CHO cells stably expressing FLAG-tagged PPARγ2. Cycloheximide was added to the media 2 hr before cell harvesting. Quantification of data is on the right. (D,E) CHO cells stably expressing FLAG-tagged PPARγ2 were co-transfected with the indicated plasmids and treated with or without the indicated reagents. Cycloheximide and MG132 were added to the media 15 hr before cell harvesting. Cycloheximide was used at 20 μM. MG132 was used at 10 μM. Data represent mean ± SEM of 3–4 independent experiments; *P < 0.05, **P < 0.01, ***P < 0.001. CHX: cycloheximide. Full-length blots are presented in Supplementary Fig. S4.\n\nFigure 5: Figure 5. (A) Photographs and micrographs of oil red O staining of the differentiated adipocytes. Either DMSO, 10 μM of rosiglitazone, or 10 μM of GW 9662 were added to the 3T3-L1 cells at the beginning of adipocyte differentiation and were replaced with culture media every 2 days. The 3T3-L1 cells were infected with AAV virus for expressing non-targeting shRNA control (shControl) or NEDD4-targeting shRNA (shNEDD4) 2 days before adipocyte differentiation. Photographs and micrographs were taken 5 days or 10 days after differentiation. Scale bar represents 40 μm. (B) Endogenous PPARγ and C/EBPα expression levels during 3T3-L1 adipocyte differentiation in the presence of AAV virus were measured by Western analysis. (C) Quantification of the endogenous PPARγ1 and PPARγ2 protein expression from panel B. (D–G) The mRNA levels of (D) aP2, (E) C/EBPα, (F) PPARγ, and (G) NEDD4 during 3T3-L1 adipocyte differentiation in the presence of AAV virus. (H) NEDD4 has no direct effect on the transcriptional activity of PPARγ. HEK293 cells were transiently co-transfected with 3 × PPRE-Luc, FLAG-tagged PPARγ2, Renilla luciferase control reporter vector pRL-SV40 and plasmids indicated under each column. After 32 hr, cells were treated with or without rosiglitazone (10 μM) for 16 hr prior to luciferase assay. Luciferase activity was normalized to Renilla activity as a control for transfection efficiency. IDM: 0.5 mM IBMX, 1 μM dexamethasone, and 1.5 μg/mL insulin. Data represent mean ± SEM of 3 independent experiments; *P < 0.05, **P < 0.01, n.s., no significance. Full-length blots are presented in Supplementary Fig. S4."
      }
    ]
  },
  {
    "id": "PMC5137149_multi_2",
    "image": [
      "images/PMC5137149-f6.png",
      "images/PMC5137149-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Ubiquitin Ligase NEDD4 Regulates PPARγ Stability and Adipocyte Differentiation in 3T3-L1 Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Representative western blot image of PPARγ expression in differentiated 3T3-L1 cells in the presence of ligand. The 3T3-L1 cells were differentiated for 8 days and treated with 5 μM of rosiglitazone for 16 hr with or without the pretreatment of lysosome inhibitor chloroquine (25 μM) or proteasome inhibitor MG132 (10 μM). Quantification figure is on the right. (B) Effect of NEDD4 knockdown on PPARγ expression in differentiated 3T3-L1 cells in the presence or absence of ligand. The 3T3-L1 cells infected with shControl or shNEDD4 AAV were differentiated for 6 days and treated with or without 5 μM of rosiglitazone for 16 hr. Representative western blot image is shown and its quantification figure is shown below. (C) NEDD4 knockdown reduces PPARγ ubiquitination in 3T3-L1 adipocytes in the presence or absence of ligand. The 3T3-L1 cells infected with shControl or shNEDD4 AAV were differentiated for 6 days and treated with or without 5 μM of rosiglitazone for 16 hr. MG132 (10 μM) was added to the media 6 hr before harvesting the cells. Arrows indicate NEDD4, PPARγ1 and γ2. (D) Representative western blot image of time-dependent expression changes of PPARγ in AAV infected 3T3-L1. The 3T3-L1 cells infected with shControl or shNEDD4 AAV were differentiated for 2–3 days and treated with or without 5 μM of rosiglitazone for 8–24 hr. Quantification figures are shown on the right. Data represent mean ± SEM of 3 independent experiments; *P < 0.05, **P < 0.01, ***P < 0.001. Full-length blots are presented in Supplementary Fig. S4.\n\nFigure 7: Figure 7. (A,B) Pearson’s R correlation coefficient between steady-state NEDD4 and PPARγ2 protein abundance in epididymal fat in 24 male HFD-fed wild-type (WT) and Nedd4+/− (Het) mice (WT: n = 12; Het: n = 12) or 28 aged (18–20 months) WT and Het mice (WT: n = 14, 12 males and 2 females; Het: n = 14, 12 males and 2 females). (C,D) Representative western blot image of NEDD4 and PPARγ expression in epididymal fat in HFD-fed or aged WT and Het mice. The HFD-fed mice at 6-week of age were fed a HFD (TD.06414, Teklad, Harlan Laboratories), containing 60% calories from fat, for 16 weeks. Samples were arranged in increasing order of NEDD4 expression. Full-length blots are presented in Supplementary Fig. S4."
      }
    ]
  },
  {
    "id": "PMC5250669_multi",
    "image": [
      "images/PMC5250669-f1.png",
      "images/PMC5250669-f2.png",
      "images/PMC5250669-f3.png",
      "images/PMC5250669-f4.png",
      "images/PMC5250669-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Tauroursodeoxycholic bile acid arrests axonal degeneration by inhibiting the unfolded protein response in X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a, b Induction of the UPR in CCALD and cAMN patient brains. Representative immunoblots for full-length ATF6, cleaved-ATF6, total PERK, phosphorylated PERK (P-PERK), eIF2α, phosphorylated-eIF2α (P-eIF2α), ATF4, CHOP, GADD34 and IRE1 levels in total lysates from controls (Ctrl) and in normal-appearing (NA) and affected (A) white matter from CCALD (a) and cAMN patients (b). XBP1 mRNA splicing analysis by RT-PCR in Ctrl samples and NA and A white matter from CCALD (c) and cAMN patients (d). Unspliced- and spliced-XBP1 mRNA corresponds to XBP1u mRNA and XBP1s mRNA, respectively. Representative immunoblots for GRP78, GRP94, and PDI levels in Ctrl samples and NA and A white matter from CCALD (e) and cAMN patients (f). Protein levels were normalized relative to γ-tubulin (γ-Tub). The histograms on the right (a, b) and below (e, f) show the ratio and the protein levels relative to control. All values are expressed as the mean ± SD (n = 5 by genotype and condition in a–f; *P < 0.05 and **P < 0. 01, one-way ANOVA followed by Tukey’s HSD post hoc test for a, b, e and f)\n\nFigure 2: Figure 2. UPR induction in the X-ALD mouse model. a Representative immunoblots of ER stress sensors full-length ATF6, cleaved-ATF6, total PERK, P-PERK, eIF2α, P-eIF2α, ATF4, CHOP, GADD34 and IRE1 in the spinal cord tissue of Abcd1 − mice and age-matched wild type (WT) mice at 3 and 12 months of age. The histograms on the right show the cleaved-ATF6, P-PERK, ATF4, CHOP, GADD34 and IRE1 levels normalized relative to γ-Tub and the P-PERK/PERK and the P-eIF2α/eIF2α ratios relative to their respective WT values. b The nuclear localization of cleaved-ATF6 in WT and Abcd1 − mice at 3 and 12 months of age. PARP1 was used as the control for the nuclear fraction (N) and aldolase A was used for the cytoplasmic fraction (C). The histograms on the right show the cleaved-ATF6 levels relative to WT values in the nuclear fractions. c Real-time RT-PCR analyses of Edem2 and Herpud1 mRNA at 12 months in Abcd1 − mouse spinal cords. d Immunoblots of GRP94 and GRP78 chaperones and PDI in the spinal cord tissue of Abcd1 − mice and age-matched wild type (WT) mice 3 and 12 months of age. The histograms on the right show the GRP94 and GRP78 chaperones and PDI levels normalized to WT mice and normalized relative to the γ-Tub. Values are expressed as the mean ± SD (n = 10 samples per genotype and condition in a, c and d; n = 6 samples per genotype and condition in b; *P < 0.05, **P < 0.01 and ***P < 0.001, Student’s t test)\n\nFigure 3: Figure 3. The UPR is primarily induced in motor neurons and astrocytes during X-ALD pathogenesis. a Immunofluorescence of GRP78 and PDI in spinal cord sections of WT and Abcd1 − mice 3 and 12 months of age. Arrows indicate high amounts of GRP78 and PDI in motor neurons; Arrowheads denote motor neurons with low amounts of GRP78. Nuclei were counterstained with DAPI. Scale bar 50 μm. b Dual immunolabelling of astrocytes (GFAP; green) with GRP78 or PDI (red) in spinal cord sections of WT and Abcd1 − mice 3 and 12 months of age. Positive cells are labelled with arrows, and the dashed-line stands for the limit between the grey- and white matter. Nuclei were counterstained with DAPI. The small panel below shows some double-positive astrocytes. Scale bar 25 μm. The histogram on the right represents the quantification of GRP78 and PDI fluorescence intensity normalized to WT mice in motor neurons (MNs) (a) and astrocytes (b). Values are expressed as the mean ± SD (n = 4 samples per genotype and condition in a and b; *P < 0.05, **P < 0.01 and ***P < 0.001, Student’s t test)\n\nFigure 4: Figure 4. Inhibition of PERK disrupts the UPR and renders the X-ALD fibroblasts more susceptible to ER stress. a Representative immunoblots for cleaved-ATF6, total PERK, P-PERK, total eIF2α, P-eIF2α, ATF4, CHOP, GADD34, GRP78, GRP94 and PDI levels in control (Ctrl) and X-ALD human fibroblasts pretreated with or without the PERK inhibitor GSK2606414 (GSK, 120 nM) for 1 h and then exposed to tunicamycin (TM, 2 µg/mL) for 48 h. Protein levels were normalized relative to γ-tubulin (γ-Tub). The histograms below show the cleaved-ATF6, P-PERK, P-eIF2α, ATF4, CHOP, GADD34, GRP94, GRP78 and PDI levels normalized relative to γ-Tub and the P-PERK/PERK and P-eIF2α/eIF2α ratios relative to their respective WT values. b Real-time RT-PCR analyses of Edem2 and Herpud1 mRNA levels in Ctrl and X-ALD human fibroblasts pretreated with or without the PERK inhibitor GSK2606414 (GSK; 120 nM) for 1 h and then exposed to tunicamycin (TM, 2 µg/mL) for 48 h. All values are expressed as the mean ± SD (n = 4 by genotype and condition; *P < 0.05 and **P < 0. 01, one-way ANOVA followed by Tukey’s HSD post hoc test)\n\nFigure 5: Figure 5. Antioxidant and TUDCA treatments prevent UPR activation in the X-ALD mouse model. a, d Representative immunoblots for full-length ATF6, cleaved-ATF6, total PERK, P-PERK, total eIF2α, P-eIF2α, ATF4 and CHOP in the spinal cord tissue of WT mice (WT), Abcd1 − mice (Abcd1 −) and a antioxidant-treated (Abcd1 − + AOX) or d TUDCA-treated (Abcd1 − + TUDCA) Abcd1 − mice at 12 months of age. GRP78, GRP94 and PDI levels were analysed in the spinal cords of WT, Abcd1 − and Abcd1 − + AOX mice (b) and Abcd1 − + TUDCA mice (e) at 12 months of age. Real-time RT-PCR analyses of Edem2 and Herpud1 in the spinal cord tissue of WT mice (WT), Abcd1 − mice (Abcd1 −) and c antioxidant-treated (Abcd1 − + AOX) or f TUDCA-treated (Abcd1 − + TUDCA) Abcd1 − mice at 12 months of age. In (a, b and d, e), the histograms on the right show normalized UPR marker levels relative to those in untreated WT mice. All values are expressed as the mean ± SD (n = 10 by genotype and condition in a–d; **P < 0.01 and ***P < 0.001, one-way ANOVA followed by Tukey’s HSD post hoc test)"
      }
    ]
  },
  {
    "id": "PMC5250669_multi_2",
    "image": [
      "images/PMC5250669-f6.png",
      "images/PMC5250669-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Tauroursodeoxycholic bile acid arrests axonal degeneration by inhibiting the unfolded protein response in X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a–q TUDCA halts axonal degeneration and locomotor disability in Abcd1 − /Abcd2 −/− mice. Immunohistological analysis of axonal pathologies performed on WT, Abcd1 − /Abcd2 −/− and TUDCA-treated Abcd1 − /Abcd2 −/− mice (Abcd1 − /Abcd2 −/− + TUDCA) of 18 months of age. Spinal cord immunohistological sections were processed for a–c Iba1, d–f GFAP, g–i synaptophysin, j–l APP and m–o Sudan black. Representative images for WT (a, d, g, j and m), Abcd1 − /Abcd2 −/− (b, e, h, k, and n), and Abcd1 − /Abcd2 −/− + TUDCA (c, f, i, l and o) mice are shown. Bars 25 µm. The quantification of synaptophysin (p) and APP (q) in 1-cm-long longitudinal sections of the dorsal spinal cord in WT, Abcd1 − /Abcd2 −/− and Abcd1 − /Abcd2 −/− + TUDCA mice at 18 m of age (n = 5 mice per genotype and condition). The number of abnormal specific profiles was counted at every ten sections for each stain. At least five sections of the spinal cord were analysed per animal and per stain. Clasping (r), treadmill (s) and bar cross (t) tests were conducted on WT, Abcd1 − /Abcd2 −/− and TUDCA-treated Abcd1 − /Abcd2 −/− mice (Abcd1 − /Abcd2 −/− + TUDCA) 17 months of age. r The best performance score of each animal was used for statistical analysis [19]. s The latency to falling from the belt (time of shocks), the number of shocks received and the ratio were computed after 5 min. t The time spent to cross the bar and the numbers of slips of the hind limbs were quantified. Values are expressed as the mean ± SD (n = 5 per condition in a–q; n = 15 per condition in r–t; *P < 0.05, **P < 0.01 and ***P < 0.001, one-way ANOVA followed by Tukey’s HSD post hoc test)\n\nFigure 7: Figure 7. Mechanisms of UPR activation in the spinal cord from an X-ALD mouse model. Representation of the ER stress response following excess VLCFA due to the lack of ABCD1 function in the X-ALD mouse model. Prior to disease onset (at 12 months), the PERK/P-eIF2α/ATF4 pathway is activated. It is central for translational control but also for the activation of ATF6 during ER stress, and as a consequence, is critical for the transcription of its target genes, including those involved in protein folding or the ERAD. Oxidative stress produced by excess VLCFA and possibly also ER membrane lipid perturbations induced by accumulation of these fatty acids could induce PERK activation independently of unfolded protein formation. This would constitute an adaptive mechanism, allowing the cell to engage ER folding and the ERAD machinery response. Both antioxidant and TUDCA treatments of X-ALD mice prevent ER stress activation and halt subsequent axonal neurodegeneration"
      }
    ]
  },
  {
    "id": "PMC5288653_multi",
    "image": [
      "images/PMC5288653-f1.png",
      "images/PMC5288653-f2.png",
      "images/PMC5288653-f3.png",
      "images/PMC5288653-f4.png",
      "images/PMC5288653-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 ligase Mule protects the heart against oxidative stress and mitochondrial dysfunction through Myc-dependent inactivation of Pgc-1α and Pink1\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Down-regulation of Mule mRNA levels in human end-stage heart failure determined by RT- qPCR. (B) To specifically inactivate Mule and Myc in the adult heart, we employed a tamoxifen (Tam) inducible Cre-loxP system in which Cre recombinase expression is controlled by the cardiomyocyte-specific myosin heavy chain 6 promoter (mcm). 4-hydroxytamoxifen (Tam) was injected intraperitoneally daily for four consecutive days in 10 week-old mice. The day of the last Tam injection was set as day zero. Veh, vehicle. Nt, no treatment. Immunoblot analysis of cytoplasmic Mule and nuclear Myc levels in left ventricular extracts (60 μg total protein/lane) of Mulefl/fl(y);mcm mice at 7 days post-Tam employing specific antibodies as indicated on the left. Animals were 12 weeks old at the time of analysis. For normalization, Western blots were probed with anti-tubulin (Tub) for cytoplasmic fractions, and anti-nucleophosmin (Npm1) for nuclear fractions. Immunoblots were repeated at least once with similar results. Transcript levels of Mule and Myc in Mulefl/fl(y);mcm mice at 7 d post-Tam as analyzed by RT-qPCR. n = 4. (C) Mule is indispensable for Myc protein stability in the heart by regulation of its ubiquitin-mediated proteasomal degradation. At 7 d post-Tam. Mulefl/fl(y);mcm, mice were intraperitoneally injected with the proteasomal inhibitor MG132 or vehicle for 6 hours. LV lysates were immunoprecipitated (IP) with anti-Myc antibodies or normal rabbit IgG. Ubiquitinated Myc proteins in the immunoprecipitates were identified by immunoblotting with antibodies to ubiquitin. IgG, immunoglobulin G. IP, immunoprecipitation. Ubi, ubiquitin. WB, Western blot. One representative result of three independent experiments is depicted. Data are means ± s.e.m.\n\nFigure 2: Figure 2. (A) Representative masson staining of longitudinal cardiac sections of the indicated mice at 4 weeks post-Tam. (B) Heart-weight corrected for body weight of the indicated strains at 4 weeks post-Tam. Animals were 15 weeks old at the time of analysis. n = 28. (C) Heart-weight corrected for tibia length at 4 weeks post-Tam. n = 28. (D) Quantification of cross-sectional area of adult cardiomyocytes at 4 weeks post-Tam. n = 12. (E) Immunofluorescence microscopy of wheat germ agglutinin (WGA; green) stained formalin-fixed LV sections at 4 weeks post-Tam. (F) Fractional shortening (FS) determined by M-mode echocardiography at 4 weeks post-Tam. n = 4. (G) Expression levels of hypertrophic and sarcomeric marker genes atrial natriuretic factor (ANP), brain natriuretic factor (BNP), α-myosin heavy chain (β-MHC), β-myosin heavy chain (β-MHC), troponin C (Tnnc1), troponin T (Tnnt1), α-actin (Acta1/2) and α-actinin (Actn1/4) as analyzed by RT-qPCR at 4 weeks post-Tam. n = 4. *P < 0.05 versus −Tam. #P < 0.01 versus −Tam. (H) Acute genetic ablation of Mule evokes premature death. Kaplan-Meier survival curves of conditional Mulefl/fl(y);mcm mice. (I) Representative masson staining of longitudinal cardiac sections from Mulefl/fl(y);mcm mice at 3 months post-Tam. (J) Heart-weight corrected for body weight of Mulefl/fl(y);mcm mice at 3 months post-Tam. n = 14. (K) Lung-weight corrected for tibia length of Mulefl/fl(y);mcm mice at the indicated time points post-Tam. n = 14. (L) Fractional shortening (FS) determined by M-mode echocardiography of Mulefl/fl(y);mcm mice at 3 months post-Tam. n = 4. Data are means ± s.e.m.\n\nFigure 3: Figure 3. (A) Analysis of cardiac fibrosis by immunofluorescence microscopy employing wheat germ agglutinin (WGA) staining (green) of collagen deposition in the extracellular matrix, cardiomyocyte-specific anti-actinin (red), and Dapi (blue) to visualize nuclear DNA. (B) Quantification of extracellular matrix area indicative of LV fibrosis shown in (B). n = 4. (C) Acute genetic ablation of Mule triggers cardiomyocyte apoptosis which is abrogated by co- deletion of Mule and Myc in DKO mice. n = 4. (D) Analysis of apoptosis in LV cardiomyocytes (white arrows) by immunofluorescence microscopy and TUNEL assays. Hearts were harvested at 8 d post-Tam. Mice were 12 weeks old at the time of analysis. Red, cardiomyocyte-specific nuclear marker, anti-Mef2a. Green, TUNEL. Blue, DAPI stain of nuclear genomic DNA. TUNEL, terminal deoxynucleotidyl transferase- mediated dUTP nick-end-labeling. (E) BrdU, an indicator for DNA synthesis was injected intraperitoneally at 7 d post-Tam. Animals were sacrificed 18 hours later. Quantitative analysis of cardiomyocytes in S phase was performed by immunofluorescence microscopy of LV cardiac sections employing anti-BrdU (green) and anti-Mef2a (red) antibodies. White arrows denote BrdU-positive and Mef2a-negative non-cardiomyocytes. Blue, nuclei). BrdU, 5-Bromo-2′-deoxyuridine. (F) Genetic ablation of Mule fails to induce cell cycle entry and DNA synthesis in adult cardiomyocytes. n = 4. Data are means ± s.e.m.\n\nFigure 4: Figure 4. Microarray-based genome-wide transcriptional profiling of LV tissue samples derived from Mulefl/fl(y);mcm mice at 4 weeks post-Tam. Animals were 15 weeks old at the time of analysis. Depicted are differentially expressed genes that were significantly enriched for a cellular metabolic gene signature in the Mule-deficient mice (column) post-Tam relative to vehicle- injected controls. Heatmap values (log2 fold expression) of this metabolic gene set are shown by color and intensity of shading. Important factors of cardiac energy metabolism and detoxification of oxygen radicals are indicated on the right. Blue, repressed. Red, induced. n = 3 biological replicates. P < 0.01. Fold change >2.0. (A) Expression levels of key genes selected from (A), involved in the regulation of branched chain amino acid metabolism, glutamine metabolism and ROS defence as analyzed by RT-qPCR at 4 weeks post-Tam. n = 4. *P < 0.05 versus −Tam. #P < 0.01 versus vehicle. (B) Expression levels of differentially enriched genes from (A), involved in the regulation of glycolysis, mitochondrial oxidative phosphorylation (OxPhos), fatty acid synthesis (FAS) and fatty acid oxidation (FAO) as analyzed by RT-qPCR at 4 weeks post-Tam. n = 4. (D,E) Time course of transcript levels of selected factors (C) participating in the regulation of important biological processes in Mulefl/fl(y);mcm mice was analyzed by RT-qPCR. n = 4. #P < 0.01 versus vehicle. (F) Endogenous Myc interacts with gene promoter sequences of Pgc-1α, Atp5a, Gstm1 and Pink1 in situ. One representative result of three independent experiments is shown. (G) Myc does not bind to the promoters of Hk2, Got1 and Bckdhb. LV tissue obtained from Mulefl/fl(y);mcm mice at 7 d post-Tam was analyzed by ChIP employing anti-Myc antibodies and PCR primers specific to the selected gene promoters. Normal rabbit IgG were used for control immunoprecipitations. Input lanes of chromatin levels used for the immunoprecipitation step demonstrate equal loading. One representative result of three independent experiments is shown. Data are means ± s.e.m.\n\nFigure 5: Figure 5. (A) Immunoblot analysis of master transcription factors regulating FAS and FAO in left ventricular extracts of Mulefl/fl(y);mcm and DKO mice at 7 days post-Tam. Numbers below the individual blots indicate fold-changes in protein expression. (B) Endogenous Myc interacts with gene promoter sequences of Esrrβ, but is not associated with the promoters of Pparα and Pparγ as analyzed by ChIP. Esrrβ, estrogen related receptor, beta. (C) Transcript expression of key factors regulating FAS/FAO, redox homeostasis and mt biogenesis in left ventricular samples of Mulefl/fl(y);mcm mice was determined by RT-qPCR at 4 weeks post-Tam. n = 4. *P < 0.05 versus vehicle. (D) ATP levels in left ventricular tissue extracts from Mulefl/fl(y);mcm mice at 7 d post-Tam. n = 4. (E) Immunoblot analysis of important constituents of the mt electron transport chain participating in oxidative phosphorylation in LV extracts of Mulefl/fl(y);mcm versus DKO mice at 7 days post-Tam. Equal loading of bands was confirmed by reprobing membranes with mt- specific anti-Opa1 antibodies. (F) Myc interacts with gene promoter sequences of OxPhos components of Ndufa4 (CI, complex 1) and Cox10 (CIV, complex 4) as analyzed by ChIP from isolated LV genomic DNA from Mulefl/fl(y);mcm mice at 7 d post-Tam. (G) Mt biogenesis, defined as relative DNA copy number of mt encoded Cytb gene normalized to the copy number of the nuclear gene Npm1, was determined by qPCR of isolated LV mt from Mulefl/fl(y);mcm and DKO mice at 7 d post-Tam. n = 4. (H) Mt capacity, defined as relative mRNA levels of the nuclear gene Ndufa8, a subunit of OxPhos complex I, normalized to Npm1 transcript expression, was determined by RT-qPCR of total RNA isolated from left ventricular tissue of the indicated wild type (−Tam) and mutant strains (+Tam). n = 4. (I) Activity of OxPhos complex I in Mulefl/fl(y);mcm and DKO mice at 7 d post-Tam. n = 4. *P < 0.01 versus vehicle. (J) Activity of OxPhos complex IV in Mulefl/fl(y);mcm mice or DKO animals at 7 d post-Tam. n = 4. *P < 0.05 versus vehicle. Data are means ± s.e.m."
      }
    ]
  },
  {
    "id": "PMC5302033_multi",
    "image": [
      "images/PMC5302033-f1.png",
      "images/PMC5302033-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"PINK1, Parkin, and Mitochondrial Quality Control: What can we Learn about Parkinson’s Disease Pathobiology?\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PINK1 and Parkin domain structures and PD-related mutations. (A-B) Given are schematic, color-coded domain representations of PINK1 and Parkin. PD-associated missense and nonsense mutations from the PD Mutation Database (http://www.molgen.vib-ua.be/PDMutDB/) are displayed on top of each structure with their respective locations. Mutations in red have been experimentally verified as loss-of-function mutations and are considered pathogenic, while functional defects for variants shown in black remain unclear. Underlined mutations are common variants based on the ExAC database (http://exac.broadinstitute.org) with allele frequencies greater than 1:10 000. (A) Domain structure of PINK1 (581 amino acids): mitochondrial targeting sequence (MTS, orange), transmembrane region (TM, red), N-terminal regulatory region (NT, gray), N-lobe of the kinase domain (cyan), C-lobe of the kinase domain (purple) and the C-terminal domain (CTD, blue). PD-associated mutations are listed on the top. Mitochondrial protease (MPP and PARL) cleavage sites and PINK1 auto-phosphorylation sites are displayed at the bottom. (B) Domain structure of Parkin (465 amino acids): ubiquitin-like domain (UBL, red), linker (gray), really-interesting-new-gene (RING)/unique Parkin domain (R0/UPD, green), RING1 (R1, cyan), in-between-RING (IBR, purple), repressor element of Parkin (REP, yellow), and RING2 (R2, pink). E2 co-enzyme and p-Ser65-Ub binding sites as well as Ser65 phosphorylation and Cys431 catalytic sites are displayed at the bottom. (C) Closed, inactive conformation of full-length human Parkin (left: front view and right: back view). The structure is shown in colored ribbons that correspond to the respective domain colors. The solvent-accessible surface area of each domain is shown in semi-transparent rendering in the same color. Ser65 is highlighted in Van der Waal representation with standard atom coloring (hydrogen: white, oxygen: red, nitrogen: blue). The zinc-finger motifs of Parkin are rendered in licorice stick with standard atom coloring and the corresponding zinc ions as spheres (cyan).\n\nFigure 2: Figure 2. PINK1/Parkin-directed mitochondria quality control. Shown is a cartoon of the PINK1/Parkin pathway(s). (A) In healthy mitochondria, PINK1 is imported and it undergoes cleavage by the mitochondrial proteases MPP and PARL. N-terminally cleaved PINK1 is then subsequently degraded by the Ub/proteasome system. Parkin remains inactive in the cytosol. (B) Upon mitochondrial damage, PINK1 is no longer imported, but accumulates on the outer mitochondrial membrane (OMM) to activate Parkin. PINK1-mediated phosphorylation of Ub and Parkin enable its E3 Ub ligase functions in concert with E2 Ub-conjugating enzymes. p-Ser65-Ub on OMM substrates acts as the Parkin receptor for its recruitment from the cytosol. Together, PINK1 and Parkin then engage a feed-forward loop amplification. Formed poly-Ub chains can be cleaved by DUBs to reverse PINK1/Parkin functions. (C) Individual OMM proteins decorated with poly-Ub can be extracted from the membrane and degraded by the 26 S proteasome (mitochondria-associated degradation; MAD). Greater, but localized mitochondrial damage is sequestered by the formation of mitochondria-derived vesicles (MDV). Severely damaged mitochondria are decorated with high levels of p-Ser65-Ub that serves as the mitophagy tag for autophagy receptors that direct their degradation in lysosomes."
      }
    ]
  },
  {
    "id": "PMC5341075_multi",
    "image": [
      "images/PMC5341075-f1.png",
      "images/PMC5341075-f2.png",
      "images/PMC5341075-f3.png",
      "images/PMC5341075-f4.png",
      "images/PMC5341075-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogen biosynthesis is spatiotemporally regulated by sensing plasmalogens in the inner leaflet of plasma membranes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. CHO-K1 (A) and HeLa (B) cells were cultured in the presence (+) or absence (−) of CHX for the indicated time. Expression level of Far1 at each time point in the absence (diamond) or presence (square) of CHX was assessed. Peroxisomal membrane protein Pex3p and β–actin for a loading control were detected with respective specific antibodies (left panels). Molecular masses were indicated on the right, using the migration of standard mass markers. Relative amounts of Far1 at each time point were represented by taking as 100 those at the time point of CHX addition in respective cells (right panels). *p < 0.05, **p < 0.01; Student’s t test compared with the expression level of Far1 at each time point in the absence of CHX. Data of unprocessed original blots are available in Supplementary Fig. S2.\n\nFigure 2: Figure 2. (A) CHO-K1 cells were incubated with DMSO, Dynasore, or CPZ for 30 min and further metabolically labelled with 14C-Etn for 5 h in the absence (−) and presence of each inhibitor. The biosynthesis of PE and plasmalogen (2-acyl-GPE) were detected with a FLA-5000 imaging analyser (upper panel). Total cellular level of phospholipids including PE, PS, phosphatidylinositol (PI), plasmalogens, phosphatidylcholine (PC), and SM were detected with iodine vapor (lower panel). Note that biosynthesis of plasmalogens was specifically reduced in the presence of Dynasore. (B) Biosynthesis of PE (open bar), plasmalogens (dark grey bar), PE plus plasmalogens (light grey bar) was represented by taking the amounts of PE plus plasmalogens as 100 in mock-treated (−) CHO-K1. Statistical analysis was performed by one-way ANOVA with Dunnett’s post hoc test as compared with the synthesis of respective lipids in mock-treated cells. *p < 0.05, **p < 0.01, and ***p < 0.001.\n\nFigure 3: Figure 3. (A) CHO-K1 cells were cultured for 5 h in the presence (+) of CHX (lane 1), Dynasore (lane 3), or CHX plus Dynasore (lane 4) and were assessed for the expression level of Far1 (upper panel). β–actin was used as a loading control. Relative expression levels of Far1 were represented by taking those as 100 in mock-treated cells (lane 2, lower panel). Note that Far1 expression was reduced in the presence of Dynasore in CHO-K1 cells (lane 3). **p < 0.01 and ***p < 0.001; two-way ANOVA with Tukey-Kramer post hoc test. (B) agps ZPEG251 was cultured for 5 h in the presence (+) or absence (−) of Dynasore and were assessed for the expression level of Far1 (upper panel). Relative expression levels of Far1 were represented by taking those as 100 in mock-treated cell (lower panel). n.s., not significant; t test. (C) Expression level of FAR1 relative to β–Actin was determined by real-time PCR using total RNA, and represented by taking as 100 that in CHO-K1 (−). n.s., not significant; t test. (D) Total cellular plasmalogens were analysed by LC-ESI-MS/MS and represented by taking that as 100 in CHO-K1 (−). n.s., not significant; t test. (E) Lipids were extracted from cells cultured in the absence (−) or presence (+) of Dynasore and assessed by TLC (upper panel) as described in Materials and Methods. Cholesterol was detected with iodine vapor and quantified (lower panel) using an image analysis software (Multi Gauge). n.s., not significant; t test. (F) CHO-K1 cells were cultured for 5 h in the presence (+) or absence (−) of MiTMAB and assessed for the expression level of Far1 (upper panel). Relative expression levels of Far1 were represented by taking those as 100 in mock-treated cells (lower panel). **p < 0.01; t test. Data of unprocessed original blots are available in Supplementary Fig. S2.\n\nFigure 4: Figure 4. (A) agps ZPEG251 was cultured in the presence (lanes 2–4) or absence (lanes 1 and 5) of purified plasmalogens (puri. Pls) for 6 h, and further cultured in the presence of Dynasore (lane 3) or PP2 (lanes 4 and 5) for 5 h. Expression levels of Far1 were assessed by immunoblotting (upper panel) and represented (lower panel) by taking as 100 that in ZPEG251 (lane 1). ###p < 0.001; one-way ANOVA with Dunnett’s post hoc test as compared with mock-treated cells. n.s., not significant. *p < 0.05 and **p < 0.01; one-way ANOVA with Dunnett’s post hoc test as compared with ZPEG251 treated with purified plasmalogens (lane 2). (B) Cellular plasmalogens were analysed by LC-ESI-MS/MS and represented by taking as 100 that in ZPEG251 cultured in the presence of purified plasmalogens (lane 2). **p < 0.01 and ***p < 0.001; one-way ANOVA with Tukey post hoc test as compared with ZPEG251. n.s., not significant. Data of unprocessed original blots are available in Supplementary Fig. S2.\n\nFigure 5: Figure 5. (A) Expression levels of Far1 and Flot1 were assessed in HeLa cells transfected with control dsRNA (lane 1) or two different dsRNAs (lanes 3 and 4) against FLOT1. Expression level of Far1 was represented by taking as 100 that in mock-treated cell (lower panel). (B) Plasmalogen synthesis was assessed in mock-treated (−) or FLOT1-knocked down (#68 and #69) HeLa cells by metabolically labelling with 14C-Etn for 2 h (upper panel). Biosynthesis of plasmalogens was represented by taking as 100 that in mock-treated cells (lower panel). *p < 0.05, **p < 0.01, and ***p < 0.001; one-way ANOVA with Dunnett’s post hoc test as compared with mock-treated cells. (C) Left panel, total cellular level of plasmalogens was represented by taking as 100 that in mock-treated cells. Right panel, expression level of FAR1 relative to ribosomal protein 3 (RPL3)63 was determined by real-time PCR using total RNA, and represented by taking as 100 that in HeLa cells (−). n.s., not significant; one-way ANOVA with Dunnett’s post hoc test as compared with mock-treated cells. Data of unprocessed original blots are available in Supplementary Fig. S2."
      }
    ]
  },
  {
    "id": "PMC5341075_multi_2",
    "image": [
      "images/PMC5341075-f6.png",
      "images/PMC5341075-f7.png",
      "images/PMC5341075-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogen biosynthesis is spatiotemporally regulated by sensing plasmalogens in the inner leaflet of plasma membranes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Expression levels of Far1 (solid bar) and Cav1 (open bar) were assessed in HeLa cells transfected with dsRNAs against CAV1. β–actin was used as a loading control. Expression level of Far1 was represented by taking as 100 that in mock-treated cell (right panel). **p < 0.01; t test versus mock-treated cells. n.s., not significant. (B) HeLa and HepG2 were cultured in the presence of Etn (5 μM) for 48 h and assessed for expression level of Far1, β–actin, Pex3p, Cav1, and Flo1. Note that Cav1 is not expressed in HepG2 cells35. Cellular plasmalogens were analysed by LC-ESI-MS/MS and represented by taking those as 100 in mock-treated respective cells. **p < 0.01; t test versus mock-treated respective cells. (C) Expression level of Far1 was represented by taking those as 100 in mock-treated respective cells. **p < 0.01; t test versus mock-treated respective cells. Data of unprocessed original blots are available in Supplementary Fig. S2.\n\nFigure 7: Figure 7. (A) HeLa cells were transfected with two different dsRNAs (lanes 2 and 3) against FLOT1 and expression of Flot1 was assessed. (B) DRMs (R) and detergent-soluble (S) fractions were prepared as described in Materials and Methods and distribution of Cav1 and Tfr was assessed using respective antibodies. (C,D) Amount of SM (C) and plasmalogens (D) in DRMs prepared as in (B) was determined by LC-ESI-MS/MS and represented by arbitrary units. *p < 0.05; one-way ANOVA with Dunnett’s post hoc test versus mock-treated HeLa cells. n.s., not significant. (E) CHO-K1 cells were cultured for 1 h with nystatin (Nys.), a cholesterol-chelating agent, further incubated for the indicated time in the presence of CHX, and assessed for the expression of Far1 at each time point (upper panel). β–actin was used as a loading control. Relative amounts of Far1 in the presence (triangle) of nystatin at each time point were represented by taking as 100 that at the time point of CHX addition. The relative expression level of Far1 in the absence (square) of nystatin was from Fig. 1A (left panels). **p < 0.01; t test compared with the expression level of Far1 at 9 h in the absence of nystatin. (F) Cellular plasmalogens in CHO-K1 cells cultured in the absence (−Nys.) or presence (+Nys.) of nystatin were analysed by LC-ESI-MS/MS and their relative level was represented by taking as 100 that at (0 h, -Nys.). n.s., not significant by two-way ANOVA. (G) Lipids were extracted from cells cultured as in (F). Cholesterol was detected as described in Fig. 3E. Relative amount of cholesterol is represented by taking as 100 that at (0 h, -Nys.). *p < 0.05 and **p < 0.01; two-way ANOVA with Tukey post hoc test. n.s., not significant. Note that cellular cholesterol was reduced by the treatment of CHX but not with nystatin.\n\nFigure 8: Figure 8. (A) Expression level of Far1 was assessed in mock-treated HeLa cells (−) or cells transfected with control dsRNA (C) or two different dsRNAs (#22 and #23) against CDC50A (upper panel). β–actin was used as a loading control. Expression level of Far1 was represented by taking as 100 that in mock-treated cell (lower panel). *p < 0.05 and **p < 0.01; one-way ANOVA with Dunnett’s post hoc test versus mock-treated cells. (B) HeLa cells were cultured as described in (A). Expression level of CDC50A relative to RPL363 was determined by real-time PCR using total cell RNA. ***p < 0.001; one-way ANOVA with Dunnett’s post hoc test versus mock-transfected cells (−). (C) HeLa cells were cultured in the presence of 14C-Etn for 18 h and further incubated with (+) or without (−) TNBS. Total cellular lipids were extracted from aliquots of equal amounts of cell proteins before (−) or after (+) treatment with TCA and analysed by TLC. (D) PE and plasmalogens localised at the outer leaflet of plasma membrane were verified as in (C) in mock-transfected HeLa cells (−) or CDC50A-knocked down cells by transfection with dsRNA (#22) (left panel). Relative amounts of TNBS-modified PE (TNBS-PE, open bar) and plasmalogens (TNBS-2-acyl-GPE, solid bar) were represented by taking as 100 those in mock-transfected cells (right panel). *p < 0.05 and **p < 0.01; t test versus mock-transfected cells. (E) Plasmalogen synthesis was assessed in mock-transfected (−) or CDC50A-knocked down (#22) HeLa cells by metabolically labelling with 14C-Etn for 5 h (left panel). Biosynthesis of PE (open bar) and plasmalogens (solid bar) was represented by taking as 100 those in mock-transfected cells (right panel). *p < 0.05 and **p < 0.01; t test versus mock-transfected cells. (F) Relative level of PE (open bar) and plasmalogens (solid bar) in CDC50A-knocked down (#22) HeLa cells was represented by taking as 100 those in mock-transfected cells. n.s., not significant; t test versus mock-transfected cells. Data of unprocessed original blots are available in Supplementary Fig. S2."
      }
    ]
  },
  {
    "id": "PMC5380948_multi",
    "image": [
      "images/PMC5380948-f1.png",
      "images/PMC5380948-f2.png",
      "images/PMC5380948-f3.png",
      "images/PMC5380948-f4.png",
      "images/PMC5380948-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MKRN2 is a novel ubiquitin E3 ligase for the p65 subunit of NF-κB and negatively regulates inflammatory responses\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (a) Schematic diagram of the structure of mouse MKRN2. Black boxes: C3H-type zinc finger domain (C3H), striped box: unique Cys-His motif (Cys-His), gray box: RING finger domain (RING). (b) Western blot analysis of MKRN2 expression in primary immune cells and MEFs. Whole cell lysates were subjected to immunoblot (IB) with anti-MKRN2 and HSP90 antibodies. MEF: mouse embryonic fibroblasts. Western blots are representative of at least three independent experiments. (c) Subcellular localization of MKRN2 protein. Splenic CD11c+ cells, MEF, NIH3T3, HeLa and RAW264.7 cells were fractionated into cytoplasmic (C) and nuclear (N) fractions, which were then analyzed by Western blotting with the MKRN2 antibody. The purity of the fractionations was confirmed by cdc37 (cytoplasm) or LSD1 (nucleus) antibody reactivity. Western blots are representative of at least three independent experiments. (d) MKRN2 interacts with PDLIM2 through LIM domain of PDLIM2. 293 T cells were transfected with His-tagged PDLIM2 or the PDLIM2 mutant lacking the LIM domain (∆LIM) along with or without c-Myc-tagged MKRN2. Whole cell extracts were immunoprecipitated with a c-Myc antibody, and immunoblotted with anti-His. Western blots are representative of at least three independent experiments.\n\nFigure 2: Figure 2. (a) Luciferase activity in NIH3T3 cells transfected with an ELAM-1 luciferase reporter construct (ELAM-1-luc) along with or without a plasmid encoding MKRN2, then left untreated or treated with LPS for 5 hr. Data are representative of at least three independent experiments. (b) Luciferase activity in NIH3T3 cells transfected with an ELAM-1-luc with or without plasmids encoding p65 in the absence or presence of increasing amounts (wedge) of MKRN2. Data are representative of at least three independent experiments and are shown as mean ± SD. **P < 0.01. (c) Luciferase activity in NIH3T3 cells first transfected with control or MKRN2-specific siRNA and then with an ELAM-1 luc without or with the plasmid encoding p65. Data are representative of at least three independent experiments and are shown as mean ± SD. *P < 0.05. (d) MKRN2 interacts with the p65 subunit of NF-κB. 293 T cells were transfected with a FLAG-tagged-p65 expression plasmid along with or without MKRN2. Whole cell extracts were immunoprecipitated with anti-c-Myc, and immunoblotted with anti-Flag. Western blots are representative of at least three independent experiments. (e) Colocalization of MKRN2 with p65 in the nucleus. HeLa cells were transfected with expression plasmids encoding p65 fused with EGFP and c-Myc-tagged MKRN2, then analyzed by fluorescence imaging with EGFP (left) or indirect immunofluorescence imaging with the Myc primary antibody and Alexa Fluor 647-conjugated goat anti-mouse IgG1 (middle). Bar: 10 μm. Inset images are close-ups of the dotted square area. Bar: 5 μm.\n\nFigure 3: Figure 3. (a) Ubiquitination assay for p65 in 293 T cells cotransfected with plasmids encoding His-tagged ubiquitin (His-Ub), FLAG-tagged p65 and increasing amount of MKRN2. His-tagged proteins were purified by Ni-Sepharose beads. Polyubiquitination of p65 was analyzed by anti-p65. (b) Effect of MKRN2 on soluble and insoluble nuclear p65 in NIH3T3 cells transfected with plasmids encoding FLAG-tagged p65 and increasing amounts of c-Myc-tagged MKRN2. Cells were subjected to fractionation and analyzed by anti-FLAG antibody. The purity of the fractionations was confirmed by anti-LSD1 (nuclear soluble) or anti-Histone H3 (nuclear insoluble) antibody staining. (c) Western blot analysis for soluble and insoluble nuclear p65 in NIH3T3 cells transfected with plasmids encoding p65 without or with MKRN2, then left untreated or treated for 4 h with MG132 (10 µM) and analyzed as in (b). (d) Schematic diagram of the structure of the MKRN2 mutant lacking the RING finger domain (∆RING). Bottom shows Western blot analysis of NIH3T3 cells transfected with expression plasmids encoding wild-type or ∆RING MKRN2, detected with anti-c-Myc antibody. (e) Ubiquitination assay for p65 in 293 T cells cotransfected with plasmids encoding His-tagged ubiquitin (His-Ub), and p65, together without or with wild-type or ∆RING MKRN2 and analyzed as in (a). (f) Effect of ∆RING MKRN2 on soluble and insoluble nuclear p65 in NIH3T3 cells transfected with plasmids encoding p65, together without or with wild-type or ∆RING MKRN2 and analyzed as in (b).\n\nFigure 4: Figure 4. (a) Effect of MKRN2 deficiency on soluble and insoluble nuclear p65 in NIH3T3 cells first transfected with control siRNA or MKRN2-specific siRNA, then transfected with plasmids encoding FLAG-p65 or c-Myc-PDLIM2 and analyzed by anti-FLAG antibody. (b) Effect of MKRN2 deficiency on ubiquitination of p65 in 293 T cells cotransfected with plasmids encoding His-tagged ubiquitin, p65 and PDLIM2, in the absence or presence of siRNA specific for MKRN2 and analyzed as in Fig. 3a. (c) Synergic effect of MKRN2 and PDLIM2 on soluble and insoluble nuclear p65 in NIH3T3 cells transfected with plasmids encoding p65, MKRN2 or PDLIM2 in the indicated combination and analyzed by anti-FLAG antibody. (d) Ubiquitination assay for p65 in 293 T cells cotransfected with plasmids encoding His-tagged ubiquitin, p65, MKRN2 or PDLIM2 in the indicated combinations and analyzed as in Fig. 3a.\n\nFigure 5: Figure 5. (a) Reduction of MKRN2 protein amount in bone marrow-derived dendritic cells, transfected with siRNA specific for MKRN2, analyzed by immunoblot with anti-MKRN2. Data are representative of three independent experiments. (b) Western blot analysis for cytoplasmic and soluble and insoluble nuclear p65 in bone marrow-derived dendritic cells transfected with control or MKRN2-specific siRNA, then left unstimulated or stimulated with the indicated concentration of LPS for 1 h and analyzed by antibodies against the indicated targets. The purity of the fractionations was confirmed by anti-cdc37 (cytoplasm), anti-LSD1 (nuclear soluble) or anti-Lamine B (nuclear insoluble) antibody staining. Western blots are representative of three independent experiments. (c) Real-time RT-PCR analysis of LPS-inducible gene expression in bone marrow-derived dendritic cells transfected with control or MKRN2-specific siRNA, then left unstimulated or stimulated with the indicated concentration of LPS for 5 h. (d) Real-time RT-PCR analysis of p65 gene expression in bone marrow-derived dendritic cells transfected with control or MKRN2-specific siRNA, then left unstimulated or stimulated with the indicated concentration of LPS for 5 h. (e) Western blot analysis for cytoplasmic and soluble and insoluble nuclear p65 in NIH3T3 cells transfected with control or MKRN2-specific siRNA, then left unstimulated or stimulated with LPS (10 ng/ml) for 1 h and analyzed by antibodies against the indicated targets. The purity of the fractionations was confirmed by anti-cdc37 (cytoplasm), anti-LSD1 (nuclear soluble) or anti-Histone H3 (nuclear insoluble) antibody staining. Western blots are representative of three independent experiments."
      }
    ]
  },
  {
    "id": "PMC5384423_multi",
    "image": [
      "images/PMC5384423-f1.png",
      "images/PMC5384423-f2.png",
      "images/PMC5384423-f3.png",
      "images/PMC5384423-f4.png",
      "images/PMC5384423-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A de novo missense mutation of GABRB2 causes early myoclonic encephalopathy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. EEG showing proband. Monopolar EEG. Red bar: Eye jerk. (A) Suppression-burst (SB) pattern during sleep at the age of 2 months. (B) SB pattern during sleep at the age of 1 year and 11 months.\n\nFigure 2: Figure 2. Pedigree and GABRB2 mutations are shown. (A) Pedigree and their genotypes. Arrow with ‘P’ indicates the proband of this family. Square, circle and black symbols indicate male, female and affected individual(s). Mutation (RefSeq accession number NM_021911: c.859A>C) was found only in the proband. (B) Chromatogram showing PCR-Sanger sequencing. Arrow indicates a C-to-A substitution. A missense mutation was found only in the proband of this family. (C) Interspecies conservation of the amino acid Thr287 is shown. Red indicates the amino acid at position 287. EME, early myoclonic encephalopathy.\n\nFigure 3: Figure 3. p.Thr287Pro mutation in the β2 subunit and γ-aminobutyric acid-A (GABAA) receptor is shown. (A) Cartoon representation of the location of the p.Thr287Pro mutation of β2 subunit of the GABAA receptor. (B) Three-dimensional structural model of the GABAA receptor that is composed predominantly of two α1 (blue ribbons), two β2 (red ribbons) and one γ2 (grey ribbon) subunits in the mammalian central nervous system. β2 subunits have four transmembrane domains (TM1 to TM4). The GABRB2 de novo p.Thr287Pro mutation is mapped onto the β2 subunit in black at the second transmembrane domain (TM2). (C) Extracellular view of the transmembrane domain in a structural model of pentameric αβγ GABAA receptor (The N-terminal domain was removed for clarity) displaying the GABRB2 mutations (in black) on β (red ribbons) subunits. TM2 domains of five subunits form the Cl− ion pore (dashed black circle) and the p.Thr287Pro mutations are within the pore region.\n\nFigure 4: Figure 4. Reduced expression and cell surface levels of mutant β2 (p.Thr287Pro) (mut) subunit. (A, B). HEK293T cells were co-transfected with α1 and γ2 subunits and wild-type β2 (wt, 1:1:1 cDNA ratio of α1: β2: γ2), mixed wt β2 and the mut subunits (mixed, 1:0.5:0.5:1 cDNA ratio of α1: β2: β2(Thr287Pro):γ2) or the mut (1:1:1 cDNA ratio of α1: β2(Thr287Pro): γ2) subunits. (A) Total lysates were analysed by sodium dodecyl sulfate polyacrylamide gel electrophoresis and western blot. The membranes were blotted with rabbit anti-β2 subunit antibody. (B) The total β2 subunit protein integrated density values (IDVs) were normalised to the wt β2 subunit in wt receptors. (C) The flow cytometry histograms depict surface expression levels of β2 subunits from HEK293T cells expressing wt, mixed or the mut α1β2γ2 receptors. Cell surface wt and mut subunits were stained with monoclonal anti-β2/β3 (BD17) antibody that was fluorescently conjugated with Alexa Fluor-647). (D) The relative fluorescence intensity of β2 subunit signals of the mut subunits were normalised to those obtained with wt β2 subunits in the wt receptors (in (B) and (D), **p<0.05, **p<0.01, ***p<0.001 vs wt). p Values were obtained by unpaired t-test.\n\nFigure 5: Figure 5. Mutant β2 (p.Thr287Pro) subunits and their wild-type partner subunits were retained intracellularly. HEK293T cells expressing the α1 and γ2S subunits with the wild-type β2 or the mutant β2(p.Thr287Pro) subunits (1:1:1 cDNA ratio) were immunostained for anti-β2/3 subunits alone (A) or in combination with rabbit anti-γ2 subunits (B). The anti-β2/3 subunits were visualised with rhodamine-conjugated IgG, while the γ2 subunits were visualised with Alexa488-conjugated IgG. The images were acquired using a confocal microscope with a 63× objective based on our previous protocol.17"
      }
    ]
  },
  {
    "id": "PMC5386292_multi",
    "image": [
      "images/PMC5386292-f1.png",
      "images/PMC5386292-f2.png",
      "images/PMC5386292-f3.png",
      "images/PMC5386292-f4.png",
      "images/PMC5386292-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Hypoxia-inducible factor-2α stabilizes the von Hippel-Lindau (VHL) disease suppressor, Myb-related protein 2\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Knockdown of HIF-2α downregulates B-Myb protein levels in pVHL-deficient 786-O cells. Cell lysates of control-, B-Myb-, or HIF-2α-knockdown 786-O cell lines were immunoblotted with anti-B-Myb or anti-HIF-2α antibodies to determine protein levels of B-Myb and HIF-2α, respectively. Hsp90 was used as loading control. Representative data from three independent experiments are shown. (B) Knockdown of HIF-2α does not affect B-Myb mRNA levels. Total RNA was isolated from control- or HIF-2α-knockdown 786-O cells and analyzed by quantitative RT-PCR analysis. Data represent the mean ± SD of three independent experiments. (C) B-Myb downregulation by HIF-2α knockdown in pVHL-deficient cells is proteasome-dependent. Control or HIF-2α-knockdown 786-O cells were cultured in the presence or absence of MG132 (10 μM for 6 h) and subjected to immunoblotting with anti-B-Myb or anti-HIF-2α antibodies. Hsp90 was used as loading control. Representative data from three independent experiments are shown. (D) Stabilization of HIF-2α and B-Myb by MG132 and lactacystin. 786-O cells were cultured in the presence or absence of MG132 (10 μM for 6 h) or lactacystin (5 μM for 6 h) and immunoblotted with anti-B-Myb or anti-HIF-2α antibodies. Hsp90 was used as loading control. Representative data from three independent experiments are shown. (E) Stability of B-Myb with or without HIF-2α. Control 786-O cells or HIF-2α knockdown cells were exposed to cycloheximide (CHX, 50 μg/ml) for 30 or 60 min. The lysates were subjected to western blot with antibodies against B-Myb (short and long exposure are shown), HIF-2α, or Hsp90. Hsp90 was used as loading control. Representative data from three independent experiments are shown. (F) The intensities of the B-Myb bands in (D) were normalized to those of the corresponding Hsp90 bands and plotted as ratio of the normalized value against control cells at 0 min. Data are presented as the mean ± SD of three independent experiments. (G) The intensities of B-Myb bands in (D) at 0 min were set as 1.\n\nFigure 2: Figure 2. (A) Control- or 3×FLAG-pVHL-expressing 786-O cell lines were cultured in the presence or absence of CoCl2 (400 μM) for 7 h, and cell lysates were immunoblotted with anti-B-Myb, anti-HIF-2α, or anti-pVHL antibodies. Forced expression of 3×FLAG-pVHL downregulates HIF-2α and B-Myb protein levels under normoxic conditions, and CoCl2 treatment rescues HIF-2α and B-Myb protein levels. Hsp90 was used as loading control. Representative data from three independent experiments are shown. (B) Knockdown of HIF-2α suppresses the accumulation of B-Myb under hypoxic-like conditions. Control or pVHL-expressing 786-O cell lines were transfected with non-specific or HIF-2α-targeting siRNA and cultured for 2 days, and cell lysates were immunoblotted with anti-B-Myb, pVHL, or anti-HIF-2α antibodies. Cells were incubated in the presence or absence of CoCl2 (400 μM) for 7 h before they were harvested. Hsp90 was used as a loading control. Representative data from three independent experiments are shown.\n\nFigure 3: Figure 3. (A) Endogenous interaction between HIF-2α and B-Myb. 786-O cell lysates were immunoprecipitated (IP) with an anti-HIF-2α antibody and immunoblotted with anti-B-Myb or anti-HIF-2α antibodies. Representative data from three independent experiments are shown. (B) Cytoplasmic and nuclear fractions were prepared from 786-O cell lysates and utilized for co-immunoprecipitation assays as in (A). Endogenous HIF-2α and B-Myb are enriched in the nucleus but also localize to the cytoplasm. An interaction between HIF-2α and B-Myb was detected in the nuclear fraction but not the cytoplasmic fraction. Hsp90 and Lamin B1 were used as cytoplasmic and nuclear protein markers, respectively. Representative data from two independent experiments are shown.\n\nFigure 4: Figure 4. (A) Schematic representation of the HIF-2α deletion mutants used in this study. (B) Co-immunoprecipitation between full-length B-Myb and deletion mutants of HIF-2α. Wild-type or deletion mutants of 3×FLAG-HIF-2α were coexpressed with full-length 3×HA-B-Myb in HEK293T cells, and cell lysates were subjected to immunoprecipitation (IP) with an anti-HA antibody and immunoblotted with anti-FLAG or anti-HA antibodies. Deletion mutants of HIF-2α containing a central region between residues 436 to 600, which fully spans the transactivation domain and partially spans the oxygen-dependent degradation domain, interact with full length B-Myb. Representative data from three independent experiments are shown.\n\nFigure 5: Figure 5. (A) Schematic representation of the B-Myb deletion mutants used in this study. (B) Co-immunoprecipitation between full-length HIF-2α and deletion mutants of B-Myb. Wild-type or deletion mutants of 3×HA-B-Myb were coexpressed with full length 3×FLAG-HIF-2α in HEK293T cells, and cell lysates were subjected to immunoprecipitation (IP) with an anti-HA antibody and immunoblotted with anti-FLAG or anti-HA antibodies. Deletion mutants of B-Myb containing the C-terminal region (starting at residue 468), which comprises the conserved region and the negative regulatory domain, interact with full-length HIF-2α. Representative data from three independent experiments are shown."
      }
    ]
  },
  {
    "id": "PMC5410580_multi",
    "image": [
      "images/PMC5410580-f1.png",
      "images/PMC5410580-f2.png",
      "images/PMC5410580-f3.png",
      "images/PMC5410580-f4.png",
      "images/PMC5410580-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Distribution of ELOVL4 in the Developing and Adult Mouse Brain\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Distribution of ELOVL4 protein and mRNA in the mouse brain. (A) Immunohistochemical labeling (IHC) for ELOVL4 in the mouse brain at P60 is widespread, but shows region-specific distribution. (B) In situ hybridization (ISH) for Elovl4 mRNA in the mouse brain at P56 also is widespread and shows distribution similar to ELOVL4 protein in (A). (Image from the Allen Institute for Brain Science Allen Mouse Brain Atlas for the P56 mouse brain, image number 69059903_134. http://mouse.brain-map.org). CB, cerebellum; BG, basal ganglia; CTX, cerebral cortex; HPF, hippocampal formation; HY, hypothalamus; M, medulla; MB, midbrain; MOB, main olfactory bulb; P, pons; cc, corpus callosum; fo, fornix; VL, lateral ventricle. Scale bars = 1 mm.\n\nFigure 2: Figure 2. Expression of ELOVL4 in development of cerebral cortex. (A) Developing cortex at E18 shows intense ELOVL4 labeling in numerous cells throughout the cortex (CTX). Labeling is especially prominent in the periventricular zone (PVZ), particularly in the region directly adjacent to the lateral ventricle (VL). (B) Developing cortex at P10 shows strong labeling of cells in all layers, but the most intensely labeled cells are present in layers II/III and V. Numerous ELOVL4-positive cells also are present in the developing corpus callosum (cc). (C) Widespread, layered expression of ELOVL4 is preserved in the cortex at P20. (D) The characteristic layered pattern of ELOVL4 expression in cortex is maintained at P60. Scale bars = 250 μm.\n\nFigure 3: Figure 3. Expression of ELOVL4 in the olfactory bulb. (A) Labeling for ELOVL4 is present in the main olfactory bulb (MOB) and accessory olfactory bulb (AOB). Mitral cells in the mitral cell layer (mi) of the MOB and the AOB show intense labeling. Cells surrounding the olfactory glomeruli (gl) and granule cells (gr) also show ELOVL4 labeling. Little labeling is present in the outer plexiform layer (opl) or inner plexiform layer (ipl). (B) Labeling for the neuronal marker, NeuN. (C) Overlay of (A,B). Scale bar = 1 mm.\n\nFigure 4: Figure 4. Expression of ELOVL4 in development of the hippocampal formation. (A) The developing hippocampal formation (HPF) at E18 shows strong labeling for ELOVL4 in cells of the developing Cornu Ammonis (CA), dentate gyrus (DG), and subiculum (Sub). Intense ELOVL4 labeling is seen near the margins of the lateral ventricle (VL). The periventricular zone (PVZ) of the overlying and developing cerebral cortex iare visible above the hippocampal formation. (B). Developing hippocampal formation at P10, with a well-developed CA region and dentate gyrus. Cells in the CA region show ELOVL4 labeling, with cells in CA3 showing stronger labeling than cells in CA1. Cells in the dentate gyrus and subiculum also show labeling. Labeled cells are also present in the developing corpus callosum (cc) and fornix (fo). Developing thalamus (TH) is visible below the hippocampal formation. (C) Hippocampal formation at P20. ELOVL4 labeling is present throughout the CA region, with cells in CA3 showing the strongest labeling. Labeling for ELOVL4 in the granule cell layer of the dentate gyrus is reduced compared to earlier stages although ELOVL4-positive cells persist along the inner margin of the dentate gyrus. Strong labeling is also present in interneurons in the polymorph layer of the dentate gyrus and in the subiculum. (D) The hippocampal formation at P60 shows distribution of ELOVL4 labeling similar to that at P20. Scale bars = 500 μm.\n\nFigure 5: Figure 5. Expression of ELOVL4 in development of the basal ganglia. (A) The developing basal ganglia at E18 show very high levels of ELOVL4 expression, particularly in the periventricular zone (PVZ) adjacent to the lateral ventricle (VL). Caudoputamen (CP), nucleus accumbens (ACB), and olfactory tubercle (OT) are shown. (B). Labeling for ELOVL4 in the basal ganglia decreases substantially by P10. (C) The basal ganglia maintain low levels of ELOVL4 expression at P20. (D) At P60, the basal ganglia maintain relatively low levels of ELOVL4 with sparsely distributed ELOVL4-labeled cells. Labeling for ELOVL4 is also evident in the subventricular zone (SVZ). HPF, hippocampal formation; HY, hypothalamus; PIR, piriform cortex; cc, corpus callosum; fo, fornix; ic, internal capsule. Scale bars = 500 μm."
      }
    ]
  },
  {
    "id": "PMC5410580_multi_2",
    "image": [
      "images/PMC5410580-f6.png",
      "images/PMC5410580-f7.png",
      "images/PMC5410580-f8.png",
      "images/PMC5410580-f9.png",
      "images/PMC5410580-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Distribution of ELOVL4 in the Developing and Adult Mouse Brain\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Expression of ELOVL4 in the amygdala. Labeling for ELOVL4 is present in the amygdala, but varies among subnuclei. Prominent labeling in the central amygdalar nucleus (CEA), basolateral amygdalar (BLA), basomedial amygdalar nucleus (BMA), posterior amygdalar nucleus (PA), and the cortical amygdalar area (COA) is shown. CA1, Cornu Ammonis, field 1; EP, endopiriform nucleus; GPe, globus pallidus external; GPi, globus pallidus internal; HPF, Hippocampal formation; Pir, piriform cortex; Sub, subiculum; VL, lateral ventricle. Scale bar = 500 μm.\n\nFigure 7: Figure 7. Expression of ELOVL4 in the developing cerebellum. (A) ELOVL4 labeling is present in the cerebellum (CB) during early development at E18. Intense labeling is present in the nascent external granule cell layer (egl) of the developing cerebellar cortex. Labeling for ELOVL4 is also present in the developing inner granule cell layer (igl). A few labeled cells also are present in the forming molecular cell layer (mcl). (B) Intense ELOVL4 labeling is present in the egl and igl of the cerebellar cortex at P10. Many cells traversing the mcl show ELOVL4 labeling. Strong ELOVL4 labeling is present in the deep cerebellar nuclei by P10 (interpositus nucleus, IP, shown). (C) Mature layering of cerebellar cortex is achieved by P20, and is characterized by very intense ELOVL4 labeling in cells in the granule cell layer (gcl). Purkinje cells in the Purkinje cell layer (pcl) also show ELOVL4 labeling, but are difficult to discern at this magnification. The sparsely distributed cells in the mcl also show labeling. Labeling of cells in the deep cerebellar nuclei also persists. (D) Distribution of ELOVL4 in the P60 cerebellar cortex and deep cerebellar nuclei (fastigial nucleus, FN, shown) is similar to that in the P20 cerebellum. IC, inferior colliculus; M, medulla; MB, midbrain; P, pons; V4, 4th ventricle. Scale bars = 500 μm for (A); 1 mm for (B–D).\n\nFigure 8: Figure 8. Expression of ELOVL4 in the thalamus. (A) Prominent labeling for ELOVL4 in the lateral thalamus is present in the lateral geniculate nucleus (LG), reticular nucleus (RT), and subgeniculate nucleus (SubG). The medial geniculate nucleus (MG) shows much weaker ELOVL4 labeling. (B) Labeling for the neuronal marker, NeuN, in lateral thalamus. (C) Overlay of (A,B). (D) Labeling for ELOVL4 also is present in more medial regions of the thalamus. Strong labeling is present in the anteroventral (AV), ventral posterolateral (VPL), and ventral anterior-lateral complex (VAL) nuclei. Moderate ELOVL4 labeling is present in the lateral dorsal (LD), ventral posteromedial (VPM), and ventromedial (VM) nuclei. Lateral posterior (LP), posterior complex (PO), and subparafascicular (SPF) nuclei of the thalamus show less ELOVL4 labeling. (E) Labeling for NeuN in the medial thalamus. (F) Overlay of (D,E). HPF, hippocampal formation; MB, midbrain; ZI, zona incerta. Scale bars = 500 μm.\n\nFigure 9: Figure 9. Expression of ELOVL4 in the hypothalamus and midbrain. (A) Extensive ELOVL4 labeling is present in the hypothalamus (HY). Prominent labeling is seen in the lateral preoptic area (LPO), lateral mammilary nucleus (LM), zona incerta (ZI), and in parts of the lateral hypothalamic area (LHA). TH, Thalamus; opt, optic tract. (B) Labeling for ELOVL4 in the midbrain is widespread but varies among nuclei. Prominent labeling is present in the superior colliculus (SC), inferior colliculus (IC), midbrain reticular nucleus (MRN), and anterior pretectal nucleus (APN). Substantia nigra (SN) shows much less labeling for ELOVL4 than other portions of the midbrain. Cerebellum (CB), cortex (CTX), and zona incerta (ZI) also are visible. Scale bars = 500 μm.\n\nFigure 10: Figure 10. Expression of ELOVL4 in the pons and medulla. Many labeled cells are present in the pons, including cells in the pontine reticular nucleus (PRN), pontine gray (PG), and superior olivary complex (SOC). In the medulla, ELOVL4-positive cells are prominent in the medial vestibular nucleus (MV), facial motor nucleus (VII), spinal nucleus of the trigeminal (SPV), parvicellular reticular nucleus (PARN), medullary reticular nucleus (MDRN), and later reticular nucleus (LRN). CB, cerebellum; IP, interpositus nucleus of the cerebellum; MB, midbrain; V4, fourth ventricle. Scale bar = 500 μm."
      }
    ]
  },
  {
    "id": "PMC5410580_multi_3",
    "image": [
      "images/PMC5410580-f11.png",
      "images/PMC5410580-f12.png",
      "images/PMC5410580-f13.png",
      "images/PMC5410580-f14.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Distribution of ELOVL4 in the Developing and Adult Mouse Brain\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. ELOVL4 expression is primarily neuronal. (A–C) Cerebral Cortex (CTX). (A) Labeling for ELOVL4 is present in all layers of the cerebral cortex (CTX). Cells in the pyramidal layers (II/III and V) are most prominently labeled, but ELOVL4-positive cells also are present in the molecular layer (I), layer 4 (IV), and layer 6 (VI). (B) Labeling for the neuronal marker, NeuN. (C) Overlay of panels (A,B) shows close correspondence of ELOVL4 (red) and NeuN labeling (green), indicating that ELOVL4 is primarily expressed by neurons in the cortex. (D–F) Hippocampal formation. (D) Labeling for ELOVL4 is present in the cellular layers of the hippocampal formation (HPF), including the Cornu Ammonis, with field 1 (CA1) showing less prominent labeling than field 3 (CA3). Prominent ELOVL4 labeling also is present in the subiculum (sub) and interneurons in the polymorph layer (arrow). Cells along the inner margin of the dentate gyrus (DG) show moderate ELOVL4 labeling, but most dentate granule cells show little ELOVL4 labeling. (E) Labeling for the neuronal marker, NeuN. (F) Overlay of (D,E) shows close correspondence of ELOVL4 (red) and NeuN (green) labeling, indicating that ELOVL4 is primarily expressed by neurons in the hippocampal formation. TH, Thalamus. (G–I) Cerebellar cortex. (G) Cross section through a cerebellar folium showing ELOVL4 expression in the cerebellar cortex. Neurons (arrows) in the molecular cell layer (mcl) show strong ELOVL4 labeling, but the monolayer of large Purkinje cells (arrowheads) that form the Purkinje cell layer (pcl) shows only moderate levels of ELOVL4 labeling. The densely packed cells of the granule cell layer (gcl) show very intense labeling. (H) Labeling for the neuronal marker, NeuN, strongly labels neurons in the gcl, but not Purkinje cells, as appropriate. (I) Overlay of panels (G,H) shows close correspondence of intense ELOVL4 (red) and NeuN (green) labeling resulting in an orange color in the gcl. These results indicate that ELOVL4 in the cerebellum is primarily expressed by neurons. wm, white matter of the arbor vitae. Scale bars = 200 μm for (A–C,G–I); 500 μm for (D–F).\n\nFigure 12: Figure 12. Astrocytes show little ELOVL4 labeling. (A) Labeling for ELOVL4 is present in many cells in the cerebral cortex (*). (B) Astrocytes (arrowheads), identified by labeling for glutamine synthetase (GS). (C) Overlay of (A,B) shows little labeling for ELOVL4 in astrocytes. Nuclei counterstained with DAPI (blue) in all panels. Scale bar = 50 μm.\n\nFigure 13: Figure 13. Radial glial cells show little ELOVL4 labeling. (A) Many cells (*) in the external and internal granule cell layers (egl and igl, respectively), as well as cells migrating through the molecular cell layer (mcl), of the developing cerebellum show ELOVL4 labeling at P10. (B) Radial glial cells and their processes (arrowheads) spanning the layers of the cerebellum can be identified by labeling for glutamine synthtase (GS). (C) Overlay of (A,B) shows no colocalization of labeling for ELOVL4 and GS. (D) Many cells in the developing cerebral cortex show ELOVL4 labeling (*) at P10. (E) Radial glial cells and their processes (arrowheads), identified by labeling for glial fibrillary acidic protein (GFAP). Non-specfic labeling of a blood vessel (bv) also is visible. (F) Radial glial cells and their processes do not show labeling for ELOVL4. Nuclei counterstained with DAPI (blue) in all panels. Scale bars = 50 μm.\n\nFigure 14: Figure 14. Glial cells in white matter express ELOVL4. (A) Immunohistochemical labeling (IHC) for ELOVL4 identifies presumptive oligodendrocytes (arrowheads) in white matter. Corpus callosum (cc) shown. CTX, cerebral cortex; BG, basal ganglia. (B) In situ hybridization (ISH) for Elovl4 mRNA also reveals small cells in corpus callosum (arrowheads). VL, lateral ventricle. (Image from the Allen Institute for Brain Science Allen Mouse Brain Atlas for the P56 mouse brain, image number 69059903_134. http://mouse.brain-map.org). Scale bars = 100 μm."
      }
    ]
  },
  {
    "id": "PMC5448236_multi",
    "image": [
      "images/PMC5448236-f1.png",
      "images/PMC5448236-f2.png",
      "images/PMC5448236-f3.png",
      "images/PMC5448236-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Energy Charge as an Indicator of Pexophagy in Pichia pastoris\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Detection of GFP expression in P. pastoris. Left: P. pastoris cells under microscope; Right: P. pastoris cells under fluorescence microscope.\n\nFigure 2: Figure 2. Pichia pastoris cells when the carbon source was switched from methanol to glucose or ethanol.\n\nFigure 3: Figure 3. AOX and FDH activities in P. pastoris cells at different concentrations of various carbon sources. (A) AOX activities of P. pastoris cells when carbon source was switched from 0.5% methanol to different concentrations of glucose. (B) FDH activities of P. pastoris cells when carbon source was switched from 0.5% methanol to different concentrations of glucose. (C) AOX activities of P. pastoris cells when carbon source was switched from 0.5% methanol to different concentrations of ethanol. (D) AOX activities of P. pastoris cells when carbon source was switched from 0.5% methanol to different concentrations of ethanol.\n\nFigure 4: Figure 4. ATP, ADP, AMP concentrations, and EC of P. pastoris cells when the carbon source was switched from 0.5% methanol to other carbon sources. (A) ATP conncentrations of P. pastoris during carbon source shifting from 0.5% methanol to different concentrations of ethanol or glucose. (B) ADP conncentrations of P. pastoris during carbon source shifting from 0.5% methanol to different concentrations of ethanol or glucose. (C) AMP conncentrations of P. pastoris during carbon source shifting from 0.5% methanol to different concentrations of ethanol or glucose. (D) EC values of P. pastorisd during carbon source shifting from 0.5% methanol to different concentrations of ethanol or glucose."
      }
    ]
  },
  {
    "id": "PMC5471156_multi",
    "image": [
      "images/PMC5471156-f1.png",
      "images/PMC5471156-f2.png",
      "images/PMC5471156-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Effects of naturally occurring missense mutations and G525V in the hydratase domain of human d-bifunctional protein on hydratase activity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Primary structure (A) and function (B) of d-BP. The first methionine is numbered 1. “AKL” at the C terminus indicates an amino acid sequence (Ala–Lys–Leu) that is a peroxisome-targeting signal.\n\nFigure 2: Figure 2. Multiple alignment of the hydratase domain of d-bifunctional protein. Amino acid sequences of human d-BP domain (amino acids 322–622) and its multiple alignment among 30 eukaryotes were taken from the Peroxisome Database. Asterisks (*) show the locations of SNPs that cause missense mutations in humans. Gray indicates amino acids with conservation rates among eukaryotes of < 70%. Black and red indicate amino acids with conservation rates > 70%. Black indicates amino acids for which hydratase activities of variants have already been investigated [7]. Red indicates amino acids for which the effects of missense mutations are not clear. Accession numbers are as follows, Homo sapiens, NP_000405; Equus caballus, NP_001075370; Monodelphis domestica, XP_001378211; Macaca mulatta, XP_001087837; Pan troglodytes, XP_003310890, Rattus norvegicus, NP_077368; Mus musculus, NP_032318; Canis familiaris, XP_531860; Bos taurus, NP_001007810; Xenopus tropicalis, NP_001027490; Takifugu rubripes, NP_058850; Tetraodon nigroviridis, NP_570602; Gallus gallus, NP_990274; Danio rerio, NP_956430; Ciona intestinalis, XP_002124954; Anopheles gambiae, XP_314766; Drosophila melanogaster, NP_573109; Apis mellifera, XP_393475; Tetrahymena thermophile, XP_001021425; Caenorhabditis elegans, NP_509146; Dictyostelium discoideum, XP_635235; Neurospora crassa, XP_962039; Aspergillus fumigatus, XP_ 746577; Yarrowia lipolytica, XP_503980; Cryptococcus neoformans, XP_571589; Eremothecium gossypii, NP_986606; Candida glabrata, XP_448864; Saccharomyces cerevisiae, NP_012934; Kluyveromyces lactis, XP_454574; Debaryomyces hansenii, XP_456704.\n\nFigure 3: Figure 3. Three-dimensional structure of human d-BP hydratase unit (A and B) and fruit fly d-BP (C and D). The enoyl-CoA hydratase 2 unit of human d-BP (PDB entry 1S9C) is shown. Blue indicates residues of the enoyl-CoA hydratase motif. Red indicates residues at which the effects of missense mutations were investigated in this study (A). Three-dimensional structure of the panel, A is rotated around the y-axis (B). The d-BP dimer of fruit fly (PDB entry 3OML). Magenta and blue indicate each monomer of the d-BP molecule (C). d-BP monomer indicated in blue in panel C is shown in stick style. As in panel A, blue and red indicate the enoyl-CoA hydratase motif and amino acid residues, respectively (D). All three-dimensional structures were drawn on the basis of data from PDB using the software Strap (Interactive Structure based Sequences Alignment Program) [14]."
      }
    ]
  },
  {
    "id": "PMC5506878_multi",
    "image": [
      "images/PMC5506878-f1.png",
      "images/PMC5506878-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Application of a diagnostic methodology by quantification of 26:0 lysophosphatidylcholine in dried blood spots for Japanese newborn screening of X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Comparison of LysoPCs in X-ALD patients, newborns and healthy adults (controls). The plots are the amount of: A) 20:0 LysoPC; B) 24:0 LysoPC; C) 26:0 LysoPC. X-ALD patients (n = 4) are in red; newborns (n = 604) and healthy adults (n = 50) are in black. The red dot is a symptomatic female; the red square marker is an X-ALD male; the other two triangle markers are two AMN males. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)\n\nFigure 2: Figure 2. Ratios of 26:0 LysoPC to 20:0 LysoPC (26:0 LysoPC/20:0 LysoPC) in X-ALD patients, newborns and healthy adults (controls). X-ALD patients (n = 4) are in red; newborns (n = 604) and healthy adults (n = 50) are in black. The red dot is a symptomatic female; the red square marker is an X-ALD male; the other two triangle markers are two AMN males. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)"
      }
    ]
  },
  {
    "id": "PMC5547663_multi",
    "image": [
      "images/PMC5547663-f1.png",
      "images/PMC5547663-f2.png",
      "images/PMC5547663-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Identification of a novel mutation in PEX10 in a patient with attenuated Zellweger spectrum disorder: a case report\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Magnetic resonance imaging scans from patient with PEX10 defect (12 years of age). The magnetic resonance imaging scan shows: a axial T2-weighted imaging and b coronal T2-weighted imaging revealing a central lesion in the mesencephalon (arrows), from the nucleus ruber dorsocaudally down to the cerebellar peduncles\n\nFigure 2: Figure 2. Immunofluorescence microscopy analysis using antibodies raised against catalase, a peroxisomal matrix enzyme, in skin fibroblasts of a control subject (left panels) and the patient, F1453 (right panels) cultured at 37 °C (upper panels) and 40 °C (lower panels) for 2 weeks. At 37 °C cells of the patient reveal a normal peroxisomal staining in most cells (a representative picture is shown), whereas at 40 °C catalase staining becomes cytosolic confirming the peroxisome biogenesis defect in the patient\n\nFigure 3: Figure 3. Sequencing chromatograms confirming the next generation sequencing findings and showing expected segregation pattern. a Patient, homozygous for c.530 T > G (p.Leu177Arg) in PEX10 gene. b and c Father and mother, heterozygous for the same variant"
      }
    ]
  },
  {
    "id": "PMC5568266_multi",
    "image": [
      "images/PMC5568266-f1.png",
      "images/PMC5568266-f2.png",
      "images/PMC5568266-f3.png",
      "images/PMC5568266-f4.png",
      "images/PMC5568266-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A homozygous missense variant in HSD17B4 identified in a consanguineous Chinese Han family with type II Perrault syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigree of the consanguineous Perrault syndrome family. Affected individuals were denoted by filled symbols. The arrow indicated the proband (IV2). Genotypes were shown below each symbol\n\nFigure 2: Figure 2. Brain MRI images for the proband (IV2). Marked and diffuse cerebellar atrophy was present in the proband\n\nFigure 3: Figure 3. Audiograms from the proband at the age of 37. a Audiogram of the left ear. b Audiogram of the right ear. In pure-tone audiometry measurements, similar air and bone thresholds are indicative of hearing loss due to dysfunction of the inner ear, which demonstrates bilaterally sensorineural hearing loss especially at high frequency. Audiograms were created using the AudGen online tool (version 0.71) (http://audsim.com/audgen/)\n\nFigure 4: Figure 4. Sanger sequences of the mutation in HSD17B4 in the affected sisters and their parents. The position of the G > T transition, which led to alanine to serine substitution, was indicated by an arrow. The mutation could be found in heterozygous parents (III5 and III6) and affected patients (IV1 and IV2)\n\nFigure 5: Figure 5. Analysis of wild-type and mutant HSD17B4 protein expression by Western blot. a Compared by T-test, expression of the variant c.298G > T (p.A100S) was lower than expression of the wild-type. b There was significant difference between protein expressions for transfected wild-type and mutant plasmids"
      }
    ]
  },
  {
    "id": "PMC5571181_multi",
    "image": [
      "images/PMC5571181-f1.png",
      "images/PMC5571181-f2.png",
      "images/PMC5571181-f3.png",
      "images/PMC5571181-f4.png",
      "images/PMC5571181-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Genetic deficiency in neuronal peroxisomal fatty acid β-oxidation causes the interruption of dauer development in Caenorhabditis elegans\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomal FA β-oxidation gene daf-22 expresses in ASK chemosensory neurons. (a) A schematic illustration of representative amphid chemosensory neurons (ASK, ADL, ASI, AWB, ASH, and ASJ). Each neuron is annotated. A, anterior; P, posterior; D, dorsal; and V, ventral. (b–e) daf-22p::GFP::daf-22 expression in a representative ASK neuron of an L2-stage worm. The ASK neuron is indicated by a solid arrowhead. Images are lateral views of the head region. Scale bar, 10 μm. (b) The expression loci of daf-22p::GFP::daf-22 in intestine and neurons. (c) DiI staining identifies amphid chemosensory neurons where ASK, ADL and ASI neurons (in order from anterior to posterior) are shown. (d) Merged image of daf-22p::GFP::daf-22 expression and DiI-stained neurons. (e) Merged image of daf-22p::GFP::daf-22 expression, DiI-stained neurons and differential interference contrast (DIC) is shown for orientation.\n\nFigure 2: Figure 2. Function of peroxisomal FA β-oxidation gene daf-22 in ASK neurons is required for pheromone-induced dauer development. (a–c) Percentage of pheromone-induced dauer formation of tissue-specific (pan-neural- and intestine-specific) daf-22 rescue worms (Ascr #1 (a), Ascr #2 (b), and Ascr #3 (c)). Data are shown as mean ± SEM of five independent experiments. (d) Percentage of pheromone (Ascr #2)-induced dauer formation of ASK neuron-specific daf-22 rescue worms. Data are shown as mean ± SEM of three independent experiments. (a–d) *P < 0.05 compared with WT, **P < 0.05 compared with daf-22(ok693) worms, Student’s t-test. (e,f) Relative concentration of worm-body ascaroside pheromones Ascr #2 (e) and Ascr #3 (f) in intestine- and ASK neuron-specific daf-22 rescue worms. Data are shown as mean ± SEM of four independent experiments with three technical repeats. *P < 0.001 compared with WT, **P < 0.001 compared with daf-22(ok693) worms, Student’s t-test. See also Supplementary Table S1.\n\nFigure 3: Figure 3. Dauer development in daf-22(ok693) worms is dependent on DAF-16 activity. (a) Changes of daf-7p::GFP expression in response to exogenous pheromone (Ascr #1) in WT and daf-22(ok693) worms. Images represent views of the head region of a representative L2-stage worm. Scale bar, 50 μm. See also Supplementary Fig. S3a,b, and Supplementary Table S2. (b) Percentage of dauer formation in WT, daf-7(e1372), daf-22(ok693), and daf-22(ok693);daf-7(e1372) worms at 25 °C. (c) Percentage of dauer formation in WT, daf-2(e1370), daf-22(ok693), and daf-22(ok693);daf-2(e1370) worms at 25 °C. (d) Percentage of pheromone (Ascr #1)-induced dauer formation in WT, daf-16(mu86), daf-22(ok693), and daf-16(mu86);daf-22(ok693) worms. (b–d) Data are shown as mean ± SEM of three independent experiments. N.D., not detected, *P < 0.05 compared with WT, **P < 0.05 compared with daf-7(e1372) worms, Student’s t-test. (e) Relative mRNA expression of sod-3 in daf-22(ok693) worms. (f) Relative sod-3 mRNA expression in WT, daf-2(e1370), daf-22(ok693) and daf-22(ok693);daf-2(e1370) worms. (e–f) Data are shown as mean ± SEM of three independent experiments. *P < 0.05 compared with WT, N.S., not significant, and **P < 0.05 compared with daf-22(ok693);daf-2(e1370) worms, Student’s t-test.\n\nFigure 4: Figure 4. Expression of ILP is increased in daf-22(ok693) worms. (a) Percentage of pheromone (Ascr #1)-induced dauer formation in WT, daf-28(tm2308), daf-22(ok693), and daf-22(ok693);daf-28(tm2308) worms. Data are shown as mean ± SEM of at least two independent experiments. *P < 0.05 compared with WT worms, N.S., not significant, and **P < 0.05 compared with daf-22(ok693);daf-28(tm2308) worms, Student’s t-test. (b) Percentage of total worms expressing daf-28p::GFP in ASK neurons in WT, daf-22(ok693), and ASK neuron-specific daf-22 rescue worms. Data are shown as mean ± SEM of seven independent experiments (WT, n = 59; daf-22(ok693), n = 56; and ASK neuron-specific daf-22 rescue worms, n = 64). N.S., not significant, *P < 0.005 compared with WT worms, and **P < 0.005 compared with daf-22(ok693) worms, Student’s t-test. (c) daf-28p::GFP expression in L2 WT and daf-22(ok693) worms. ASK and ASI neurons are indicated by filled and open arrowheads, respectively. Images are lateral views of the head region of a representative L2-stage worm. Inset images are magnified images of ASK, ADL, and ASI neurons (in order from anterior to posterior). Scale bar, 10 μm. (d) daf-28p::GFP expression in ASK neuron-specific daf-22 rescue worms. ASK and ASI neurons are indicated by filled and open arrowheads, respectively. Images are lateral views of the head region of a representative worm. Scale bar, 10 μm. (e) (Left) Changes in relative mRNA expression of ILPs in daf-22(ok693) worms compared with WT worms at L2 stage. Dotted line indicates the reference ILP expression in WT worms at L2 stage. Data are shown as mean ± SEM of four independent experiments. (Right) Relative daf-28 mRNA expression in daf-22(ok693) compared with WT worms. Data are shown as mean ± SEM of three independent experiments. The figure shown here was drawn based on data presented in Supplementary Fig. S4a for comparison between mRNA levels of ILPs in daf-22(ok693). See also Supplementary Fig. S4a. *P < 0.05 compared with WT worms, Student’s t-test.\n\nFigure 5: Figure 5. ER stress response is increased in daf-22(ok693) worms. (a) hsp-4p::GFP expression in WT and daf-22(ok693) worms. Scale bar, 100 μm. (b) Relative abundance of total and spliced xbp-1 transcript, xbp-1 splicing (spliced xbp-1/total xbp-1 transcript), and hsp-4 mRNA expression in daf-22(ok693) worms compared with WT worms. (c) Relative mRNA expression of hsp-4 and hsp-6 in L2 daf-22(ok693) worms compared with WT worms. (d) Relative abundance of xbp-1 splicing (spliced xbp-1/total xbp-1 transcript) and hsp-4 mRNA expression in WT, daf-2(e1370), daf-22(ok693), and daf-22(ok693); daf-2(e1370) worms. (b–d) Data are shown as mean ± SEM of three independent experiments. N.S., not significant, *P < 0.05 compared with WT, **P < 0.05 compared with daf-22(ok693);daf-2(e1370) worms, Student’s t-test."
      }
    ]
  },
  {
    "id": "PMC5571181_multi_2",
    "image": [
      "images/PMC5571181-f6.png",
      "images/PMC5571181-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Genetic deficiency in neuronal peroxisomal fatty acid β-oxidation causes the interruption of dauer development in Caenorhabditis elegans\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. XBP-1 activity stimulated by the increased ER stress response enhances ILP expression in daf-22(ok693) worms. (a) Relative daf-28 mRNA expression in the ER stress response mutants, pek-1(ok275), atf-6(ok551), and ire-1(ok799) worms at L2 stage. (b) Relative mRNA expression of daf-28, ins-12, and hsp-4 in L2 xbp-1(zc12) mutants compared with WT worms. See also Supplementary Fig. S6b. (a,b) Data are shown as mean ± SEM of three independent experiments. N.S., not significant, *P < 0.05 compared with WT worms, Student’s t-test. (c) Relative mRNA expression of daf-28, ins-12, and hsp-4 in L2 WT, xbp-1(zc12), daf-22(ok693), and daf-22(ok693); xbp-1(zc12) worms. Data are shown as mean ± SEM of two independent experiments. *P < 0.05 compared with WT, **P < 0.05 compared with daf-22(ok693) worms, Student’s t-test. (d) Expression of hsp-4p::GFP and daf-28p::DsRed in head neurons of WT and daf-22(ok693) worms. Images are lateral views of the head region of a representative worm. The three images on the right are magnified images of the boxed areas in the left-most images of WT and daf-22(ok693) worms, respectively. Scale bar, 10 μm.\n\nFigure 7: Figure 7. Proposed model for cellular mechanisms causing interruption of alternative developmental process by defective peroxisomal FA β-oxidation in ASK neurons in C. elegans. In WT animals, exogenous pheromones representing stressful growth conditions can suppress the expression of neuronal insulin-like peptides (ILPs), diminishing insulin/IGF-1 signaling (IIS) in non-neuronal cells. This causes activation of DAF-16/FOXO, which is required for worms to enter dauer development in response to pheromones. However, in daf-22(ok693) mutant worms, deficiency of peroxisomal FA β-oxidation in ASK neurons causes an increase in the levels of VLCFAs and a disturbance in cellular lipid homeostasis, which may subsequently activate the ER stress response and its downstream transcription factor XBP-1. In turn, activated XBP-1 stimulates the transcription of neuronal ILPs, such as daf-28 and ins-12, which would consequently enhance IIS of non-neuronal cells to suppress DAF-16/FOXO. Therefore, dauer development of daf-22(ok693) is interrupted even in the presence of exogenous pheromones. Bold arrows and red arrows indicate activation, and the symbol ⊥ indicates inhibition."
      }
    ]
  },
  {
    "id": "PMC5610811_multi",
    "image": [
      "images/PMC5610811-f1.png",
      "images/PMC5610811-f2.png",
      "images/PMC5610811-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Diagnostic application of clinical exome sequencing in Leber congenital amaurosis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Color photographs of the retinas of six patients with LCA. A, B: Two 6-month-old babies (P2 and P3) with compound heterozygous mutations in GUCY2D (p.[Phe993LeufsTer13]+[Gly1013Glu] and p.[His664Pro]+[Phe883LeufsTer13], respectively) have no definite abnormal finding (OD) in the retina. C: A 7-month-old baby (P5) with compound heterozygous missense mutations in NMNAT1 (p.[Arg66Trp]+[Arg237Cys]) has marked chorioretinal atrophic changes in the macula with vessel narrowing and mild pigmentary changes (OD). D: A 1-year-old baby (P6) with only one pathogenic mutation in NMNAT1 (p.[Arg237Cys]+[?]) shows nystagmus, hyperopia, and a characteristic macular coloboma-like lesion (OS). E: An 8-month-old baby (P8) presented with poor eye contact, extinguished electroretinogram, +6.00 diopters hyperopia, slight optic disc pallor, and mild vessel narrowing (OD). We identified one frameshift mutation (p.Arg1189GlyfsTer7) in RPGRIP1. F: A 29-year-old male (P9) presented with nystagmus developed at the age of 6 years, 20/200 acuity, optic atrophy, and mild vessel attenuation (OD). Compound heterozygous mutations were identified in RPGRIP1 (p.[Tyr693Ter]+[c.2212_2215+21del]).\n\nFigure 2: Figure 2. Fundus photographs of a 29-year-old male with mutations in RPGRIP1 who was initially misdiagnosed with idiopathic infantile nystagmus. He had sustained left head turn posture with left beating jerk nystagmus. Anderson-Kestenbaum surgery was performed at the age of 6 years. At the age of 29 years, his best visual acuity was 20/200 bilaterally. A, B: Fundus photography shows mild optic atrophy with retinal vessel attenuations. C, D: Spectral domain optical coherence tomography shows thinning of the inner segment and outer segment line.\n\nFigure 3: Figure 3. Pedigrees of three patients with mutations in NMNAT1. These patients were nonconsanguineous, and all patients harbored a pathogenic mutation in NMNAT1 (c.709C>T; p. Arg237Cys), which was supposed to be a founder mutation in Koreans."
      }
    ]
  },
  {
    "id": "PMC5642483_multi",
    "image": [
      "images/PMC5642483-f1.png",
      "images/PMC5642483-f2.png",
      "images/PMC5642483-f3.png",
      "images/PMC5642483-f4.png",
      "images/PMC5642483-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"HIF-1α:CRAT:miR-144-3p axis dysregulation promotes osteoarthritis chondrocyte apoptosis and VLCFA accumulation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A. Chondrocytes isolated from either healthy (non-osteoarthritis), or osteoarthritis cartilage from patients who underwent total knee replacement surgery and had different BMIs, were stained with BODIPY. B. Chondrocytes (normal, non-osteoarthritis, and osteoarthritis) were isolated, and total lipid content was analyzed using gas chromatography/mass spectrometry. Lipids were then separated into VLCFA, and either long or medium chain fatty acids (LCFA and MCFA, respectively). The data shown are representative of independent data from at least four patients.\n\nFigure 2: Figure 2. TEM images of human non-osteoarthritis chondrocytes and osteoarthritis chondrocytes (upper panel) were analyzed (lower panel). *indicates abnormal mitochondria and peroxisome. The data shown are representative of three independent experiments.\n\nFigure 3: Figure 3. A. Chondrocytes (normal and non-osteoarthritis) were isolated, and peroxisomal gene profiles were analyzed, represented as a heat map (upper panel). “Red” and “Green” indicates high and low relative expression, respectively. Similarly, the heat map for chondrocytes (normal versus osteoarthritis) (upper panel) is shown. Body-mass indices (BMI) of patients used in this study (left), and relative quantification of CRAT (expressed as fold difference compared with normal chondrocytes) are represented as dot graphs (lower panel). B. CRAT expression was analyzed by age represented as dot graph.\n\nFigure 4: Figure 4. Normal chondrocytes were transfected with specific siRNAs against CRAT. A. The efficiency of siRNAs was analyzed by quantitative PCR (qPCR). B. Cells were stained with mitotracker and mitopotential was analyzed. C. Expression levels of COMP, aggrecan, and MMP13 were analyzed by PCR. D. Normal chondrocytes were treated with lignoceric acid for VLCFA and cell proliferation assays. E. Apoptosis was analyzed using the Muse Cell Analyzer (left panel), while mRNA levels of apoptosis-related genes in CRAT-suppressed, chondrocytes were analyzed by PCR (right panel). F. Cells were stained with anti-PMP70 antibody and BODIPY. G. Catalase activity was analyzed (left panel). Total lipid was measured using gas chromatography/mass spectrometry and divided into VLCFA, and LCFA and MCFA (right panel). The data shown are representative of at least four individuals per experiment. Bars represent the mean ± SD of three individual experiments. *P < 0.05 versus control (normal).\n\nFigure 5: Figure 5. A. Normal chondrocytes were transfected with specific siRNA against CRAT (siCRAT), the miRNA profile analyzed and represented as a heat map. B. Relative quantification of each peroxisome-related gene is expressed as fold difference compared to the control. C. The level of miR-144-3p was analyzed in normal and osteoarthritis chondrocytes of osteoarthritis patients. D. Normal chondrocytes were infected with either miR-144-3p or its inhibitor (anti-miR-144-3p), and proliferation was analyzed. E. Normal chondrocytes were infected with either miR-144-3p or its inhibitor (anti-miR-144-3p) in the absence or presence of siCRAT and apoptosis were analyzed. F. Cells were stained with Ki-67, PMP-70, and mitotracker. The data shown are representative of at least four individuals per experiment. Bars represent the mean ± SD of four individual experiments. *P < 0.05 versus control (normal)."
      }
    ]
  },
  {
    "id": "PMC5649119_multi",
    "image": [
      "images/PMC5649119-f1.png",
      "images/PMC5649119-f2.png",
      "images/PMC5649119-f3.png",
      "images/PMC5649119-f4.png",
      "images/PMC5649119-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Case Report: Ursodeoxycholic acid treatment in Niemann-Pick disease type C; clinical experience in four cases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Note post-CA increases in bilirubin, transaminases, and total plasma cholesterol, which paralleled deterioration of the patients’ clinical status.\n\nFigure 2: Figure 2. These indicate statistically significant (Student’s T-test, performed with Rv3.2.0: *, p < 0.05; **, p < 0.005) elevations in all denoted parameters except alkaline phosphatase, while on cholic acid (CA) compared to ursodeoxycholic acid (UDCA) therapy.\n\nFigure 3: Figure 3. This demonstrated a marked improvement in liver function parameters.\n\nFigure 4: Figure 4. This demonstrated abnormal levels before starting ursodeoxycholic acid (UDCA) that normalized following initiation of UDCA. Dotted line signifies normal value (less than 50 units/L)\n\nFigure 5: Figure 5. ( a) Total NIH score (without hearing and auditory brainstem response) for Case 3. Time of ursodeoxycholic acid (UDCA) commencement (6.67 yrs) marked on graph. ( b) NIH severity scale scores in the four key domains (Ambulation, Fine motor, Swallow and Cognition) for Case 3, both before and after commencement of UDCA."
      }
    ]
  },
  {
    "id": "PMC5675651_multi",
    "image": [
      "images/PMC5675651-f1.png",
      "images/PMC5675651-f2.png",
      "images/PMC5675651-f3.png",
      "images/PMC5675651-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"S149R, a novel mutation in the ABCD1 gene causing X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A-D) Brain MRI of the patient showing multiple patchy symmetrical subtle T2-weighted high-signal-intensity, T1-weighted low-signal-intensity and T2-FLAIR-high-signal-intensity lesions in the bilateral white matter around the lateral ventricle, posterior limbs of the internal capsule, and genu and splenium of the corpus callosum, brainstem and cerebellum. Mild enlargement of the bilateral third ventricle, fourth ventricle and lateral ventricle was observed. (E-F) Abdominal CT showing nodular hyperplasia in the bilateral adrenal glands and calcification in the left gland.\n\nFigure 2: Figure 2. (A) Protein (ALDP) and gene (ABCD1): Genomic structure of the human ABCD1 gene. The gene consists of 10 exons (boxes) with the start codon in exon 1. Red letters in the gene indicate the position of the missense mutation, which is located in exon 1 of the ABCD1 gene. (B) Sequencing diagram of part of exon 1 in the ABCD1 gene. The arrow indicates the involved nucleotide change. The upper panel is the normal sequence, whereas the lower panel is the mutated sequence. (C) Schematic of the ALDP molecular structure. ALDP contains a TMD (amino acids 75-352) and a nucleotide-binding domain (NBD, also named the ATP-binding region, amino acids 474-700). The red X mark shows the position of the mutation S149R in exon 1 of the ABCD1 gene.\n\nFigure 3: Figure 3. (A) The prediction of the mutation effect by the PolyPhen software program showing a damaging effect of the p.S149R mutation (score: 1.000 with a prediction: probably damaging). (B) 3D-structure of ALDP: left: wild-type ALDP; middle: change of the ALDP structure with novel missense mutations: p.S149N in a previous study; right: p.S149R in the present study.\n\nFigure 4: Figure 4. CHO cells were transfected with empty vector, pEGFP/ABCD1 (wild-type), or pEGFP/mutant-ABCD1 (p.S149R), and protein localization was observed by fluorescence microscopy. The ABCD3 proteins localized in the peroxisomes were detected using an anti-human ABCD3 antibody followed by secondary antibodies conjugated with Alexa Fluor 555 (red). The expressed ABCD1 proteins were detected as green fluorescent dots. The wild-type ABCD1 was localized to peroxisomes, but the mutant ABCD1 was diffuse in the cytosol. Original magnification: 600×."
      }
    ]
  },
  {
    "id": "PMC5679159_multi",
    "image": [
      "images/PMC5679159-f1.png",
      "images/PMC5679159-f2.png",
      "images/PMC5679159-f3.png",
      "images/PMC5679159-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Tumor necrosis factor-like weak inducer of apoptosis regulates quadriceps muscle atrophy and fiber-type alteration in a rat model of chronic obstructive pulmonary disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Evaluation of COPD rat model. a Weight change of healthy control and COPD groups over the 90-day test period. At 30, 60 and 90 days, the weights of COPD rats were significantly lower than that of controls. n = 10, *P < 0.05,versus the control group. b Rat lung function. The PEF, FEV0.3 and FEV0.3/FVC values of COPD rats were also significantly reduced compared with controls. n = 10, *P < 0.05,versus the control group. c-f Hematoxylin and eosin staining of rat lung tissue (magnification, ×100). c and d The lung tissue of control rats exhibited thin alveolar septa, normal alveoli and no inflammatory cell infiltration. e and f The lungs of COPD rats exhibited damaged alveolar septa, alveolar enlargement and inflammatory cell infiltration (indicated by black arrows). *P < 0.05. COPD, chronic obstructive pulmonary disorder; PEF, peak expiratory flow; FVC, forced vital capacity; FEV0.3, forced expiratory volume at 0.3 s\n\nFigure 2: Figure 2. Alterations in the weight, cross-sectional area and fiber-type of the quadriceps in rats with COPD. Relative to controls, the a weight and b muscle fiber cross-sectional area and nuclear cell number of the quadriceps muscle in COPD rats were significantly reduced. n = 10, *P < 0.05,versus the control group. c Hematoxylin and eosin staining of quadriceps samples from the control group identified neat and tight muscle fibers, a narrow gap between adjacent muscle fibers, normal structures, a normal nucleus number and an even distribution (magnification, ×200). d Hematoxylin and eosin staining of quadriceps samples from the COPD group identified muscle fiber atrophy, disordered fiber arrangement, a wide gap between adjacent muscle fibers, a reduced number of nuclei and an uneven distribution of fiber sizes (indicated by black arrows; magnification, ×200) e ATPase histochemical staining (calcium-cobalt method) of quadriceps samples from the control group (magnification, ×100). Following staining, type I muscle fibers appear lighter in color than type II fibers. Control samples exhibited a larger proportion of type I muscle fibers. f ATPase histochemical staining of quadriceps samples from the COPD group (magnification, ×100). Type II fibers comprised a larger proportion of the total fibers in COPD samples (indicated by red arrows). g Quantification of muscle fiber proportions. Type I fibers were significantly decreased and type II fibers were significantly increased in the COPD group. n = 10, *P < 0.05,versus the control group. COPD, chronic obstructive pulmonary disease\n\nFigure 3: Figure 3. Correlation of TWEAK expression with quadriceps weight and fiber type. Immunohistochemical staining of TWEAK expression in the quadriceps muscle of a control and b COPD model rats. Markedly increased TWEAK expression was observed in the COPD group. TWEAK was concentrated to the membrane of the skeletal muscle cells (brown stain, black arrows; magnification, ×100). c Western blot analysis of TWEAK expression. Lanes 1–3 represent the control group and lanes 4–9 represent the COPD group. Levels of TWEAK expression were significant higher in COPD samples. n = 6, *P < 0.05,versus the control group. d Correlation between TWEAK expression and quadriceps muscle weight. e Correlation between TWEAK expression and type I fiber proportion. f Correlation between TWEAK and type II fiber proportion. TWEAK expression was significantly proportional (* P < 0.05) to the type II fiber ratio while being significantly inversely proportional to the weight and type I fiber proportion of the quadriceps (* P < 0.05). TWEAK, tumor necrosis factor-like weak inducer of apoptosis; COPD, chronic obstructive pulmonary disease\n\nFigure 4: Figure 4. Expression of NF-κB, MuRF1 and PGC-1α in the quadriceps of COPD rats. a Immunohistochemical staining of NF-κB, MuRF1 and PGC-1α in quadriceps samples from control and COPD model rats (NF-κB magnification, ×100, MuRF1 and PGC-1α magnification, ×200). Samples from COPD rats exhibited higher levels of NF-κB and MurF1 and lower levels of PGC-1α, relative to controls. All three factors were localized to the membranes of skeletal muscle cells (black arrows). Subsequent western blot analysis indicated that the changes in b NF-κB, c MuRF1 and d PGC-1α protein expression were significant. Lanes 1–3 represent the control group and lanes 4–9 represent the COPD group. n = 6, *P < 0.05,versus the control group. COPD, chronic obstructive pulmonary disease; NF-κB, nuclear factor-κB; MuRF1, muscle ring finger-1; PGC-lα, peroxisome proliferator-activated receptor-γ coactivator-lα"
      }
    ]
  },
  {
    "id": "PMC5691142_multi",
    "image": [
      "images/PMC5691142-f1.png",
      "images/PMC5691142-f2.png",
      "images/PMC5691142-f3.png",
      "images/PMC5691142-f4.png",
      "images/PMC5691142-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Excessive glucocorticoid-induced muscle MuRF1 overexpression is independent of Akt/FoXO1 pathway\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The effect of DEX treatment (100 µM for 3, 8, 12, and 24 h) on atrogin-1 (A, C) and MuRF1 (B, D) expressions in C2C12 cells. Results are presented as the mean ± S.E.M. (n≥4); control and DEX treatments were compared at each time point, and means with * are significantly different (P<0.05).\n\nFigure 2: Figure 2. The effect of DEX treatment (100 µM for 8 h) on mRNA expressions of FoXO1, FoXO3, MuRF1, and atrogin-1 (A), protein expressions of p-FoXO1/3a (B), MuRF1, atrogin-1 (C), p-mTOR and p-Akt (D) in C2C12 cells. Results are presented as the mean ± S.E.M. (n≥5); control and DEX treatments were compared for each gene, and means with * are significantly different (P<0.05).\n\nFigure 3: Figure 3. The effect of DEX (100 µM for 8 h) and EPOX (1.5 μM for 5 h) on protein expressions of MuRF1 (A) and atrogin-1 (B) in C2C12 cells. Results are presented as the mean ± S.E.M. (n≥3); four groups were compared for each gene, and means without a common letter are significantly different (P<0.05).\n\nFigure 4: Figure 4. The effect of DEX (100 µM for 8 h) and RU486 (10 μM for 5 h) on protein expressions of p-FoXO1/3a (A), MuRF1 and atrogin-1 (B) in C2C12 cells. Results are presented as the mean ± S.E.M. (n≥3); four groups were compared for each gene, and means without a common letter are significantly different (P<0.05).\n\nFigure 5: Figure 5. The effect of DEX (100 µM for 8 h) and LY294002 (10 μM for 5 h) on protein expressions of p-FoXO1/3a (A) and MuRF1 (B) in C2C12 cells. Results are presented as the mean ± S.E.M. (n≥3); four groups were compared for each gene, and means without a common letter are significantly different (P<0.05)."
      }
    ]
  },
  {
    "id": "PMC5691142_multi_2",
    "image": [
      "images/PMC5691142-f6.png",
      "images/PMC5691142-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Excessive glucocorticoid-induced muscle MuRF1 overexpression is independent of Akt/FoXO1 pathway\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The effect of DEX (100 µM for 8 h) and RAPA (25 μM for 5 h) on protein expressions of p-FoXO1/3a (A), MuRF1 and atrogin-1 (B) in C2C12 cells. Results are presented as the mean ± S.E.M. (n≥3); four groups were compared for each gene, and means without a common letter are significantly different (P<0.05).\n\nFigure 7: Figure 7. (↑ increase; ↓ decrease; gray blocks represent unaffected proteins; solid arrows represent findings in this study and dashed arrows represent findings reported previously [23–25,38,39]). Excessive GCs stimulated protein degradation through MuRF1, but not atrogin-1. Other pathway that is independent of Akt/FoXO1 pathway may account for the excessive GC-induced MuRF1 activation. There is a cross-talk between anabolic regulator mTOR and catabolic regulator FoXO1-MuRF1."
      }
    ]
  },
  {
    "id": "PMC5725694_multi",
    "image": [
      "images/PMC5725694-f1.png",
      "images/PMC5725694-f2.png",
      "images/PMC5725694-f3.png",
      "images/PMC5725694-f4.png",
      "images/PMC5725694-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Reduced muscle strength in ether lipid‐deficient mice is accompanied by altered development and function of the neuromuscular junction\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Overview of the peroxisomal contribution to ether lipid biosynthesis. Dihydroxyacetone phosphate O‐acyltransferase (DHAPAT; bold circle), encoded by the Gnpat gene, catalyzes the first step in the pathway. After export of the precursor (alkyl‐DHAP) from the peroxisome, residual biosynthesis steps take place elsewhere, in case of plasmalogens at the endoplasmic reticulum. AADHAPR, acyl/alkyl‐dihydroxyacetone phosphate reductase; ADHAPS, alkyl‐dihydroxyacetone phosphate synthase; AHGP, 1‐alkyl‐2‐hydroxy‐glycerophosphate; DHAP, dihydroxyacetone phosphate; FAR, fatty acyl‐CoA reductase; GPI, glycosyl‐phosphatidyl‐inositol; PAF, platelet‐activating factor.\n\nFigure 2: Figure 2. Absence of plasmalogens from muscle tissue of Gnpat KO mice. Plasmalogen levels were determined by detecting dimethylacetals (DMA) after acidic methanolysis and normalizing them to their corresponding fatty acid methyl esters (FAME). Neither C16:0 (a) nor C18:0 (b) DMA were detected in muscle tissue of Gnpat KO mice (WT, n = 4; Gnpat KO, n = 3). n.d., not detected\n\nFigure 3: Figure 3. Motor impairment in ether lipid‐deficient mice. (a) Kaplan–Meier plots indicating survival functions of male (WT: n = 315, Gnpat KO: n = 244) and female (WT: n = 278, Gnpat KO: n = 203) mice. Note that some KO pups may have died before their birth was recorded. Statistical analysis using log‐rank tests revealed highly significant differences between the genotypes (p < 0.001 for males, females or both sexes combined) but not between sexes, although the longest‐living animals were females (see inset). (b) In the accelerating rotarod test (maximal time 500 s), the latency to fall was recorded in adult WT (n = 26) and Gnpat KO (n = 27) mice. *p < 0.05 (Mann–Whitney U‐test). (c) Scores obtained by the same cohort as in (b) in the balance beam test are depicted as the number of animals per genotype reaching a certain score (defined in Table S1); the better the performance, the lower the score. Statistical analysis using Mann–Whitney U‐test revealed a highly significant difference between the genotypes (p < 0.001). (d) For the inverted screen task, the mean latency to fall was recorded for adult WT (n = 30) and Gnpat KO (n = 31) mice. n.s., not significant (Mann–Whitney U‐test) (e) Cumulative scores (time × weight coefficient) obtained in the weights test are depicted for the same cohorts as in (d). ***p < 0.001 (Mann–Whitney U‐test). Box‐and‐whisker plots in (b), (d), and (e) are drawn according to Tukey's method with the horizontal, bold line indicating the median value.\n\nFigure 4: Figure 4. Wider area of nervous innervation and exaggerated phrenic nerve branching in ether lipid‐deficient diaphragm muscle. Whole mounts of diaphragms from WT and Gnpat KO fetuses were stained by indirect immunofluorescence with a mixture of antibodies specific for neurofilament M and synaptophysin and the area covered by neurons was quantified at E14.5 (WT, n = 4; Gnpat KO, n = 5) (a), E16.5 (WT, n = 4; Gnpat KO, n = 5) (b), and E18.5 (WT, n = 5; Gnpat KO, n = 8) (c). In Gnpat KO diaphragms, extensive branching of the main axons (white arrows) and excessive growth beyond the main axon (red arrows) are notable. For the mode of quantification, see Supporting Information. Bar charts to the right show the summary statistics (means ± SD) of genotype comparisons for each developmental time point. **p < 0.01, *p < 0.05 (two‐tailed Student's t‐test); scale bars = 250 μm (in each micrograph).\n\nFigure 5: Figure 5. Impaired acetylcholine receptor (AChR) clustering in vitro in Gnpat KO myotubes. Clustering of AChRs was induced by stimulation with neural agrin in myotubes derived from immortalized myoblasts from WT and Gnpat KO mice. AChRs were stained with Alexa Fluor 594‐conjugated α‐BTX and representative images of clusters (indicated by arrows) are shown in (a) for both genotypes; scale bar: 10 μm. Quantifications of cluster number (b) and area (c), both normalized to myotube area, as well as the Feret diameter of clusters (d) and the size of myotubes (e) are presented as means ± SD (n = 5 experiments/genotype involving a total of > 225 clusters/genotype derived from one WT and two KO cell lines). ***p < 0.001, **p < 0.01, *p < 0.05 (two‐tailed Student's t‐test)."
      }
    ]
  },
  {
    "id": "PMC5725694_multi_2",
    "image": [
      "images/PMC5725694-f6.png",
      "images/PMC5725694-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Reduced muscle strength in ether lipid‐deficient mice is accompanied by altered development and function of the neuromuscular junction\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Normal acetylcholine receptor (AChR) stability in ether lipid‐deficient mice as indicated by in vivo radioligand binding. Adult WT (n = 4 limbs derived from two mice) and Gnpat KO (n = 6 limbs derived from three mice) mice were injected intramuscularly (tibialis anterior muscle) with radioactively labeled α‐BTX and the loss of radioactivity was monitored over 24 days. Data are presented as means (circles) ± SEM and the curves were fitted as described previously (Strack et al. 2011). Statistical analysis using two‐tailed Student's t‐tests did not reveal significant differences at any time point. Thus, no correction for the repeated measurements was performed.\n\nFigure 7: Figure 7. Increased amplitude and strongly reduced frequency of mEPPs but normal evoked potentials at diaphragm muscles of Gnpat KO mice. Miniature end plate potentials (mEPPs), reflecting spontaneous vesicle fusion, were recorded from diaphragms of adult WT (left panel) and Gnpat KO (right panel) mice; representative traces for each genotype are shown in (a). The mEPP amplitude (b), mEPP frequency (c), and input resistance (d) (b–d: WT, n = 7 mice, 88 fibers total; Gnpat KO, n = 7 mice, 118 fibers total) as well as the amplitude of end plate potentials (EPPs) in response to 1 Hz pulses (WT, n = 5 mice, 50 fibers total; Gnpat KO, n = 7 mice, 86 fibers total) (e) and quantal content (the ratio between end plate currents (EPC) and mEPC; WT, n = 5 mice, 43 fibers total; Gnpat KO, n = 7 mice, 86 fibers total) (f) are presented as means ± SEM. ***p < 0.001, **p < 0.01, *p < 0.05, n.s., not significant (two‐tailed Student's t‐test)."
      }
    ]
  },
  {
    "id": "PMC5737649_multi",
    "image": [
      "images/PMC5737649-f1.png",
      "images/PMC5737649-f2.png",
      "images/PMC5737649-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Genomic and Proteomic Evidence for the Presence of a Peroxisome in the Apicomplexan Parasite Toxoplasma gondii and Other Coccidia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. —Putative central peroxin factors for PTS1- and PTS2-mediated peroxisomal matrix protein import in Toxoplasma gondii. Pex5, Pex7, and Pex14 possess all the required motifs for proper function/interaction during peroxisomal matrix protein import. Numbers indicate amino acid positions of the individual primary sequences. Cys: cysteine; N-t motif: conserved N-terminal motif of Pex5; FxxxW and WxxxF/Y: motifs for interaction of Pex5 with Pex13 and Pex14; Pex7-binding domain: motif known to be crucial for interaction of the co-receptor Pex5 with the PTS2 receptor Pex7; TPR: tetratricopeptide repeat, protein–protein interaction motif; WD40: protein–protein interaction motif; Pex14_N: N-terminal domain of Pex14 known to be required for interaction with the PTS1 receptor Pex5; PxxP: potential Pex13 binding motif of Pex14; PUB: PNGase/UBA or UBX domain.\n\nFigure 2: Figure 2. —Model of the Toxoplasma gondii peroxisome. The hypothetical peroxisome of T. gondii consists of a biogenesis/division/maintenance system that is also responsible for matrix protein import (peroxins, Pex, see numbers). The β-oxidation of fatty acids takes place inside the peroxisomal lumen (matrix), mainly during the oocyst life cycle stage of the parasite. Fatty acids might be imported into the peroxisome via an ABC class D transporter (ABC-D) and activated by FACS. Unsaturated fatty acids are converted by the accessory enzymes DECR and ECI to suitable substrates to be channeled into the β-oxidation cycle, which is catalyzed by ACOX, ECH, 3HCDH, and 3KCT. Hydrogen peroxide (H2O2) generated as a consequence of the ACOX reaction, is neutralized by the peroxisomal CAT. Acetyl-CoA, the end product of the fatty acid β-oxidation, finally may be transported to the mitochondria for energy production via the TCA-cycle, maybe after conversion by a putative PTS2-targeted peroxisomal CS into citrate, whereas acyl-CoA shortened by 2 C-atoms (n-2C) can be further oxidized in another round of β-oxidation in the peroxisome (or mitochondrion). VLC: very long chain; FACS: fatty acyl-CoA synthetase; ACOX: acyl-CoA oxidase; ECH: enoyl-CoA hydratase; 3HCDH: (3R)-hydroxyacyl-CoA dehydrogenase; ECI: enoyl-CoA isomerase; DECR: 2, 4-dienoyl-CoA reductase; 3KCT: 3-ketoacyl-CoA thiolase; CAT: catalase; CS: citrate synthase; PTS1/2: peroxisomal targeting signal of type 1 or 2; Mito.: mitochondrion. Numbers in the figure correspond to the individual peroxins (Pex). See supplementary table S2, Supplementary Material online, for protein identification numbers.\n\nFigure 3: Figure 3. —Multiple losses of putative peroxisomes in apicomplexans. The schematic tree depicts the potential evolutionary history of peroxisomes in chromerids and apicomplexans. Group names on branches specifically refer to the individual species listed besides/below, that is, those analyzed in this study. The presence of peroxisomes (indicated by blue letters) is hypothetical, that is, mainly based on bioinformatic results, and requires experimental verification. A green line/branch indicates that a photosynthetic plastid is present in these organisms, whereas a green asterisk denotes loss of photosynthesis, which is not necessarily accompanied by a loss of the plastid/apicoplast. Red lines/branches represent groups of apicomplexans probably devoid of peroxisomes, with a red asterisk indicating loss of putative peroxisomes in addition to a loss of β-oxidation enzymes in these organisms. Coccidians are the only apicomplexans for which bioinformatic and proteomic evidence for the presence of peroxisomes exists. All other non-coccidian apicomplexans seem to lack these organelles, but have retained two proteins possessing sequence similarity to the peroxisomal factors Pex4 and Pex22. Piroplasms, such as Theileria and Babesia, group together with the haemosporidians and were not included into the figure, but according to Gabaldon and colleagues, just as Plasmodium spp. these organisms are devoid of specific peroxisomal markers and thus peroxisomes (Gabaldon et al. 2016). The tree architecture is based on recently published phylogenies of apicomplexans and their sister groups (Arisue and Hashimoto 2015; Simdyanov et al. 2017)."
      }
    ]
  },
  {
    "id": "PMC5752207_multi",
    "image": [
      "images/PMC5752207-f1.png",
      "images/PMC5752207-f1-2.png",
      "images/PMC5752207-f1-3.png",
      "images/PMC5752207-f2.png",
      "images/PMC5752207-f2-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"LRP1 regulates peroxisome biogenesis and cholesterol homeostasis in oligodendrocytes and is required for proper CNS myelin development and repair\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (a) Timeline in weeks indicating when Lrp1 ablation was induced (Lrp1flox/flox;CAG-CreERTM, Lrp1 iKO), lysolecithin (LPC) injected, and animals sacrificed. (b) Cartoon showing unilateral injection of LPC in the corpus callosum (CC) and PBS into the contralateral side. Coronal brain sections (series of 6, each 120 µm apart) probed for Mbp by in situ hybridization (ISH). Brain sections containing the lesion center were identified and subjected to quantification. (c) Coronal brain sections through the CC 21 days post LPC injection (21 DPI). The outer rim of the lesion area (lesionout) is demarcated by the elevated Mbp signal (white dashed line). The non-myelinated area of the lesion is defined by the inner rim of elevated Mbp signal (lesionin) and delineated by a solid yellow line. Scale bar = 200 µm. (d) Quantification of the initial lesion size (lesionout) in Lrp1 control (n = 8) and iKO (n = 6) mice. (e) Quantification of white matter repair in Lrp1 control (n = 8) and iKO (n = 6) mice. The extent of repair was calculated as the percentile of (lesionout - lesionint)/(lesionout) x 100. (f) Timeline in weeks showing when OL-lineage-specific Lrp1 ablation (Lrp1flox/flox;Pdgfra-CreERTM, Lrp1 iKOOL) was induced, LPC injected, and animals sacrificed. (g) Coronal brain sections through the CC at 21 days post LPC injection of Lrp1 control and iKOOL mice. The initial lesion area is demarcated by a white dashed-line. A solid yellow line delineates the non-myelinated area. Scale bar = 200 µm. (h) Quantification of the initial lesion size in Lrp1 control (n = 4) and iKOOL (n = 4) mice. (i) Quantification of white matter repair in Lrp1 control (n = 4) and iKOOL (n = 4) mice. Results are shown as mean ±SEM, *p<0.05, **p<0.01, and ***p<0.001, Student’s t-test. For a detailed statistical report, see Figure 1—source data 1. 10.7554/eLife.30498.005Figure 1—source data 1.Raw data and detail statistical analysis report.\n\nFigure 1: Figure 1. (a) Lrp1 wildtype (wt) and conditional, LoxP flanked (floxed), alleles. The location of PCR primers used for genotyping, the neomycin cassette (Neo), and LoxP sites are shown. (b) For global inducible gene ablation, the CAG-CreERTM mouse line was used, in which the Cre recombinase is fused with a tamoxifen (TM)-responsive estrogen receptor (Ers1) and expressed under the control of a ubiquitous chicken β-actin-CMV hybrid (CAG) promoter. (c) Following TM administration, recombination can lead to deletion of Neo only or deletion of Neo and exon 1. (d) PCR genotyping of brain genomic DNA. Analysis of PCR products amplified from of Lrp1+/+ mice with (+) or without (-) the cre allele; Lrp1flox/+ mice ± Cre allele and ±TM treatment; Lrp1flox/flox mice ± Cre allele and ±TM treatment. The F1/R1 primer pair amplifies a ~300 bp PCR product from the wt Lrp1 allele and a ~400 bp PCR product if the Neo cassette is deleted. The F2/R2 primer pair amplifies a 291 bp PCR product from wt Lrp1 allele and a 350 bp PCR product from Lrp1 flox allele. The F1/R2 primer pair amplifies a ~500 bp PCR product if exon1 in deleted. The IL-2pF/IL-2pR primer pair amplifies a 324 bp fragment and served as internal PCR quality control. The CreF/CreR primer pair amplifies a ~200 bp PCR product if Cre is present. (e) Immunoblots of whole brain lysates prepared from Lrp1flox/flox;CAG-CreERTM mice 31 and 52 days after TM (+) or vehicle (-) treatment. Representative blots probed with anti-LRP1β, anti-GFAP, anti-β-actin, anti-β-III tubulin, and anti-GAPDH. (f) Coronal-sections of adult Lrp1 control and iKO mice 31 days after i.p. TM administration. Sections were stained with FM Green or probed for Mpb mRNA by in situ hybridization. Scale bar = 1 mm.\n\nFigure 1: Figure 1. (a) Coronal forebrain sections of adult Lrp1 control (naive) mice and mice subjected to stereotaxic injection of PBS into the corpus callosum. At 10 days post injection (10 DPI) and 21 DPI of PBS, brains were collected, serially sectioned, and stained with FM Green, anti-GFAP and Hoechst dye33342. The white dotted lines demarcate the corpus callosum. The injection site is readily identified by the elevated GFAP immunoreactivity. (b) Coronal forebrain sections of Lrp1 control and iKO mice at 10 DPI and 21 DPI of LPC stained with FM Green, anti-GFAP, and Hoechst dye33342. White dotted lines demarcate the corpus callosum. The white matter lesion is identified by the absence of FM Green labeling. Scale bar = 200 µm. (c) Serial coronal-sections of adult brain after PBS and LPC injection in the corpus callosum, probed for Pdgfra, Plp1, Mag, and Mbp mRNA expression to identify the lesion area and to examine gene expression changes in the OL lineage. The site injected with PBS is marked by an arrowhead and the LPC injection site is marked by an arrow. The lesion boarder shows elevated staining for Plp1, Mag and Mbp. Scale bar = 200 µm. (d) Serial brain sections of adult Lrp1 control mice injected with LPC at 21 DPI. Serial sections through the lesion area (120 µm apart) were probed for Mag, Plp1, and Pdgfra, mRNA expression. Scale bar = 200 µm. (e) Coronal brain sections through the CC including the lesion center of Lrp1 control and Lrp1 iKO mice injected with LPC at 21 DPI. Serial sections were probed for Pdgfra, Plp1, and Mag mRNA expression. Scale bar = 200 µm.\n\nFigure 2: Figure 2. (a) Ultrastructural images of optic nerve cross-sections from P10, P21, and P56 control and Lrp1flox/flox;Olig2-Cre conditional knockout mice (Lrp1 cKOOL). Scale bar = 1 µm. (b) Quantification of myelinated axons in the optic nerve of Lrp1 control and cKOOL mice at P10, P21 and P56 (n = 4 mice per genotype for each three time point). (c) Averaged g-ratio of Lrp1 control and cKOOL optic nerve fibers from four mice per genotype for each of the three time points. At P10, n = 488 myelinated axons for control and n = 261 for cKOOL; at P21, n = 1015 for control and n = 997 for cKOOL; at P56, n = 1481 for control and n = 1020 for cKOOL mice. (d) Nodes of Ranvier in P21 optic nerves of Lrp1 control and cKOOL mice were labeled by anti-PanNaCh (green, node) and anti-Caspr (red, paranode) staining. Scale bar = 1 µm. (e) Nodal defects detected include elongated node, heminode, and missing node (Na+ channels absent). (f) Representative nodal staining categorized by axon diameter. (g) Quantification of nodal density in P21 Lrp1 control (n = 6) and cKOOL (n = 5) optic nerves. (h) Quantification of abnormal nodes of Ranvier in Lrp1 control (n = 6) and cKOOL (n = 5) optic nerves. (i) Quantification of nodes associated with large (>1 μm), intermediate (0.5–1 μm), and small caliber fibers (<0.5 μm) in Lrp1 control (n = 6) and cKOOL (n = 5) optic nerves. Results are shown as mean ±SEM, *p<0.05, **p<0.01, and ***p<0.001, Student’s t-test. For a detailed statistical report, see Figure 2—source data 1. 10.7554/eLife.30498.009Figure 2—source data 1.Raw data and detail statistical analysis report.\n\nFigure 2: Figure 2. (a) Lrp1flox/flox mice were crossed with Olig2-Cre mice to conditionally ablate Lrp1 in OL lineage (cKOOL). (b) To ensure that the presence of the Olig2-Cre allele does not lead to altered expression of myelin-associated proteins or LRP1, P21 brains of Lrp1flox/+ and Lrp1flox/+;Olig2-Cre mice were lysed and subjected to SDS-PAGE. Representative Western blots probed with anti-LRP1β, anti-MAG, anti-CNP, anti-MBP, and anti-β-actin are shown. (c) Quantification of protein levels detected by Western blotting of Lrp1flox/+ (n = 3) and Lrp1flox/+;Olig2-Cre (n = 3) brain lysates revealed no differences in the presence or absence of the Olig2-Cre allele. (d) Immunoblotting of whole brain lysates prepared from P10, P21, and P56 of Lrp1 control (Ctrl) and cKOOL mice. Representative blots probed with anti-LRP1β and anti-β-Actin. (e) Average g-ratio of myelinated optic nerve axons of Lrp1 control and cKOOL mice, n = 4 mice per genotype for each of the three time points. (f, i, and l) Graphs show the percentage of myelinated axons in the optic nerve at P10, P21 and P56 as a function of axon caliber in Lrp1 control (n = 4 for each time point) and cKOOL (n = 4 for each time point) mice. Axon calibers were binned into nine groups of 0.2 μm intervals, ranging from 0.1 to 1.7 μm. (g, j, and m) Scatter plot showing the distribution of g ratios for individual fibers in the optic nerve at P10, P21, and P56 of Lrp1 control and cKOOL mice. P10, n = 488 axons from Lrp1 control mice and n = 261 axons from cKOOL mice; P21, n = 1015 axons from Lrp1 control mice and n = 997 axons from 4 cKOOL mice; P56, n = 1481 axons from Lrp1 control mice and n = 1020 axons from 4 cKOOL mice. (h, k, and n) Morphometric assessment of axon caliber distribution in P10, P21, and P56 optic nerves of Lrp1 control (n = 4) and cKOOL (n = 4) mice. Measurements of axon diameter were made from electron microscopy images. (o) Immunoblotting of whole brain lysates prepared from P56 Lrp1 control (Ctrl) and cKOOL mice. Representative blots probed with anti-LRP1β, anti-CNP, anti-MAG, anti-MBP, anti-β-III tubulin, anti-GFAP, and anti-β-actin. (p) Quantification of protein levels detected by Western blotting of Lrp1 control (n = 3) and cKOOL (n = 3) brain lysates. (q) Electron microscopy images of optic nerve cross- and longitudinal-sections acquired from P21 Lrp1 control and cKOOL mice. Axons that are >1 μm in diameter are colored in light blue. Scale bar = 1 μm. (r) Quantification of axon density in the P21 optic nerve for Lrp1 control (n = 4) and cKOOL (n = 4) mice. (s) Quantification of optic nerve axons smaller than <0.5 µm, between 0.5–1.0 µm and larger than 1 µm in Lrp1 control (n = 4) and cKOOL (n = 4) mice. Results are presented as the mean ±SEM, *p<0.05, **p<0.01, and ***p<0.001, Student’s t-test. For a detailed statistical report, see Figure 2—source data 1."
      }
    ]
  },
  {
    "id": "PMC5752207_multi_2",
    "image": [
      "images/PMC5752207-f2-3.png",
      "images/PMC5752207-f3.png",
      "images/PMC5752207-f3-2.png",
      "images/PMC5752207-f4.png",
      "images/PMC5752207-f4-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"LRP1 regulates peroxisome biogenesis and cholesterol homeostasis in oligodendrocytes and is required for proper CNS myelin development and repair\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. (a) Scheme depicting the orientation of an optic nerve prepared for compound action potential (CAP) recordings. Positions of the stimulating electrode, the recording electrode, and artifact subtraction electrode are shown. (b) Left: representative raw CAP traces of P21 optic nerves. Right: For each recording, traces were fitted with four Gaussians representing peak 1 (red), peak 2 (green), peak 3 (blue), peak 4 (cyan), and the sum of the four peaks (magenta). (c) The distribution of peak populations in Lrp1 control and cKOOL mice. (d) Quantification of amplitudes (mV) of peaks 1, 2, 3, and 4 in Lrp1 control and cKOOL optic nerves. (e) Quantification of conduction velocities (m/sec) of peaks 1, 2, 3, and 4 in Lrp1 control and cKOOL optic nerves. (f) Reconstituted averaged peaks 1–4 amplitude as a function of time. Lrp1 control (n = 21 nerves/14 mice) and cKOOL (n = 9 nerves/7 mice). Results are presented as the mean ±SEM, *p<0.05, **p<0.01, and ***p<0.001, Student’s t-test. For a detailed statistical report, see Figure 2—source data 1.\n\nFigure 3: Figure 3. (a) Cross-sections of Lrp1 control and cKOOL optic nerves stained with anti-PDGFRα (OPC marker), anti-Olig2 (pan-OL marker), anti-CC1 (mature OL marker), and Hoechst dye33342. Scale bar = 100 µm. (b) Cross- and -longitudinal sections of Lrp1 control and cKOOL optic nerves probed for Pdgfra, Mag, and Plp mRNA expression. Scale bar = 100 µm. (c) Quantification of labeled cells per nerve cross-section. Anti-PDGFRα in control (n = 8) and cKOOL (n = 6) mice; anti-Olig2 and anti-CC1 in control (n = 11) and cKOOL (n = 12) mice. (d) Quantification of labeled cells per nerve cross-section. Pdgfra, control (n = 8) and cKOOL (n = 6) mice; Mag, control (n = 11) and cKOOL (n = 11) mice; Plp, control (n = 11) and cKOOL (n = 10) mice. (e) Workflow for OPC isolation and culturing with timeline when growth medium (GM) or differentiation medium (DM) was added and cells were harvested. (f) OPC/OL cultures after 3 days in DM stained with anti-NG2 (premyelinating marker), anti-CNP (differentiating OL marker), and Hoechst dye33342. Scale bar = 100 µm. (g) Immunoblot of OL lysates prepared from Lrp1 control and cKOOL cultures after 3 days in DM probed with anti-LRP1β and anti-β-actin. (h) Quantification of NG2+ (n = 3) and CNP+ (n = 3) cells in Lrp1 control and cKOOL cultures. (i) Control and Lrp1 deficient OL cultures after 5 days in DM stained with anti-MAG, anti-PLP, and anti-MBP. Scale bar = 100 µm. (j) Immunoblotting of OL lysates prepared from Lrp1 control and cKOOL cultures after 5 days in DM probed with anti-LRP1β, anti-CNP, anti-MAG, anti-PLP, anti-MBP, and anti-β-actin. (k) Quantification of MAG+, PLP+, and MBP+ cells in Lrp1 control (n = 3) and cKOOL (n = 3) cultures. (l) Quantification of protein levels in OL lysates detected by immunoblotting. Anti-LRP1, CNP, and PLP, n = 3 per condition; anti-MAG, n = 4 per condition; anti-MBP n = 5 per condition. Results are shown as mean values ± SEM, *p<0.05, **p<0.01, and ***p<0.001, Student’s t-test. For a detailed statistical report, see Figure 3—source data 1. 10.7554/eLife.30498.012Figure 3—source data 1.Raw data and detail statistical analysis report.\n\nFigure 3: Figure 3. (a) Quantification of optic nerve diameter in Lrp1 control (n = 5) and cKO (n = 5) mice. (b) To ensure that the presence of the Olig2-Cre allele does not lead to altered expression of myelin-associated proteins or LRP1, in primary OPCs/OLs prepared from Lrp1flox/+ or Lrp1flox/+;Olig2-Cre pups, cells were lysed and subjected to Western blot analysis. OPCs/OLs were cultured for 5 days in differentiation medium (DM). Cell lysates were separated by SDS-PAGE and protein blots probed with anti-LRP1β, anti-CNP, anti-MAG, anti-PLP and anti-β-actin. Equal amounts of total protein were loaded per lane. (c) Quantification of LRP1, MAG, and PLP protein levels detected by immunoblotting of Lrp1flox/+ and Lrp1flox/+;Olig2-Cre OPC/OL culture lysates (n = 3 per genotype) revealed no differences in the presence or absence of the Olig2-cre allele. (d) Timeline in days indicating when growth medium (GM) was added to cells and when cells were harvested (H) to assess proliferation. (e) OPC/OL culture after 1 or 2 days in GM stained with anti-Ki67 (proliferation marker) and Hoechst dye33342. Scale bar = 100 µm. (f) Quantification of cell proliferation in OPC/OL cultures prepared from Lrp1 control and cKOOL mice. The percentile of Ki67+/Hoechst+ cells was calculated on day 1 for Lrp1 control (n = 5) and cKOOL (n = 5) cultures and on day 2 for Lrp1 control (n = 4) and cKOOL (n = 4) cultures. (g) Immunoblots of cell lysates prepared from Lrp1 control and cKOOL OPC/OL cultures after 3 days in differentiation medium (DM). Blots were probed with anti-LRP1β, anti-CNP, anti-MAG, anti-PLP, and anti-β-actin. (h) Immunoblots of lysates prepared from Lrp1 control and cKOOL OPC/OL cultures after 3 days in DM. Representative blots were probed with anti-pAKT (S473), anti-AKT, anti-pERK (1/2), anti-ERK (1/2), and anti-GAPDH. (i) Quantification of protein levels detected by immunoblotting of Lrp1 control and cKOOL cell culture lysate. Anti-LRP1β (n = 3), anti-MAG (n = 3), anti-CNP (n = 4) and anti-PLP (n = 4) per genotype. (j) Quantification of protein levels detected by immunoblotting of Lrp1 control and cKOOL cell lysates. pAKT/AKT, n = 5 for Lrp1 control and cKOOL cultures; pERK/ERK, n = 3 for Lrp1 control and cKOOL cultures. Results are presented as the mean ±SEM, *p<0.05, **p<0.01, and ***p<0.001, Student’s t-test. For a detailed statistical report, see Figure 3—source data 1.\n\nFigure 4: Figure 4. (a) OPCs were isolated from P8 brains by anti-PDGFRα immunopanning, sonicated and subjected to measurement of cholesterol (Chol). (b and c) Quantification of free Chol (b) and total Chol (Chol and Chol ester) (c) in OPCs isolated from Lrp1 control (n = 5) and cKOOL (n = 5) mouse pups. (d) Lrp1 control and cKOOL OLs after 5 days in DM stained with filipin and anti-MBP. Scale bar = 10 µm. (e–g) Quantification of OL size in µm2 (e), the intensity of filipin and MBP labeling per cell (f), and the intensity of filipin and MBP staining per µm2 (g). For Lrp1 control and cKOOL OLs, n = 29 cells from three mice in each group. (h) Timeline in days showing when growth medium (GM) or differentiation medium (DM) with (+) or without (-) Chol was added and when cells were harvested. (i and k) Immunoblotting of OL lysates prepared from Lrp1 control and cKOOL cultures after 3 days in DM. Representative blots were probed with anti-LRP1β, anti-SREBP2, anti-β-actin, anti-PLP, anti-MAG, anti-CNP, and anti-GAPDH. (j, l–n) Quantification of SREBP2 (j), PLP (l), MAG (m), and CNP (n) in Lrp1 control and cKOOLcultures ± bath applied Chol. Number of independent immunoblots: anti-PLP and MAG, n = 3 per condition; anti-SREBP2 and anti-CNP, n = 4 per condition. (o) Immunoblotting of OL lysates prepared from Lrp1 control and cKOOL cultures after 5 days in DM ±bath applied Chol. Representative blots were probed with anti-LRP1β, anti-PLP/DM20, and anti-β-actin. (p) Quantification of PLP (n = 4 per condition) in Lrp1 control and cKOOLcultures ± bath applied Chol (q) Immunostaining of OLs after 5 days in DM ±bath applied Chol. Primary OLs stained with anti-MBP and Hoechst dye33342. Scale bar = 100 µm. (r) Quantification showing relative number of MBP+ cells in Lrp1 control and cKOOL cultures (n = 3–5 per condition). Results are shown as mean values ± SEM, *p<0.05, **p<0.01, and ***p<0.001, 2-way ANOVA, post hoc t-test. For a detailed statistical report, see Figure 4—source data 1. 10.7554/eLife.30498.015Figure 4—source data 1.Raw data and detail statistical analysis report.\n\nFigure 4: Figure 4. (a) Primary OPCs were isolated by anti-PDGFRα immunopanning from Lrp1flox/+ and Lrp1flox/+;Olig2-Cre pups and cultured for 3 days in differentiation medium (D3 in DM). Cells were lysed and subjected to immunoblotting with anti-SREBP2 and anti-β-actin. (b) Quantification of SREBP2 protein levels in cell lysates of Lrp1flox/+ (n = 4) and Lrp1flox/+;Olig2-Cre (n = 4) cultures revealed comparable levels. This demonstrates that the presence or absence of the Olig2-Cre allele does not affect SREBP2 levels. (c) Cholesterol biosynthetic pathway and site of action of statins (simvastatin), which function as inhibitors of 3-hydroxy-3methyl-glutaryl-coenzyme A reductase (HMG-CoA), the rate controlling enzyme of the mevalonate pathway. (d) Timeline in days showing when growth medium (GM) and differentiation medium (DM), either containing simvastatin or mevalonate (M/S) were added to cultures and when cells were harvested (H) for immunofluorescence labeling. (e) Immunostaining of control and Lrp1-deficient OL cultures after 5 days in DM treated with vehicle or statin. Cell cultures were labeled with anti-MBP and Hoechst dye33342. Scale bar = 50 µm. (f) Quantification of MBP+ cells in Lrp1 control cultures treated with vehicle (n = 4), Lrp1 control cultures treated with statin (n = 3), Lrp1 cKOOL cultures treated with vehicle (n = 4), and Lrp1 cKOOL cultures treated with statin (n = 3). (g) Immunostaining of control and Lrp1 deficient OL cultures after 5 days in DM treated with vehicle or mevalonate. Cell cultures were labeled with anti-MBP and Hoechst dye33342. Scale bar = 50 µm. (h) Quantification of MBP+ cells in Lrp1 control cultures treated with vehicle (n = 3), Lrp1 control cultures treated with mevalonate (n = 3), Lrp1 cKOOL cultures treated vehicle (n = 3), and Lrp1 cKOOL cultures treated with mevalonate (n = 3). Results are shown as mean values ± SEM, *p<0.05, **p<0.01, and ***p<0.001, 2-way ANOVA, post hoc t-test. For a detailed statistical report, see Figure 4—source data 1."
      }
    ]
  },
  {
    "id": "PMC5752207_multi_3",
    "image": [
      "images/PMC5752207-f5.png",
      "images/PMC5752207-f5-2.png",
      "images/PMC5752207-f6.png",
      "images/PMC5752207-f7.png",
      "images/PMC5752207-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"LRP1 regulates peroxisome biogenesis and cholesterol homeostasis in oligodendrocytes and is required for proper CNS myelin development and repair\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 5: Figure 5. (a) Primary OLs prepared from Lrp1 control and cKOOL OL pups, cultured for 5 days in DM were stained with anti-MBP and anti-PMP70. Scale bar = 10 µm. (b–d) Quantification of PMP70 labeling intensity per cell (b), PMP70+ puncta per cell (c), and scatter plot showing the number of PMP70+ peroxisomes as a function of cell size for MBP+ OLs of Lrp1 control and Lrp1 cKOOL cultures (d). For Lrp1 control OLs, n = 112 cells from three mice. For Lrp1 cKOOL OLs, n = 60 cells from three mice. (e) Representative distribution of PMP70+ puncta of Lrp1 control and cKOOL OL. For quantification, the center of the cell was marked with a red cross. Puncta within a 25 µm radius from the center (dashed circle) were subjected to quantification. (f) Quantification of peroxisome number plotted against the distance from the center of Lrp1 control (n = 113 cells, three mice) and cKOOL (n = 63 cells, three mice) OLs. (g and h) Representative high-magnification views of PMP70+ puncta from areas boxed in panel (a). Scale bar = 1 µm. Results are shown as mean values ± SEM, *p<0.05, **p<0.01, and ***p<0.001, Student’s t-test. For a detailed statistical report, see Figure 5—source data 1. 10.7554/eLife.30498.018Figure 5—source data 1.Raw data and detail statistical analysis report.\n\nFigure 5: Figure 5. Acutely isolated OPCs from Lrp1+/+ and Lrp1flox/flox;Olig2-Cre mouse pups were subjected to microarray analysis. (a) GO structure of biological process module related to peroxisome function. Each box shows the GO term ID, p-value, GO term, and the genes from the input list associated with the GO term. The color of each box shows the level of enrichment for each GO term. Specific GO terms were queried with the Mouse Genome Informatics (MGI) GO browser. p-Values were calculated by Fisher’s exact test. The fold-enrichment was calculated by dividing the ratio of genes that are associated with each GO term from the input list by the ratio of genes that are expected in the database. (b) Quantification of relative expression levels of gene products that are associated with specific GO terms listed in (a). mRNA was prepared from acutely isolated OPCs of Lrp1 controls (n = 4) and cKOOL (n = 4) pups and analyzed with the Affymetrix mouse gene 2.1 ST array. Differentially regulated gene products include Pex2 (peroxisomal biogenesis factor 2), Pex5l (peroxisomal biogenesis factor five like), Hrasls (hRas-like suppressor), Ptgis (prostaglandin I2 synthase), Mavs (Mitochondrial antiviral signaling), and Stard10 (StAR-related lipid transfer protein 10). (c) Immunoblotting of lysates prepared from Lrp1 control and cKOOL OL cultures after 5 days in DM. Representative blots probed with anti-LRP1β, anti-PEX2, and anti-β-actin. (d) Quantification of PEX2 in Lrp1 control (n = 3) and cKOOL (n = 3) cultures. Results are shown as mean values ± SEM, *p<0.05 and **p<0.01, Student’s t-test. For a detailed statistical report, see Figure 5—source data 1.\n\nFigure 6: Figure 6. (a) Timeline in days showing when growth medium (GM) or differentiation medium (DM) with pioglitazone (Pio) were supplied and cells were harvested for analysis. (b) Immunoblots of OL lysates prepared from Lrp1 wildtype cultures after 5 days in DM with (+) or without (-) Pio, probed with anti-LRP1β. Anti-β-actin is shown as loading control. (c) Immunostaining of Lrp1 control and cKOOL cultures after 5 days in DM. Representative cell cultures stained with anti-MBP and Hoechst dye 33342. Scale bar = 50 µm. (d) Quantification of MBP+ cells in Lrp1 control cultures with vehicle (n = 6), Lrp1 control cultures with Pio (n = 6), cKOOL cultures with vehicle (n = 4), and cKOOL cultures with Pio (n = 4). (e–f) Primary OLs probed with anti-MBP and anti-PMP70. Scale bar = 10 µm. (g–i) Quantification of OL size in µm2 (g), the number of PMP70+ puncta (h), and the intensity of MBP staining per cell (i). (j) Distribution of peroxisomes as a function of distance from the cell center in Lrp1 control and cKOOL OLs treated ±Pio. The number of PMP70+ peroxisomes between 6–15 µm in Lrp1 control and cKOOL cultures was subjected to statistical analysis in (k). Lrp1 control (n = 112 cells, three mice), Lrp1 control cultures with Pio (n = 180 cells, three mice), cKOOL (n = 60 cells, three mice), and cKOOL cultures with Pio. (n = 110 cells, three mice) (k). (l) Immunostaining of OLs after 5 days in DM ±GW9662, probed with anti-MBP and Hoechst dye33342. Scale bar = 50 µm. (m) Quantification of MBP+ cells under each of the four different conditions (n = 3 per condition). Results are shown as mean values ± SEM, *p<0.05, **p<0.01, and ***p<0.001, 2-way ANOVA, post hoc t-test. For a detailed statistical report, see Figure 6—source data 1. 10.7554/eLife.30498.020Figure 6—source data 1.Raw data and detail statistical analysis report.\n\nFigure 7: Figure 7. (a) Timeline in days showing when growth medium (GM) or differentiation medium (DM) with pioglitazone (Pio) and cholesterol (Chol) was supplied and cells were harvested for analysis. (b) Immunostaining of Lrp1 control and cKOOL cultures after 5 days in DM, probed with anti-MBP and Hoechst dye 33342. Scale bar = 50 µm. (c) Quantification of MBP+ cells in Lrp1 control cultures treated with vehicle (n = 4), Lrp1 control cultures treated with Pio and Chol (n = 3), cKOOL cultures treated with vehicle (n = 4), and cKOOL cultures treated with Pio and Chol (n = 3). (d and e) Primary OLs probed with anti-MBP and anti-PMP70. Scale bar = 10 µm. (f–h) Quantification of OL size in µm2 (f), the number of PMP70+ puncta and (g), the intensity of MBP staining per cell (h). (i) Distribution of peroxisomes as a function of distance from the cell center in Lrp1 control and cKOOL cultures with (+) or without (-) Pio and Chol combo-treatment. The number of PMP70+ peroxisomes between 5–15 µm in Lrp1 control and cKOOL cultures was subjected to statistical analysis in (j). Lrp1 control cultures with vehicle (n = 210 cells, three mice), Lrp1 control cultures treated with Pio and Chol (n = 208 cells, three mice), cKOOL cultures treated wtih vehicle (n = 199 cells, three mice), and cKOOL cultures treated wtih Pio and Chol (n = 190 cells, three mice) (k). Results are shown as mean values ± SEM, *p<0.05, **p<0.01, and ***p<0.001, 2-way ANOVA, post hoc t-test. For a detailed statistical report, see Figure 7—source data 1. 10.7554/eLife.30498.022Figure 7—source data 1.Raw data and detail statistical analysis report.\n\nFigure 8: Figure 8. (a) LRP1 in the OL-lineage is necessary for proper CNS myelin development and the timely repair of a chemically induced focal white matter lesion. In OPCs, Lrp1 deficiency leads to dysregulation of cholesterol homeostasis and impaired peroxisome biogenesis. (b) LRP1 is a key regulator of multiple pathways important for OPC differentiation into mature myelin producing OLs: (I) LRP1 regulates cholesterol homeostatsis; (II) LRP1 regulates peroxisome biogenesis; and (III) the combined treatment of Lrp1 deficient primary OPCs with cholesterol and pioglitazone is sufficient to drive maturation into MBP+ myelin sheet producing OLs."
      }
    ]
  },
  {
    "id": "PMC5792714_multi",
    "image": [
      "images/PMC5792714-f1.png",
      "images/PMC5792714-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Pexophagy: Molecular Mechanisms and Implications for Health and Diseases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisome biogenesis is coordinated by two different pathways, de novo biogenesis and the ‘growth and division’. First, peroxisomes can be formed by peroxisome assembly and maturation of pre-peroxisomal vesicles originated from ER or mitochondria, which contain pre-peroxisomal carriers, including PEX3 and PEX16. Second, peroxisomes can proliferate the numbers by a growth and division progress from existing peroxisomes. PEX11 and Drp1 proteins mediate elongation and fission of the peroxisomes.\n\nFigure 2: Figure 2. Pexophagy is triggered by both stress conditions and peroxisomal dysfunctions. Ubiquitination of PMPs, such as peroxins and PMP70, promotes pexophagy. Both NBR1 and p62 act as autophagy adaptor proteins, which interact with PMPs and sequester target peroxisome into autophagosomes. Under conditions of oxidative stress, the ataxia-telangiectasia mutation activates pexophagy by phosphorylating PEX5, leading to its ubiquitination. Pexophagy may be regulated by an unidentified protein (X)."
      }
    ]
  },
  {
    "id": "PMC5811209_multi",
    "image": [
      "images/PMC5811209-f1.png",
      "images/PMC5811209-f2.png",
      "images/PMC5811209-f2-2.png",
      "images/PMC5811209-f3.png",
      "images/PMC5811209-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Sorting of a multi-subunit ubiquitin ligase complex in the endolysosome system\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) A cartoon model showing two conserved pathways (VPS and AP3) for transporting proteins from Golgi to vacuole. Some VPS cargoes can be recycled from the endosome to Golgi by the retromer complex before reaching the vacuole. EE: early endosome, MVB: multivesicular body. (B) Localization of Ubx3-nG and Vph1-mCh in WT, vps27∆, pep12∆, and apl6∆ strain cells. Scale bar: 2 µm.\n\nFigure 2: Figure 2. (A) A cartoon model showing known Dsc components in budding yeast. (B) A silver staining gel showing that Ypr109W and Yir014W co-immunoprecipitate with Ubx3-Flag, together with other known Dsc components. HC, heavy chain. LC, light chain. (C) 014W-Flag can selectively pull down known Dsc components. (D) 014W-Flag can selectively pull down with known Dsc components. (E) Cartoon representations of 014W and 109W. Both proteins are predicted to be tetra-spanning membrane proteins. (F) 014W-HA and 109W-Flag do not pull down each other. St: Starting material. Ub: Unbound. El: Elution.\n\nFigure 2: Figure 2. (A) Mass spectrometry peptide coverage for Yir014W. The peptides identified by mass spectrometry are highlighted in red. The underlined sequences are the predicted transmembrane helices. (B) Mass spectrometry peptide coverage for Ypr109W. The peptides identified by mass spectrometry are highlighted in red. The underlined sequences are the predicted transmembrane helices. (C) Sequence similarity between Yir014W and Ypr109W. The alignment was performed with Clustal Omega (Sievers et al., 2011).\n\nFigure 3: Figure 3. (A) 014W-nG co-localizes with FM4-64 labelled vacuole membrane, whereas 109W-nG localizes to the intracellular punctae. (B) Quantification of the number of 109 W-nG punctae. (C) Left, 109W-nG partially co-localizes with Mars-Sec7 labelled trans-Golgi (white arrows). Right, quantification of the co-localization. Error bar represents the Standard Error of the Mean (SEM). (D) Left, 109W-nG partially co-localizes with FM4-64 labelled endosomes (white arrows). Right, quantification of the co-localization. Error bar represents the SEM. (E) Co-localization between 109W and Ubx3 using rapamycin induced co-localization (RICo) assay. Left: A cartoon diagram showing the principle of the assay. Right: FRB-mCherry localization before and after rapamycin treatment. White arrows indicate the co-localization. Scale bar: 2 µm. 10.7554/eLife.33116.007Figure 3—source data 1.The source data for the quantification of 109W-nG punctae in Figure 3B. 10.7554/eLife.33116.008Figure 3—source data 2.The source data for the quantification of co-localization in Figure 3C-D.\n\nFigure 4: Figure 4. (A) Localization of Ubx3-nG after either VLD1 or GLD1 deletion. Note a small amount of punctae are also observed outside the vacuole in gld1∆ cells. (B) The small Ubx3-nG punctae in the gld1∆ cells co-localize with ER marker, DsRed-HDEL, whereas the punctae in vld1∆ cells do not co-localize with ER marker. (C) A competition assay to show elevating the Vld1 expression level in vld1∆ cells gradually diverts Ubx3-nG from punctae to vacuole membrane. Scale bar: 2 µm."
      }
    ]
  },
  {
    "id": "PMC5811209_multi_2",
    "image": [
      "images/PMC5811209-f4-2.png",
      "images/PMC5811209-f5.png",
      "images/PMC5811209-f6.png",
      "images/PMC5811209-f6-2.png",
      "images/PMC5811209-f6-3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Sorting of a multi-subunit ubiquitin ligase complex in the endolysosome system\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 4: Figure 4. (A) A competition assay to show the localization of Ubx3-nG in strains with different GLD1 expression levels. The vacuoles were labeled with FM4-64. Vec: empty vector. (B) Immunoprecipitation experiments to show the interactions between Ubx3-Flag and other Dsc components in WT, Vld1-HA overexpression, and Gld1-GFP overexpression strains. Note for the Input, 1OD600 cells were loaded for each sample except Vld1-HA, lane 2 and Gld1-GFP OE, lane 3. Only 0.1 OD600 cells were loaded for these two samples due to the overexpression. Scale bar: 2 µm.\n\nFigure 5: Figure 5. (A) Subcellular localizations of GFP-Yif1 before (0 hr) and after (4 hr) amino acid starvation. (B) Western blot analysis of the GFP-Yif1 starvation assay. 1 OD600 cells were loaded in each lane. (C) Subcellular localizations of Cot1-GFP before (0 hr) and after (8 hr) Zn2+ withdrawal. (D) Western blot analysis of the Cot1-GFP degradation assay. Same volume of cells was loaded, with 0.25 OD600 cells loaded at 0 hr. Scale bar: 2 µm.\n\nFigure 6: Figure 6. (A) Deletion analysis for Vld1-nG and Gld1-nG localizations. (B) Deletion analysis for Ubx3-nG localization. (C) Co-localization between the Ubx3-nG punctae and ER marker DsRed-HDEL in either dsc2∆ or vld1∆ gld1∆ strains. (D) Double deletion of TUL1 and DSC3 did not change the localization patterns of Vld1-nG, Gld1-nG, or Ubx3-nG. (E) Western blot analysis of the Dsc complex assembly after deleting indicated Dsc components. St: Starting material, El: Elution. (F) A model to summarize the core complex concept. White dashed lines indicate the periphery of yeast cells. Scale bar: 2 µm.\n\nFigure 6: Figure 6. (A) Western blot analysis of the Cot1-GFP degradation after Zn2+ withdrawal in WT, Ubx3-nG, and Vld1-nG strains. Same volume of cells was loaded for each group, with 0.25 OD600 cells loaded at 0 hr. (B) Western blot analysis of the GFP-Yif1 degradation after amino acid starvation in WT, Ubx3-nG, and Gld1-nG strains. Same volume of cells was loaded, with 0.5 OD600 cells loaded at 0 hr.\n\nFigure 6: Figure 6. (A) Co-localization of Vld1-nG punctae with the ER marker DsRed-HDEL in either dsc2∆ or ubx3∆ strains. (B) Co-localization of Gld1-nG punctae with the ER marker DsRed-HDEL in either dsc2∆ or ubx3∆ strains. (C) Localization of Ubx3-nG in vld1∆ gld1∆ cells expressing either an empty vector or spDsc4. The vacuoles were labeled with fluorescent dye FM4-64. Scale bar: 2 µm."
      }
    ]
  },
  {
    "id": "PMC5812032_multi",
    "image": [
      "images/PMC5812032-f1.png",
      "images/PMC5812032-f2.png",
      "images/PMC5812032-f3.png",
      "images/PMC5812032-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Targeting as a Sensitive Tool to Detect Protein-Small RNA Interactions through in Vivo Piggybacking\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomal targeting of P15FHA reveals P15/small RNA interactions not detected by immunoprecipitation. (A) Northern analysis of small RNAs (SUL, IR71, REP2, miR159, miR160, miR160∗, miR169, miR173) in total (left) and @HA immunoprecipitated (IP; right) fractions from SUC:SUL and 35S:P15FHA/SUC:SUL rosette leaves was obtained by sequential rounds of probing and stripping the same membrane. The three IP samples (#1, #2, #3) correspond to three technical replicates obtained from a pool of ten 35S:P15FHA/SUC:SUL plants. (B) Western analysis of P15FHA accumulation in total (left) and @HA IP (right) fractions obtained from the plants described in (A). (C) Northern analysis of small RNAs in total (left) and peroxisomal (perox.; right) fractions obtained from 35S:P15FHA/SUC:SUL and 35S:P15FHASKL/SUC:SUL plants. The small RNA species detected are the same as in (A). The three peroxisome samples (#1, #2, #3) correspond to three biological replicates of 35S:P15FHASKL/SUC:SUL plants. (D) Western analysis of plant peroxisomal marker hydroxypyruvate reductase (@HPR) and P15FHA/P15FHASKL (@HA) in total (left) and peroxisomal (right) fractions obtained from the plants described in (C). Note that more peroxisomal protein was loaded to detect P15FHA/P15FHASKL than to detect HPR. Northern analyses were performed on high-resolution gels. Accumulation of snU6 was used as RNA loading control, while coomassie staining was used as protein loading control. Figure source data can be found with the Supplementary information.\n\nFigure 2: Figure 2. Peroxisomal targeting of P19HA leads to import of 21, 22, and 24nt small RNAs into these organelles. (A) Photos of SUC:SUL, 35S:P19HA/SUC:SUL (transgenic lines #2 and #8) and 35S:P19HASKL/SUC:SUL (transgenic lines #1 and #2) plants used for peroxisome isolation. (B) Western analysis of plant peroxisomal marker hydroxypyruvate reductase (@HPR) and P19HA/P19HASKL (@HA) in total (left) and peroxisomal (perox. right) fractions obtained from the plants described in (A). Note that more peroxisomal protein was loaded to detect P19HA/P19HASKL than to detect HPR. (C) Northern analysis of small RNAs (SUL, IR71, REP2, miR159) in total (left) and peroxisomal (right) fractions from the plants described in (A) was obtained by sequential rounds of probing and stripping the same membranes. Northern analysis was performed on a low-resolution gel. Accumulation of snU6 was used as RNA loading control, while coomassie staining was used as protein loading control. Figure source data can be found with the Supplementary Information.\n\nFigure 3: Figure 3. Peroxisomal targeting of P19HA reveals P19/small RNA interactions not detected by immunoprecipitation. (A) Northern analysis of small RNAs (SUL, IR71, REP2, miR159, miR160, miR160∗, miR169, miR173) in total (left) and @HA immunoprecipitated (IP; right) fractions from SUC:SUL and 35S:P19HA/SUC:SUL rosette leaves was obtained by sequential rounds of probing and stripping the same membrane. The three IP samples (#1, #2, #3) correspond to three technical replicates obtained from a pool of ten 35S:P19HA/SUC:SUL plants. (B) Western analysis of P19HA accumulation in total (left) and @HA IP (right) fractions obtained from the plants described in (A). (C) Northern analysis of small RNAs in total (left) and peroxisomal (perox.; right) fractions obtained from 35S:P19HA/SUC:SUL and 35S:P19HASKL/SUC:SUL plants. The small RNA species detected are the same as in (A). The three peroxisome samples (#1, #2, #3) correspond to three biological replicates of 35S:P19HASKL/SUC:SUL plants. (D) Western analysis of plant peroxisomal marker hydroxypyruvate reductase (@HPR) and P19HA/P19HASKL (@HA) in total (left) and peroxisomal (right) fractions obtained from the plants described in (C). Note that more peroxisomal protein was loaded to detect P19HA/P19HASKL than to detect HPR. Northern analyses were performed on high-resolution gels. Accumulation of snU6 was used as RNA loading control, while coomassie staining was used as protein loading control. Figure source data can be found with the Supplementary information.\n\nFigure 4: Figure 4. AGO2SKL is not imported into peroxisomes, while overexpression of AGO2 impacts the miR390/TAS3 pathway. (A) Western analysis of plant peroxisomal marker hydroxypyruvate reductase (@HPR) and AGO2/AGOSKL (@AGO2) in total (left) and peroxisome (right) fractions obtained from Col0, 35S:AGO2/ago2-1 (transgenic lines #5 and #6) and 35S:AGO2SKL/ago2-1 (transgenic lines #6 and #8) plants. Total proteins also include ago2-1. (B) Photos of the plants described in (A). (C) Northern analysis of small RNAs (miR159, miR173, miR390, miR390∗, miR403, miR408, TAS1-derived siRNA (255), and TAS3-derived siRNA 5′D7(+) (TAS3)) in total leaf tissue of plants described in (A,B) was obtained by sequential rounds of probing and stripping the same membrane. Northern analysis was performed on a low-resolution gel. Accumulation of snU6 was used as RNA loading control, while coomassie staining was used as protein loading control. Figure source data can be found with the Supplementary Information."
      }
    ]
  },
  {
    "id": "PMC5818364_multi",
    "image": [
      "images/PMC5818364-f1.png",
      "images/PMC5818364-f2.png",
      "images/PMC5818364-f3.png",
      "images/PMC5818364-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural and functional roles of ether lipids\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Chemical structures of diacyl and ether-linked phospholipids. Diacyl phospholipids have fatty acyl side chains linked to the sn-1 and sn-2 position of the glycerol backbone by ester bonds. Ether-linked phospholipids are a subclass of glycerophospholipids that have an alkyl chain attached by an ether bond at the sn-1 position. The sn-2 position of ether lipids generally has an ester-linked acyl chain, as in diacyl phospholipids. Some ether-linked phospholipids, called alkenyl-acylphospholipids, contain a cis double bond adjacent to the ether linkage and are commonly referred to as plasmalogens. The polar head group of ether-linked phospholipids is most commonly choline or ethanolamine\n\nFigure 2: Figure 2. Acyl-DHAP pathway of ether lipid synthesis. This process begins in peroxisomes and is subsequently completed in the ER. The pathway utilizes dihydroxyacetone phosphate (DHAP) generated by glycerol 3-phosphate dehydrogenase (G3PDH)-mediated dehydrogenation of G3P as the substrate for ether lipid synthesis. Fatty acid synthase (FAS)-mediated de novo lipogenesis generates fatty acyl-CoA that is utilized by glyceronephosphate O-acyltransferase (GNPAT) or reduced to a fatty alcohol by a fatty acyl-CoA reductase (FAR1 or FAR2) to later be catalyzed by alkylglycerone phosphate synthase (AGPS), forming the ether bond and exchanging the acyl chain for an alkyl group. PexRAP (an acyl/alkyl DHAP reductase) then catalyzes the final peroxisomal step, generating the ether lipid precursors, 1-O-alkyl-G3P (AGP) or the diacyl phospholipid precursor lysophosphatidic acid (LPA). The completion of phospholipid synthesis occurs in the ER. This includes acylation of the glycerol backbone at the sn-2 position, converting LPA to diacylglycerol (DAG) and AGP to alkyl-acylglycerol (AAG), as well as addition of a cytidine diphosphate-alcohol head group (such as CDP-choline or CDP-ethanolamine) at the sn-3 position to form the mature phospholipid\n\nFigure 3: Figure 3. Peroxisomal lipid synthesis is required for maintaining neutrophil viability and membrane integrity. In healthy neutrophils, fatty acid synthase (FAS) and PexRAP participate in peroxisomal lipid synthesis, including the generation of ether-linked phospholipids that are incorporated into the plasma membrane, contributing to membrane integrity. Genetic ablation of FAS or PexRAP disrupts the lipid synthetic pathway, leading to a preferential loss of ether-linked phospholipids in neutrophils. This alters membrane stability, leading to the activation of ER stress, increased apoptosis, and ultimately neutropenia\n\nFigure 4: Figure 4. Role of ether lipids in Schwann cell differentiation and myelination. In a healthy Schwann cell, the cell membrane is enriched in plasmalogens. This is necessary for proper recruitment of Akt to the plasma membrane, resulting in its phosphorylation and activation. Activated Akt phosphorylates GSK3β at Ser9, inhibiting its activity. Plasmalogen deficiency impairs recruitment and activation of Akt, preventing it ability to inhibit GSK3β. Active GSK3β impairs Schwann cell differentiation, resulting in disrupted radial sorting and myelination. Supplementation of lithium or TDZD-8 to inhibit GSK3β rescues plasmalogen-deficient phenotype, restoring differentiation and myelination"
      }
    ]
  },
  {
    "id": "PMC5820819_multi",
    "image": [
      "images/PMC5820819-f1.png",
      "images/PMC5820819-f2.png",
      "images/PMC5820819-f3.png",
      "images/PMC5820819-f4.png",
      "images/PMC5820819-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Childhood cerebral X-linked adrenoleukodystrophy with atypical neuroimaging abnormalities and a novel mutation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generalized melanoderma. Note the hyperpigmentation of the nail beds\n\nFigure 2: Figure 2. Axial T2-weighted MR images: (a) Symmetrical hyperintense signal in ventral pons (arrows). Note absence of signal abnormality in middle cerebellar peduncles and cerebellar hemisphere; (b) hyperintense signals in bilateral cerebral peduncles (arrows); (c) patchy signal abnormality in posterior limb of left internal capsule (arrow)\n\nFigure 3: Figure 3. Axial T2-weighted MR images: (a) A mildly increased hyperintense signal in ventral pons (arrows) as compared to Figure 2a. Also note bilateral cerebellar atrophy. (b) Atrophy of midbrain. (c) Bilateral hyperintense signal in posterior limb of internal capsule (arrows), left side more involved than the right\n\nFigure 4: Figure 4. Axial T2-weighted images: (a) Hyperintense signal in bilateral middle cerebellar peduncles (arrows) and right cerebellar hemisphere (curved arrow). (b) Sagittal image showing abnormal hyperintense signals in the ventral pons and splenium of the corpus callosum (arrow). (c) Postcontrast image showing subtle enhancement at the level of the midbrain in the right cerebral peduncle (arrow). (d) Minimal enhancement is also seen in the posterior limb of the left internal capsule\n\nFigure 5: Figure 5. Electropherogram showing the mutated sequence profile detected in the patient. The red letters display respective nucleotide bases being incorporated to create the frame shift mutation starting at cDNA position 257 and resulting in a duplication of respective amino acids c.257_268dup, p.Val86_Arg89dup. The green bar displays the reference sequence and corresponding coding amino acid triplets. The mutation resulted in replacement of amino acid glutamic acid (represented by the letter E in the reference sequence) [open arrow] by Valine (represented by letter V) [solid arrow]"
      }
    ]
  },
  {
    "id": "PMC5826702_multi",
    "image": [
      "images/PMC5826702-f1.png",
      "images/PMC5826702-f2.png",
      "images/PMC5826702-f3.png",
      "images/PMC5826702-f4.png",
      "images/PMC5826702-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A versatile plasmid system for reconstitution and analysis of mammalian ubiquitination cascades in yeast\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The pRA vectors (A) are yeast centromeric shuttle plasmids that carry an auxotrophic marker (URA3, TRP1 or LEU2 gene) for selection in yeast and the ampicillin (Amp) resistance gene for selection in E. coli. The gene of interest can be cloned into the multiple cloning site (MCS) under control of either the inducible GAL1 promoter (3 different strengths) or the constitutive TEF promoter. The expressed protein will bear any of the four (Flag, Myc, HA or V5) N-terminal epitope tags allowing easy detection. All restriction sites indicated are unique. (B) High copy (2 μm) yeast shuttle plasmids carrying the HIS3 auxotrophic marker and expressing either 6xHis-Myc tagged ubiquitin (Ub) or SUMO (Smt3) under control of the copper inducible promoter (CUP). CTA1 and Cyc1 term (inator), transcription termination sequences derived from the yeast Catalase A and Cytochrome c1 gene, respectively.\n\nFigure 2: Figure 2. Yeast strain yRA2 transformed with E6-E7 cloned in pRA1 (Flag tag, URA3 marker, 93%-GAL1 promoter), pRA2 (Flag tag, URA3 marker, 31%-GAL1 promoter) and pRA3 (Flag tag, URA3 marker, 15%-GAL1 promoter), was induced for the indicated time points by the addition of 2% galactose. Cells were lysed and equivalent amounts of protein extract were analyzed by SDS-PAGE and anti-Flag immunoblotting. Hexokinase is used as a loading control.\n\nFigure 3: Figure 3. (A) Yeast strain yRA2 was transformed with E6AP (wild type or catalytically inactive mutant) cloned in pRA306 (HA tag, LEU2 marker, TEF promoter), UBCH7 cloned in pRA300 (Flag tag, URA3 marker, TEF promoter) and E6-E7 cloned in pRA20 (V5 tag, TRP1 marker, 93%-GAL1 promoter). Following 1 hour of galactose induction, cells were treated with 75 μM MG132 for the indicated time points. Cells were lysed and equivalent amounts of protein extract were analyzed by SDS-PAGE and immunoblotting using the indicated antibodies. (B) Yeast strain yRA2 was transformed with E6AP (wild type or catalytically inactive mutant) cloned in pRA306 (HA tag, LEU2 marker, TEF promoter), E6-E7 cloned in pRA20 (V5 tag, TRP1 marker, 93%-GAL1 promoter) and 6xHis-Myc-Ub (Myc tag, HIS3 marker, CUP promoter) or empty p423 vector. Expression of 6xHis-Myc-Ub was induced by addition of CuSO4 (100 μM). Following 1 hour of galactose induction, cells were treated with 50 μM MG132 for 120 min. Cells were lysed and equivalent amounts of protein extract were analyzed by SDS-PAGE and immunoblotting using anti-V5 antibody. The band marked with an asterisk (*) is an example of an ubiquitinated E6-E7 band that in cells overexpressing 6xHis-Myc-Ub, generates additionally slower migrating species (arrow head) due to the incorporation of the 6xHis-Myc-tagged ubiquitin.\n\nFigure 4: Figure 4. Yeast strain yRA2 was transformed with E6AP, UBCH7 and E6-E7 as described in the legend to Figure 3. Following 1 hour of galactose induction, cells were treated with 50 μg/ml CHX for the indicated time points. Cells were lysed and equivalent amounts of protein extract were analyzed by SDS-PAGE and immunoblotting using the indicated antibodies.\n\nFigure 5: Figure 5. Yeast strain yRA1 was transformed with PML cloned in pRA20 (V5 tag, TRP1 marker, 93%-GAL1 promoter) and with a plasmid expressing 6xHis-Myc-Smt3 under control of the CUP promoter (HIS3 marker) or with empty vector. Expression of PML and Smt3 was induced by addition of galactose (2% [w/v]) and CuSO4 (100 μM), respectively. Cells were lysed and equivalent amounts of protein extract were analyzed by SDS-PAGE and anti-V5 (A) or anti-Myc (B) immunoblotting. The band marked with an asterisk (*) in panel A is an example of PML modified by a single Smt3 moiety that, in cells overexpressing 6xHis-myc-Smt3, gives rise to a slower migrating species (arrow head) due to covalent attachment of the 6xhis-Myc-tagged Smt3."
      }
    ]
  },
  {
    "id": "PMC5830475_multi",
    "image": [
      "images/PMC5830475-f1.png",
      "images/PMC5830475-f2.png",
      "images/PMC5830475-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Coagulopathy in Zellweger spectrum disorders: a role for vitamin K\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Relationship between last measured dihydroxycholestanoic acid (DHCA) (x axis, normal range 0.00–0.12 μmol/L) and prothrombin time (PT) (y axis, normal range 9.7–11.6 s). Trend line indicates a significant correlation of DHCA and PT (r = 0.76, p < 0.001)\n\nFigure 2: Figure 2. a Proteins induced by vitamin K absence (PIVKA-II) of 17 patients before (dots) and after (squares) vitamin K therapy administered orally. Cutoff range is <2.5 μg/L. Almost all patients showed a decreased PIVKA-II level (p ≤ 0.05). b PIVKA-II levels before (T = 0) and after (T = 72 h) vitamin K supplementation IV. Interrupted lines indicate reference range of 21–56 mAU/ml\n\nFigure 3: Figure 3. Thrombin generation analysis of Zellweger spectrum disorders (ZSD) patients. Thrombin generation was initiated with a1 pM or b 5 pM tissue factor. Thrombin generation was averaged for five patients before and after 72 h of vitamin K therapy IV"
      }
    ]
  },
  {
    "id": "PMC5837213_multi",
    "image": [
      "images/PMC5837213-f1.png",
      "images/PMC5837213-f2.png",
      "images/PMC5837213-f3.png",
      "images/PMC5837213-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"SLC30A9 mutation affecting intracellular zinc homeostasis causes a novel cerebro-renal syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigree of studied kindred and linkage analysis. (A) Pedigree of the large consanguineous Bedouin kindred studied. (B) Histological haematoxylin and eosin stain of renal biopsy derived from Patient V-15 at age 13 months revealed chronic tubulo-interstitial nephritis with no evident cysts or tubular dilatation. (C) HomozygosityMapper plot, blue arrow presenting a homozygous locus shared by all affected individuals.\n\nFigure 2: Figure 2. The SLC30A9 mutation, conservation and expression pattern. (A) Sanger sequencing of an affected individual (Patient V:12) and obligatory carrier (Subject IV:3). (B) Above is the predicted domain architecture of SLC30A9 showing its cation efflux domain. Below is a multiple sequence alignment of selected SLC30A9 orthologues. The in-frame deletion mutation is predicted to cause a p.(A350del) (marked with arrow) in a highly conserved residue within the putative cation efflux domain of SLC30A9 (boxed in blue). (C) RT-PCR of 21 normal human tissues demonstrating the expression pattern of SLC30A9.\n\nFigure 3: Figure 3. SLC30A9 protein subcellular localization, effect on Wnt signaling and structural modeling. (A) Overexpression of SLC30A9 protein fused to enhanced green fluorescent protein (EGFP) and immunofluorescent staining of different endosomal, Golgi and ER markers (CD63, EEA1, Rab7, GM130 and Calnexin) showing partial co-localization with endoplasmic reticulum in SH-SY5Y cells. On the bottom left side of the merged image of Calnexin marker panel is a magnification of the dashed frame, showing the co-localization in a single cell. Scale bars = 10 µm. (B) TOP flash reporter assay of neuroblastoma (SH-SY5Y) cells showing enhanced Wnt signalling in both SLC30A9 wild-type and mutant transfected cells. There was no significant difference between wild-type and mutant transfected cells. (C) Structural model of ZnT-9 protein showing the p.(A350del) in the fourth transmembrane helix, putatively causing destabilization of the protein structure in general, affecting the TM metal binding site specifically.\n\nFigure 4: Figure 4. Cytosolic free zinc measurements of HEK293 cells overexpressing wild-type or mutant ZnT-9. (A) ZnT9 expression was assessed by quantitative RT-PCR and expression levels were equivalent in ZnT9-WT and ZnT9-mut expressing cells. (B) Normalized average traces obtained from three independent experiments (n = 90 cells for HEK-ZnT9-WT and n = 119 cells for HEK-ZnT9-mut). Steady-state fluorescence intensity ratio (citrine to cerulean) was first measured before obtaining the Rmax under perfusion with KHB buffer containing the zinc chelator N,N,N’,N’-tetrakis (2-pyridylmethyl) ethylenediamine (50 μM; zinc-free condition). Finally, the Rmin was obtained under perfusion with KHB buffer containing 5 μM pyrithione and 100 μM Zn2+ (zinc-saturated condition), providing saturating intracellular Zn2+ concentrations. (C) The probe occupancy was determined for ZnT-9 wild-type and mutant expressing cells (D) free zinc concentration was calculated using the formula: [Zn2+] = Kd (Rmax − R)/(R − Rmin), revealing significant decreases in cytosolic free zinc levels in cells expressing the mutant form compare to cells expressing wild-type ZnT-9 (****P-value < 0.0001)."
      }
    ]
  },
  {
    "id": "PMC5857114_multi",
    "image": [
      "images/PMC5857114-f1.png",
      "images/PMC5857114-f2.png",
      "images/PMC5857114-f3.png",
      "images/PMC5857114-f4.png",
      "images/PMC5857114-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Role of Parkin and endurance training on mitochondrial turnover in skeletal muscle\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Effect of Parkin deficiency and training on muscle mass. a Representative Western blot of Parkin expression in skeletal muscle of control wild-type (WT) and Parkin knockout (KO) mice. b Graphical representation of voluntary running distance (kilometers per week) between WT and KO mice (n = 8). Wheels were provided in animal cages for a duration of 6 weeks. c Total body weight of untrained and trained Parkin KO and WT animals (n = 8). d Quadriceps muscle mass corrected for total body weight (n = 8). e Heart mass corrected for total body weight (n = 8). Values are means ± SEM. ¶P < 0.05, main effect of time. *P < 0.05, main effect of training. WT, wild type; KO, Parkin knockout; UT, untrained; T, trained\n\nFigure 2: Figure 2. Effect of training and Parkin on whole muscle protein markers. a Representative Western blot of Parkin expression in untrained and trained skeletal muscle of control wild-type (WT) mice above. A graphical representation is shown below (n = 5, *P < 0.05, vs UT). b Representative immunoblots of COXI, COXII, COXIV and TFAM expression in untrained and trained skeletal muscle of Parkin KO and WT animals. c A graphical representation of whole muscle COXI shown (n = 4, *P < 0.05, main effect of training; #P < 0.05, vs trained WT). d Quantification of whole muscle COXII (n = 6, *P < 0.05, main effect of training). e Whole muscle COXIV expression (n = 4, *P < 0.05, main effect of training, #P < 0.05, main effect of genotype). f Quantification of whole muscle TFAM (n = 4, *P < 0.05, main effect of training). Values are means ± SEM. †P < 0.05, interaction effect of training and genotype. α-tubulin was used for muscle loading control. WT, wild type; KO, Parkin knockout; UT, untrained; T, trained; COXI, cytochrome c oxidase subunit 1; COXII, cytochrome c oxidase subunit 2; COXIV, cytochrome c oxidase subunit 4; TFAM, mitochondrial transcription factor A; A.U., arbitrary units\n\nFigure 3: Figure 3. Effect of training and Parkin on key regulators of mitochondrial biogenesis. a Representative Western blots of PGC-1α, PARIS and p-ACC expression in untrained and trained skeletal muscle of Parkin KO and WT animals. b A graphical representation of whole muscle PGC-1α (n = 4, *P < 0.05, vs untrained WT). c Quantification of whole muscle PARIS (n = 6, *P < 0.05, main effect of training; #P < 0.05, vs untrained WT). d A graphical representation of whole muscle phosphorylation of ACC (n = 6, *P < 0.05, main effect of training; #P < 0.05, vs untrained KO). Values are means ± SEM. †P < 0.05, interaction effect of training and genotype. α-tubulin was used for muscle loading control. WT, wild type; KO, Parkin knockout; UT, untrained; T, trained; p-ACC, phospho-acetyl-CoA carboxylase; PARIS, Parkin-interacting substrate; PGC-1α, peroxisome proliferator gamma coactivator-1α; A.U., arbitrary units\n\nFigure 4: Figure 4. Mitochondrial adaptations following 6 weeks of voluntary wheel training. a Representative Western blots of COXI, COXII, COXIV and TFAM expression on isolated mitochondria from untrained and trained skeletal muscle of Parkin KO and WT animals. b Graphical representation of mitochondrial COXI expression (n = 8). c Quantification of mitochondrial COXII content (n = 4). d Mitochondrial yield of mixed hindlimb muscles of Parkin KO and WT animals (n = 4). e Skeletal muscle cytochrome c oxidase (COX) activity following training in quadriceps muscle of Parkin KO and WT animals (n = 5). f Mitochondrial state 4 and state 3 respiration rates in KO compared with WT animals (n = 8). g Mitochondrial ROS emission expressed per natom of oxygen consumed in Parkin KO and WT mice (n = 8; ¶P < 0.05, vs state 4 trained WT). Values are means ± SEM. *P < 0.05, main effect of training; #P < 0.05, main effect of genotype; †P < 0.05, interaction effect of genotype and training. Voltage-dependent anion channel (VDAC) was used as a mitochondrial loading control. WT, wild type; KO, Parkin knockout; UT, untrained; T, trained; COX1, cytochrome c oxidase subunit 1; COXII, cytochrome c oxidase subunit 2; COX4, cytochrome c oxidase subunit 4; TFAM, mitochondrial transcription factor A; ROS, reactive oxygen species; A.U., arbitrary units\n\nFigure 5: Figure 5. Effect of Parkin and training on acute exercise performance. a Representative Western blot of Parkin localization on isolated mitochondria from untrained and trained WT muscle, prior to exercise (Con) and immediately following exercise (Ex). Quantification of mitochondrial Parkin localization is shown below, corrected for loading using mitochondrial voltage-dependent anion channel (VDAC) (n = 6, ¶P < 0.05, vs untrained Con). b Animal endurance performance (i.e. total distance run) of WT and KO animals (n = 8, *P < 0.05, main effect of training). c Blood lactate levels measured prior to (Con), and immediately following exercise (Ex) (n = 8, #P < 0.05, main effect of exercise). Values are means ± SEM. WT, wild type; KO, Parkin knockout; UT, untrained; T, trained; A.U., arbitrary units"
      }
    ]
  },
  {
    "id": "PMC5857114_multi_2",
    "image": [
      "images/PMC5857114-f6.png",
      "images/PMC5857114-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Role of Parkin and endurance training on mitochondrial turnover in skeletal muscle\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Mitophagic LC3II flux following acute exercise, training, and combined treatments in WT and KO animals. Representative Western blots of mitochondrial LC3II localization of WT (a) and Parkin KO (b) mice injected with water (Veh) or 0.4 mg/kg colchicine (Col). Quantification of mitochondrial LC3II flux (c) is shown (n = 6). Mitophagic LC3II flux was assessed under basal conditions, and immediately following acute exercise, in untrained and trained groups of WT and KO animals. The fold change in LC3II flux (D) was calculated with acute exercise-induced values over basal values (n = 6). Values are means ± SEM. ¶P < 0.05, vs untrained WT; #P < 0.05, main effect of exercise; §P < 0.05, main effect of genotype; *P < 0.05, vs all other experimental conditions; †P < 0.05, interaction effect of genotype and training. Voltage-dependent anion channel (VDAC) was used as a mitochondrial loading control. WT, wild type; KO, Parkin knockout; UT, untrained; T, trained; LC3II, lipidated microtubule-associated protein 1A/1B-light chain 3; A.U., arbitrary units\n\nFigure 7: Figure 7. Mitophagic p62 flux following acute exercise, training, and combined treatments in WT and KO animals. Representative Western blots of mitochondrial p62 localization of WT (a) and Parkin KO (b) mice injected with water (Veh) or 0.4 mg/kg colchicine (Col). Quantification of mitochondrial p62 flux (c) is shown (n = 5). Mitophagic p62 flux was assessed under basal conditions, and immediately following acute exercise, in untrained and trained groups of WT and KO animals. The fold change in p62 flux (d) was calculated with acute exercise-induced values over basal values (n = 5). Values are means ± SEM. *P < 0.05, main effect of genotype; #P < 0.05, main effect of exercise. Voltage-dependent anion channel (VDAC) was used as a mitochondrial loading control. WT, wild type; KO, Parkin knockout; UT, untrained; T, trained; p62, sequestosome 1; A.U., arbitrary units"
      }
    ]
  },
  {
    "id": "PMC5861206_multi",
    "image": [
      "images/PMC5861206-f1.png",
      "images/PMC5861206-f2.png",
      "images/PMC5861206-f3.png",
      "images/PMC5861206-f4.png",
      "images/PMC5861206-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mechanistic Role of Reactive Oxygen Species and Therapeutic Potential of Antioxidants in Denervation- or Fasting-Induced Skeletal Muscle Atrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Bioinformatics analysis of gene expression in skeletal muscles identifies distinct modules of co-expression genes. (A) The gene modules generated by weighted gene coexpression network analysis (WGCNA) using microarrays data from 36 skeletal muscle samples. The 20 co-expression modules were obtained and clustered into 6 classes by cluster merging module. (B) Heatmap of ROS production-related genes, positive regulators for ROS production were gradually up-regulated, and negative regulators for ROS production were gradually down-regulated. (C) The negative and positive regulators for ROS production were mainly distributed in classes 2 and 6, respectively.\n\nFigure 2: Figure 2. Histograms showing an increased ROS level in (A) C2C12 myotubes suffering from fasting (nutrient deprivation, ND) or (B) mouse soleus muscles atrophied by denervation (Den) as compared to that in (A) C2C12 myotubes or (B) mouse soleus muscles without exposure to fasting or denervation stimulation (Nors, serving as respective controls) respectively. *p < 0.05 vs. Nor.\n\nFigure 3: Figure 3. After fasted C2C12 myotubes were incubated with Hank's balanced salt solution for 12 h in the absence or presence of 5 mM NAC or 80 μM PQQ, DCF staining was performed to determine the ROS level in different samples, including normal myotubes (Nor, without exposure to atrophic stimulation and antioxidant treatment), fasted C2C12 myotubes (ND), fasted C2C12 myotubes treated with NAC (ND+NAC), and fasted C2C12 myotubes treated with PQQ (ND+PQQ). Histogram comparing the ROS level (as expressed by DCF fluorescence intensity) among different myotube samples. *p < 0.05.\n\nFigure 4: Figure 4. After fasted C2C12 myotubes were incubated with Hank's balanced salt solution for 12 h in the absence or presence of 5 mM NAC or 80 μM PQQ, MHC staining was performed to quantify the diameter of different myotube samples, including normal C2C12 myotubes (Nor, without exposure to atrophic stimulation and antioxidant treatment), fasted C2C12 myotubes (ND), fasted C2C12 myotubes treated with NAC (ND+NAC), and fasted C2C12 myotubes treated with PQQ (ND+PQQ). Histogram (Right) comparing the myotube diameter among different myotube samples, where the myotube diameter value is expressed as the mean ± SD from three independent experiments. *p < 0.05. Also shown (Left) are representative MHC staining images.\n\nFigure 5: Figure 5. After fasted C2C12 myotubes were incubated with Hank's balanced salt solution for 12 h in the absence or presence of 5 mM NAC (A) or 80 μM PQQ (B), Western blot analysis was performed to determine the protein levels of MHC, MuRF-1, and MAFbx in different myotube samples, including normal myotubes (Nor, without exposure to atrophic stimulation and antioxidant treatment), fasted C2C12 myotubes (ND), fasted C2C12 myotubes treated with NAC (ND+NAC), and fasted C2C12 myotubes treated with PQQ (ND+PQQ). Representative Histogram (right) comparing the MHC, MuRF-1, and MAFbx levels among different myotube samples, and *p < 0.05 vs. ND+NAC (A) or ND+PQQ (B), respectively. Also shown (left) are representative Western blot images."
      }
    ]
  },
  {
    "id": "PMC5861206_multi_2",
    "image": [
      "images/PMC5861206-f6.png",
      "images/PMC5861206-f7.png",
      "images/PMC5861206-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Mechanistic Role of Reactive Oxygen Species and Therapeutic Potential of Antioxidants in Denervation- or Fasting-Induced Skeletal Muscle Atrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. After mice with denervation-induced soleus muscle atrophy had been injected with saline vehicle or saline vehicle plus NAC (100 mg/kg) or PQQ (5 mg/kg) for 14 days, the mouse soleus muscle was harvested for determining the ROS level using DHE staining. Different muscle samples were harvested from mice receiving sham-operation and further saline treatment (Nor, serving as control), mice receiving sciatic nerve transection and further saline treatment (Den), mice receiving sciatic nerve transection and further saline plus NAC treatment (Den+NAC), and mice receiving sciatic nerve transection and further saline plus PQQ treatment (Den+PQQ), respectively. Histogram (right) comparing the ROS level (as expressed by DHE fluorescence intensity) among different muscle samples (n = 6). *p < 0.05. Also shown (left) are representative DHE staining images.\n\nFigure 7: Figure 7. After mice with denervation-induced soleus muscle atrophy had been injected with saline vehicle or saline vehicle plus NAC (100 mg/Kg) or PQQ (5 mg/kg) for 14 days, the mouse soleus muscle was harvested for determining the fiber CSA. Different muscle samples were harvested from mice receiving sham-operation and further saline treatment (Nor, serving as control), mice receiving sciatic nerve transection and further saline treatment (Den), mice receiving sciatic nerve transection and further saline plus NAC treatment (Den+NAC), and mice receiving sciatic nerve transection and further saline plus PQQ treatment (Den+PQQ), respectively. Histogram (Right) comparing the fiber CSA (upper: absolute value, and lower: distribution frequency) among different muscle samples, where the fiber CSA value is expressed as the mean ± SD from three independent experiments (n = 6). *p < 0.05. Also shown (Left) are representative laminin staining images.\n\nFigure 8: Figure 8. After mice with denervation-induced soleus muscle atrophy had been injected with saline vehicle or saline vehicle plus NAC (100 mg/kg, A) or PQQ (5 mg/kg, B) for 14 days, the mouse soleus muscle was harvested to undergo Western blot analysis. Different muscle samples were harvested from mice receiving sham-operation and further saline treatment (Nor, serving as control), mice receiving sciatic nerve transection and further saline treatment (Den), mice receiving sciatic nerve transection and further saline plus NAC treatment (Den+NAC), and mice receiving sciatic nerve transection and further saline plus PQQ treatment (Den+PQQ), respectively. Histograms (right) comparing the MHC, MuRF-1, and MAFbx levels among different muscle samples (n = 6). *p < 0.05 vs. Den+NAC (A) or Den+PQQ (B), respectively. Also shown (left) are representative Western blot images."
      }
    ]
  },
  {
    "id": "PMC5864075_multi",
    "image": [
      "images/PMC5864075-f1.png",
      "images/PMC5864075-f2.png",
      "images/PMC5864075-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Improving the efficiency of homologous recombination by chemical and biological approaches in Yarrowia lipolytica\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The URA3-blaster cassette with 50 bp of homology arm to target gene or locus was amplified from pUC-ylURA3 or pUC-ylURA3-P4UAS1B plasmid. The URA3-blaster cassettes are integrated into the Y. lipolytica genome by HR and then HR between the 100 bp 3HA direct repeat results in excision of the URA3 marker at the integrated locus. (A) Gene deletion cassettes amplified from the pUC-ylURA3 plasmid. (B) Gene integration cassettes amplified the pUC-ylURA3-P4UAS1B plasmid.\n\nFigure 2: Figure 2. (A) A schematic representation of the β-carotene biosynthetic pathway in Y. lipolytica. Integrated genes include geranyl diphosphate synthase (crtE), phytoene synthase (crtYB) and carotene desaturase (crtI). (B) Scheme for the construction of the β-carotene producing strain and the efficiency of targeted gene integration. The crtI, crtYB and crtE genes, driven by their individual 4UAS1B promoters, were integrated into the pox1, pox2 and pox3 sites in the ku70-disrupted Y. lipolytica strain, respectively. Cells treated with HU were transformed with the gene replacement cassette with 50 bp of homology arm to the target gene. The gene targeting rate (%) is shown, and the numbers in parentheses represent the correct integrants/total transformants screened. The experiments were performed in duplicate. HMG-CoA, 3-hydroxy-3-methylgluratyl-coenzyme A; MVA, mevalonic acid; DMPAA, dimethylallyl pyrophosphate; IPP, isopentyl pyrophosphate; PP, pyrophosphate.\n\nFigure 3: Figure 3. (A) ESI-mass spectrum of the wild-type Y. lipolytica strain. (B) ESI-mass spectrum of the resulting β–carotene producing strain (crtI/YB/E). All strains was cultivated for 6 days at 30°C in 50 mL of YPD medium containing 20 g/L glucose. The experiments were performed in duplicate, and the representative results are shown."
      }
    ]
  },
  {
    "id": "PMC5868148_multi",
    "image": [
      "images/PMC5868148-f1.png",
      "images/PMC5868148-f2.png",
      "images/PMC5868148-f3.png",
      "images/PMC5868148-f4.png",
      "images/PMC5868148-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ring finger protein 38 promote non-small cell lung cancer progression by endowing cell EMT phenotype\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Increased RNF38 transcript levels in different types of cancer. (A) Analysis RNF38 mRNA level in colon mucinous adenocarcinoma vs. normal (TCGA colon data retrieved from Oncomine). (B) A significant RNF38 upregulation in colorectal carcinoma as compared to normal tissue. (C) RNF38 transcript levels in smoldering myeloma versus normal bone marrow tissues are shown significant upregulation. (D) High level of RNF38 mRNA was observed in prostate carcinoma compared with normal tissue.\n\nFigure 2: Figure 2. Increased RNF38 expression in NSCLC patients. (A) RNF38 mRNA expression in 15 paired NSCLC tissues (T) and adjacent non-tumor tissues(N). (B)The protein expression of RNF38 in 8 paired NSCLC tissues (T) and adjacent non-tumor tissues (N). *P < 0.05. (C). Representative pictures of RNF38 staining in 208 paired NSCLC tissues matched adjacent normal tissue. (D) Analysis of the integrated optical density (IOD) value of RNF38 immunostaining through IPP6.0 in 208 paired NSCLC tissues matched adjacent normal tissue. *P<0.05, **P<0.01, ***P<0.001.\n\nFigure 3: Figure 3. High level of RNF38 is negatively correlated with E-cadherin expression and predict poor prognosis of patients with NSCLC. (A) Analysis of correlation between different RNF38 level and different clinicopathological features of this cohort of NSCLC patients as well as the estimate of their corresponding overall survival. (AC: adenocarcinoma, SC: squamous cell carcinoma, RNF38high: high expression of RNF38, RNF38low: low expression of RNF38). (B) Representative photos of 208 NSCLC patients showing that RNF38 expression was negatively associated with E-cadherin expression. (C) Kaplan-Meier survival curves for 208 NSCLC patients according to RNF38 expression status. (D) Prognostic significance assessed by Kaplan-Meier survival estimates and log-rank tests Kaplan-Meier according to the combination of RNF38 and E-cadherin expression. (Group 1, low RNF38 and preserved E-cadherin; Group 2, RNF38 and E-cadherin both high or both low; Group 3, high RNF38 and impaired E-cadherin.)\n\nFigure 4: Figure 4. RNF38 accelerate NSCLC cell proliferation, migration and invasion. (A, B). RNF38 mRNA and protein levels was confirmed by real‑time qRT‑PCR and western blot respectively in NSCLC cell lines. β‑actin was used as a loading control. (C). RNF38 expression in A549 and 95D cells was reduced distinctly by RNA interference. (D). Wound healing assays were used to evaluate the migration ability of A549 and 95D cells. (E). Transwell assays were used to measure the changes in invasive abilities of shRNF38-transfected A549 and 95D cells. (F) For measurement of cell growth, CCK‑8 assays were used to detect changes in NSCLC cells after down-regulation of RNF38 at different time intervals (from12 to 72 h). (G). Changes in Colony formation activity of NSCLC cells treated with sh-control or sh-RNF38. P values were calculated using Student's t-test All bar graphs depicted quantification of triplicate results with mean ± SD. *P<0.05, **P<0.01, and ***P<0.001\n\nFigure 5: Figure 5. RNF38 promoted NSCLC cell invasion by promoting EMT. (A) The changes of E-cadherin, vimentin, key molecules of EMT, expression levels were determined by Western blot after knockdown of RNF38 in A549 and 95D cells. (B) Representative pictures of Fluorescence staining for E-cadherin and Vimentin in A549 and 95D cells. DAPI-blue stains the nuclei."
      }
    ]
  },
  {
    "id": "PMC5935100_multi",
    "image": [
      "images/PMC5935100-f1.png",
      "images/PMC5935100-f2.png",
      "images/PMC5935100-f3.png",
      "images/PMC5935100-f4.png",
      "images/PMC5935100-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural Basis for Recognition of L-lysine, L-ornithine, and L-2,4-diamino Butyric Acid by Lysine Cyclodeaminase\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Stereo ribbon diagram of S. pristinaespiralis LCD (SpLCD)/NAD+ monomer. Helices are light pink, strands are magenta, and loops are grey. The yellow stick represents NAD+. All figures, including protein structures, were drawn using PyMOL software (The PyMOL Molecular Graphics System, http://www.pymol.org). (B) Ribbon diagram of SpLCD/NAD+ dimer. The height of the structure was measured after rotating the structure 90 degrees. (C) Analyti-calgel filtration profile of SpLCD. Standard curve generated using molecular weight markers. The positions of the molecular weight markers for β-amylase, alcohol dehydrogenase, carbonic anhydrase, and cytochrome C are indicated with blue dots. The position of SpLCD is marked with a red dot.\n\nFigure 2: Figure 2. Multi-alignment of SpLCD (UniProtKB/Swiss-Prot accession numberD9UBW0) against LCD from Streptomyces virginiae(UniProtKB/Swiss-Prot accession numberQ8RR22), Streptomyces hygroscopicus(UniProtKB/Swiss-Prot accession numberA0A0A0NQJ4), Streptomyceskanamyceticus (UniProtKB/Swiss-Prot accession numberE9KTB3), Actinoplanes friuliensis(UniProtKB/Swiss-Prot accession numberU5VYY1), Agrobacterium tumefaciens (UniProtKB/Swiss-Prot accession numberQ9R468), Pseudomonas putida(UniProtKB/Swiss-Prot accession numberA0A179QU84), Brucella suis biovar 1(UniProtKB/Swiss-Prot accession numberA9WVR4), Brucella abortus biovar 1 (UniProtKB/Swiss-Prot accession numberC4IUX0), and Neorhizobium galegae by officinallis (UniProtKB/Swiss-Prot accession number A0A0T7GIJ3). Secondary structural elements were assigned using PyMOL and every twentieth residue is marked with a black dot. Strictly (100%) and semi-conserved residues (80%) are highlighted in green and light blue, respectively. Cylinders and arrows above the sequences denote α-helices and β-strands, respectively. Black, magenta, and cyan triangles below the LCD sequences denote L-pipecolic acid, L-proline, and L-DABA, respectively. Black boxes indicate residues interacting with water molecules when LCD or OCD bound its ligands and blue boxes denote residues interact with water molecules when LCD bound its cofactor; NAD+. Red and blue diamonds represent residues in the structures of SpLCD and Pseudomonas putida ornithine cyclodeaminase (PpOCD) that coordinate with NAD+ and NADH, respectively. Residues interacting with L-ornithine in OCD are shown in a pink triangle.\n\nFigure 3: Figure 3. The residues involved in coordination of NAD+ and NADH with SpLCD-NAD+ (PDB entry 5YU0, magenta) and PpOCD-NADH (PDB entry 1U7H, cyan) were compared. Dashed lines represent hydrogen bonds. The residues interacting with NAD+ and NADH are shown in magenta for SpLCD and cyan for PpOCD. Blue dots represent water molecules. A 2Fo-Fc electron density map (1.0 σ) of the NAD+ molecule is presented at the bottom of the figure.\n\nFigure 4: Figure 4. Stereo diagrams of the SpLCD active sites surrounding ligands (A) L-pipecolic acid, (B) L-proline, and (C) L-DABA. Dashed lines represent hydrogen bonds and blue dots indicate water molecules. A 2Fo-Fc electron density map (1.0 σ) for each ligand is shown to the right of each stereo diagram.\n\nFigure 5: Figure 5. (A) The active sites of SpLCD/NAD+/L-DABA and PpOCD/NADH/L-ornithine are shown. The L-ornithine molecule with PpOCD was visualized in the active sites of SpLCD/NAD+/L-DABA by superimposing SpLCD and PpOCD. (B) Proposed catalytic mechanism of SpLCD. Dashed line represents the hydrogen bond between side chain of E63 and water molecule."
      }
    ]
  },
  {
    "id": "PMC5959964_multi",
    "image": [
      "images/PMC5959964-f1.png",
      "images/PMC5959964-f2.png",
      "images/PMC5959964-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Functional characterisation of peroxisomal β-oxidation disorders in fibroblasts using lipidomics\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic overview of peroxisomal β-oxidation and ether phospholipid biosynthesis. a) Metabolism of very long-chain fatty acids (VLCFAs), in particular the enzymes and proteins involved in β-oxidation are shown. Saturated and unsaturated VLCFAs enter the peroxisome as coenzyme A (CoA) esters via the ABC transporter D1 (ABCD1, ALD protein (ALDP)), and alternatively via the ABC transporters D2 (ABCD2), and D3 (ABCD3), respectively, and subsequently undergo one or several rounds of β-oxidation. Each round comprises a cycle of dehydrogenation, hydration, dehydrogenation, and thiolytic cleavage, and results in the production of a 2-carbon-shortened fatty acid and acetyl-CoA. The enzymes involved in β-oxidation of VLCFAs are acyl-CoA oxidase 1 (ACOX1), D-bifunctional protein (DBP), and 3-ketoacyl-CoA thiolase (ACAA1) or sterol carrier protein X (SCPx). b) Biosynthesis of ether phospholipids. The first two reactions of ether phospholipid biosynthesis take place in the peroxisome. First, dihydroxyacetone phosphate (DHAP) is acylated with a fatty acyl-CoA at the sn-1 position by the enzyme glyceronephosphate O-acyltransferase (GNPAT). Next, alkylglycerone phosphate synthase (AGPS) catalyses the exchange of the fatty acyl group of 1-acyl-DHAP for a fatty alcohol. The fatty alcohol is converted from a fatty acyl-CoA outside of the peroxisome and subsequently imported into the organelle, reactions that are performed by fatty acyl reductase 1 (FAR1). The produced 1-O-alkyl-DHAP is then converted to 1-O-alkyl-2-hydroxy-sn-glycerophosphate by the enzyme acyl/alkyl-DHAP reductase (ADHAPR), a process which can occur both in the peroxisome and in the endoplasmic reticulum (ER). The following reactions take place in the ER. The intermediate 1-O-alkyl-2-acyl-sn-glycerol is formed by alkyl/acyl-glycerophosphate transferase, which exchanges the hydroxy group at the sn-2 position of the substrate for an acyl-group. Subsequently, phosphatidic acid phosphatase removes the phosphate group to form 1-O-alkyl-2-acyl-sn-glycerol. Next, PE- and PC-plasmanyl glycerophosphate (GP) species are formed by ethanolamine and choline phosphotranferase, respectively, by incorporation of CDP-ethanolamine and -choline. The alkyl group of PE-plasmanyl-GP is then dehydrogenated by plasmenylethanolamine desaturase to form PE-plasmenyl-GP (PE-plasmalogens). Finally, since no plasmenylcholine desaturase exits, the head group of PE-plasmalogen species is hydrolysed by phospholipase C and subsequently CDP-choline is incorporated by choline phosphotransferase to form PC-plasmalogens\n\nFigure 2: Figure 2. Phospholipid profiles of PED patient fibroblasts. a) Multivariate model of variations phospholipid composition using PLS-DA. Score plot of the model in the plane of the first (X-variate) and second component (Y-variate). The percentage of variance explained by the components is indicated in parentheses. The percentage of predictor variance explained by the full model (RX2) is 0.285; the percentage of response variance (RY2) is 0.242. The predictive performance of the model estimated by cross-validation (Q2Y) is 0.225. b) Left panel: relative abundance of LPC(26:0), right panel: ratio of LPC species containing VLCFAs (≥C24) over LCFAs (≤C22), determined by lipidomics. c) Left panel: total C26:0 levels, and right panel: ratio of total C26:0 over C22:0 levels, measured by derived from GC-MS measurement of total VLCFAs. d) Total phospholipid levels, sorted by phospholipid class. Phosphatidylcholine (PC) and phosphatidylethanolamine (PE), their derivates lyso-PC (LPC) and lyso-PE (LPE) and associated ether phospholipids (PC(O-), LPC(O-), PE(O-), and LPE(O-)). Total levels of other phospholipid classes are shown in Suppl. Fig. 1. Total phospholipid levels are defined as the summation of the relative abundance of all identified phospholipid species of the same class normalised to the corresponding internal standard, assuming identical response with respect to internal standard. Figures in b to d are shown as box-and-whisker plots, with floral-white plots indicating the control group (n = 7), white plots indicating the ACBD5-deficient cell line (n = 3; technical replicates), light gray plots the ACOX1-deficient group (n = 7), dim gray plots the ABCD1-deficient group (n = 7), and dark gray plots the DBP-deficient group (n = 6). One-way ANOVA with Dunnett’s multiple comparisons test was performed to determine significant differences between the groups, when compared to the healthy control group (* p-value <0.05; ** p-value <0.01; *** p-value <0.001; **** p-value <0.0001)\n\nFigure 3: Figure 3. Common and specific ratios for fibroblasts from PED patients. Flowchart for data processing, filtering and selection of common and specific ratios per group. Left panel: processing procedure to obtain ratios. Right panel: statistical restrictions for the different conditions to obtain common ratios for all PED groups when compared to control samples, and specific ratios for affected enzymes located inside the peroxisome (ACOX1- and DBP deficiency) when compared to disorders with the affected enzymes outside the peroxisome (ALD, ACBD5 deficiency) and controls. For both common and specific ratios, three box plots are presented as examples. All ratios are listed in Suppl. Table D. Ratios are shown as box-and-whisker plots, and ratio values are based on the relative abundance of the phospholipid species after normalisation to the corresponding internal standards"
      }
    ]
  },
  {
    "id": "PMC5959966_multi",
    "image": [
      "images/PMC5959966-f1.png",
      "images/PMC5959966-f2.png",
      "images/PMC5959966-f3.png",
      "images/PMC5959966-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Plasma lipidomics as a diagnostic tool for peroxisomal disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Phospholipid profiles in plasma from patients with peroxisomal disorders. a) Score plot of the multivariate model based on PLS-DA depicting variations in phospholipid profiles. Shown are the first (X-variate) and second component (Y-variate) of the model, the percentage of variance explained by the components is indicated in parentheses. b) Un-supervised hierarchical clustering plot of phospholipid species with the highest VIP score as determined by OPLS-DA between plasma samples from ZSD patients and controls. Data were logarithm-transformed, and colors in the heat-map reflect the logarithm of the relative metabolite abundance (z-score): red color indicates higher, and blue color indicates lower values than the mean abundance per metabolite\n\nFigure 2: Figure 2. Differences in phospholipid composition in plasma samples from patients with DBP deficiency. a) Score plot of the multivariate PLS-DA model of plasma samples from patients with DBP deficiency classified by disease severity. The first (X-variate) and second component (Y-variate) of the PLS-DA model are depicted, and the percentage of variance explained by the components is indicated in parentheses. Plasma samples from three very mild type III DBP patients are highlighted (sample no. F, N, and S). b) Left panel: volcano plot of plasma samples from three very mild type III DBP patients as indicated in (a) versus samples from controls. Phospholipid species that were increased in plasma samples from DBP patients when compared to controls are depicted as green dots, and species that were decreased in plasma samples from DBP patients are depicted as red dots. Right panel: two examples of statistically significantly different phospholipid species as shown in the left panel are shown as box-and-whisker plots\n\nFigure 3: Figure 3. Unique phospholipid species in plasma from patients with Refsum disease and AMACR deficiency. a) Representative extracted ion chromatograms of straight-chain and branched-chain fatty acids (highlighted by dotted line). The ratios of the branched-chain peak (sn-1)/straight-chain peak (sn-1) are indicated. b) Scatter plot of the correlation of phytanic acid and branched-chain (sn-1) LPC20:0 levels in plasma samples from patients with Refsum disease (left panel), and pristanic acid and branched-chain (sn-1) LPC(19:0) levels in plasma samples from patients with AMACR deficiency (right panel) are shown. The coefficient of determination (R2) indicates the estimate of goodness of fit of the linear regression model, and the Pearson correlation coefficient (r) indicates the measure of correlation\n\nFigure 4: Figure 4. Correlation of phospholipid species with aberrant metabolites used for diagnosis of peroxisomal disorders. Scatter plots showing the correlations of (phospho)lipid species levels (as indicated for each plot) and total C26:0 levels in plasma samples from ZSD patients, and patients with DBP deficiency; total phytanic acid levels in plasma samples from patients with RCDP and Refsum disease; and total pristanic acid levels in plasma samples from patients with AMACR deficiency. Pearson correlation coefficient (r) indicates the measure of correlation"
      }
    ]
  },
  {
    "id": "PMC6055728_multi",
    "image": [
      "images/PMC6055728-f1.png",
      "images/PMC6055728-f2.png",
      "images/PMC6055728-f3.png",
      "images/PMC6055728-f4.png",
      "images/PMC6055728-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Hepatic PPARα function is controlled by polyubiquitination and proteasome‐mediated degradation through the coordinated actions of PAQR3 and HUWE1\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Paqr3 knockdown lowers hepatic TG contents and enhances PPARα functions in response to fasting. Male C57BL/6 mice (8‐10 weeks old) were injected with adenovirus containing control shRNAs or PAQR3‐specific shRNAs by way of tail vein injection for 7 days, followed by fasting for 18 hours (n = 8 per group). (A) PAQR3 mRNA levels were measured by quantitative real‐time RT‐PCR. (B) Liver TG levels. (C) Oil Red O staining of liver sections from mice. (D‐G) Other liver and serum parameters including NEFAs (D), serum NEFAs (E), serum β‐hydroxybutyrate (F), and serum FGF21 concentrations (G). (H) Relative rate of fatty acid oxidation in the mouse liver. (I) Quantitative real‐time RT‐PCR analysis of genes involved in fatty acid oxidation, lipogenesis, lipid secretion, and lipid uptake in the liver. All data are presented as the mean ± SD. For data shown in panels A‐H: *P < 0.05; **P < 0.01; ***P < 0.001. ns, not significant. For data shown in panel I: *comparison between fed‐control and fed‐shPAQR3 groups; ∧comparison between fed‐control and fasted‐control groups; #fasted‐control and fasted‐shPAQR3 groups; one symbol for P < 0.05, two symbols for P < 0.01; three symbols for P < 0.001.\n\nFigure 2: Figure 2. Liver‐specific deletion of Paqr3 elevates PPARα functions. Male mice with a liver‐specific deletion of Paqr3 (Paqr3−/− mice) and age‐matched flox/flox littermates (wt) at 8‐10 weeks old were fed ad libitum or fasted for 18 hours (n = 8 per group). (A) PAQR3 expression levels were measured by way of real‐time RT‐PCR in the liver. (B) Liver TG contents. (C) Oil Red O staining of liver sections from mice. (D‐G) Other liver and serum parameters including NEFAs (D), serum TG (E), serum NEFAs (F), serum β‐hydroxybutyrate (G), and serum FGF21 concentrations (H). (I) Relative rate of fatty acid oxidation in the liver. (J) Quantitative real‐time RT‐PCR analysis of genes involved in fatty acid oxidation, lipogenesis, lipid secretion, and lipid uptake in the mouse liver. All data shown above are presented as the mean ± SD. For data shown in panels A‐I: *P < 0.05; **P < 0.01; ***P < 0.001. ns, not significant. For data shown in panel J: *comparison between fed‐control and fed‐Paqr3−/− groups; ∧comparison between fed‐control and fasted‐control groups; #fasted‐control and fasted‐Paqr3−/− groups; one symbol for P < 0.05, two symbols for P < 0.01, three symbols for P < 0.001.\n\nFigure 3: Figure 3. PAQR3 regulates PPARα functions in primary hepatocytes. (A) PAQR3 regulates the expression of PPARα target genes in hepatocytes. Primary hepatocytes from wild‐type control or liver‐specific Paqr3 deletion mice were treated with WY14643 (30 μM) as described in the Materials and Methods. The mRNA levels of PAQR3 as well as genes involved in fatty acid oxidation, lipogenesis, lipid secretion, and lipid uptake were measured by way of quantitative real‐time RT‐PCR. (B) PAQR3 modulates fatty acid oxidation in hepatocytes. The cells in panel A were treated with WY14643 (30 μM) or fenofibrate (50 μM) for 24 hours, followed by measurement of the fatty acid oxidation rate. (C) PAQR3 affects lipid accumulation in hepatocytes. The TG concentration was determined in primary hepatocytes as in panel A after incubation with or without oleic acid (OA, 200 μM) for 18 hours. (D) Oxygen consumption is modified by PAQR3. HepG2 cells infected with lentivirus‐containing control shRNAs or PAQR3‐specific shRNAs were analyzed with a Seahorse XF24 extracellular flux analyzer. The basal respiration and respiratory capacity oxygen consumption rates were measured and calculated as averages for each phase. (E, F) PAQR3 regulates ligand‐dependent PPARα transactivation. HepG2 cells that stably expressed ectopic PAQR3 (E) or PAQR3‐shRNA (F) as well as their individual controls through lentiviruses were transiently transfected with the PPAR‐responsive luciferase reporter, followed by treatment with WY14643 (30 μM) for 24 hours as indicated. Luciferase activity was measured in these cells. All data are presented as the mean ± SD. For data shown in panel A: *comparison between control and WY14643 groups; ∧comparison between control and shPAQR3 groups; #shPAQR3 and shPAQR3+WY14643 groups; one symbol for P < 0.05, two symbols for P < 0.01, three symbols for P < 0.001. For data shown in panels B‐F: *P < 0.05; **P < 0.01; ***P < 0.001.\n\nFigure 4: Figure 4. PAQR3 regulates PPARα stability and polyubiquitination. (A‐D) Paqr3 knockdown increases PPARα protein levels without changing its mRNA levels. Lentivirus‐containing control shRNAs or PAQR3‐specific shRNAs were used to infect HEK293T or HepG2 cells, followed by immunoblotting and RT‐PCR to determine PPARα protein and mRNA levels, respectively. HEK293T cells were transiently transfected with PPARα expression plasmids (A, B). Endogenous PPARα was detected in HepG2 cells (C, D). Data are presented as the mean ± SD, ***P < 0.001. (E, F) Paqr3 knockdown elevates PPARα protein stability. The cells used in panels A and C were treated with 100 μg/mL of cycloheximide (CHX) for different lengths of time and then harvested for immunoblotting with the antibodies as indicated. (G) PAQR3 promotes PPARα ubiquitination. HEK293T cells were transiently transfected with HA‐tagged ubiquitin, Myc‐tagged PAQR3, and Flag‐tagged PPARα as indicated. At 24 hours after the transfection, the cells were pretreated with or without MG132 (10 μM) for 6 hours, followed by immunoprecipitation (IP) and immunoblotting (IB) with antibodies as indicated. (H) Paqr3 knockdown decreases endogenous PPARα polyubiquitination. HepG2 cells were stably transfected with lentivirus‐expressing control shRNAs or PAQR3‐specific shRNAs. The cells were pretreated with MG132 (10 μM) for 6 hours, and then the cell lysates were used in IP and IB with the antibodies as indicated.\n\nFigure 5: Figure 5. PAQR3 interacts with PPARα. (A) Cell lysates from HEK293T cells transfected with Flag‐tagged PPARα and/or Myc‐tagged PAQR3 were used for immunoprecipitation (IP) and immunoblotting (IB) with the antibodies as indicated. (B) Interaction of PAQR3 with endogenous PPARα in Hepa1‐6 cells. Hepa1‐6 cells were transiently transfected with Myc‐tagged PAQR3 and the cell lysates were used for IP and IB with the antibodies as indicated. (C‐E) Identification of the structural domains in PPARα and PAQR3 involved in the interaction. HEK293T cells were transiently transfected with the plasmids as indicated, followed by IP and IB with the antibodies as indicated. (F) Direct interaction between PAQR3 and PPARα GST pull‐down assay was used to analyze the in vitro binding of purified His‐tagged PPARα (101‐173 aa) with purified GST‐fused PAQR3 (1‐71 aa)."
      }
    ]
  },
  {
    "id": "PMC6061697_multi",
    "image": [
      "images/PMC6061697-f1.png",
      "images/PMC6061697-f2.png",
      "images/PMC6061697-f3.png",
      "images/PMC6061697-f4.png",
      "images/PMC6061697-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Impaired plasticity of macrophages in X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Transcriptome analysis reveals dysregulation of inflammatory pathways in monocytes of AMN patients. The complete transcriptome of primary CD14+ monocytes from AMN patients and healthy controls was obtained by RNA-Seq. RT-qPCR analysis of pro-inflammatory cytokine (TNFA, IL1B and IL6) expression in AMN and control monocytes cultured for 6 h with either 0.5 or 10 ng/ml LPS. See also Table 1. Left: Representative results of monocytes derived from one AMN patient and a matched healthy control, isolated and treated in parallel. Each bar represents the mean of two independent LPS treatments each measured in two technical replicates. Right: Pairwise comparisons (indicated by lines) of the response to LPS of AMN and corresponding healthy control monocytes isolated and treated in parallel (n = 5 each). The induction is depicted as the fold-increase in relative mRNA levels of TNFA, IL1B and IL6 obtained by high LPS (10 ng/ml) relative to low LPS (0.5 ng/ml) concentration. The mRNA levels were normalized to GAPDH, which is not induced by LPS. *P ≤ 0.05 (Wilcoxon-signed rank test); error bars = standard deviation; P = AMN patient; C = healthy control.\n\nFigure 2: Figure 2. Deregulated gene expression pathways in AMN monocytes are reflected by recruitment of monocytes to perivascular cuffs in AMN spinal cord areas affected by myelopathy. (A) Heatmap of normalized read counts for genes found to be significantly deregulated in these cells. This list includes all genes with an adjusted P-value < 0.1 as determined by either edgeR or DESeq. Genes that were also deregulated in activated monocytes from AMN Patients P1 and P2 are underlined. P = AMN patient; C = healthy control. (B) Light microscopy images taken from the centre of cervical demyelinating lesions in post-mortem AMN spinal cord tissue. Left: Immunohistochemistry for MRP14 (early marker for activated monocytes/macrophages) detects infiltrating monocytes/macrophages. Right: Staining for the phagocytosis marker CD68 reveals the presence of macrophages and microglial cells. See also Table 1.\n\nFigure 3: Figure 3. ABCD1 deficiency does not impair in vitro differentiation and pro- or anti-inflammatory polarization of monocyte-derived macrophages. (A) CD14+ monocytes isolated from the blood of AMN patients or healthy controls were differentiated with either GM-CSF or M-CSF for 7 days and subsequently either activated with LPS plus IFN-γ or IL-4, resulting in pro- or anti-inflammatory activation, respectively, or left untreated for additional 2 days. Pro-inflammatory (MHCII, CD80 and CD86) and anti-inflammatory (CD163, CD206) cell surface marker expression was assessed by flow cytometry. The dashed, vertical line represents the 1% threshold of the isotype control staining of AMN-derived macrophages. Histograms represent one out of three experiments with independent AMN and healthy control donor pairs. (B) Secreted levels of pro-inflammatory cytokines (TNFα, IL-1β, IL12p40 and IL-23) were measured in cell culture supernatants of LPS/IFN-γ activated GM-CSF differentiated macrophages, derived from blood monocytes isolated from three pairs of AMN patients and matched healthy controls and treated in parallel. The results are depicted with the level in patient samples relative to the matched controls (= 100%). (C) The concentrations of C26:0, C22:0 and C16:0 were determined by GC–MS in monocytes and in vitro differentiated and activated macrophages from one AMN patient and a matched healthy control. The relative amounts of C26:0 displayed as ratio to either C22:0 or C16:0 are shown. P = AMN patient; C = healthy control.\n\nFigure 4: Figure 4. Macrophages derived from AMN patients only partially downregulate LPS-induced pro-inflammatory genes upon myelin phagocytosis. CD14+ bloodstream monocytes isolated from AMN patients or healthy controls were differentiated in vitro with M-CSF and subsequently activated with LPS for 24 h before incubation with or without myelin for additional 24 h. (A) The efficiency of myelin phagocytosis in AMN and healthy control macrophages was determined by FACS analysis after incubation with pHrodo®-Red labelled myelin for 6 h or 24 h. The mean fluorescence intensity of macrophages derived from isolated blood monocytes of three AMN patients and three healthy controls is depicted. *P ≤ 0.05, n.s. = not significant (two-tailed unpaired Student’s t-test). (B and C) The relative expression of IL12B/IL-12p40 and TNFA induced by LPS activation was measured by RT-qPCR without (B) or with (C) added myelin. The mRNA levels were normalized to the geometric mean of two reference genes, HPRT and HMG20B, which are not induced by LPS. In C, the normalized mRNA levels of control macrophages without myelin addition was set as 100%. For statistical analyses, logarithmic transformation was used to normalize the IL12B/IL-12p40 dataset. *P ≤ 0.05 (two-tailed unpaired Student’s t-test). P = AMN patient; C = healthy control.\n\nFigure 5: Figure 5. Comparison of pro- and anti-inflammatory polarization markers on monocytes/macrophages and microglia in primary demyelinating CNS lesions in CALD and multiple sclerosis. (A) Primary CALD (Cases 1 and 3, one tissue section per patient; Case 2, two tissue sections; Case 4, three tissue sections; n = 4 cases) and multiple sclerosis brain lesions (one tissue section per patient, n = 6 cases) were stained with antibodies directed against the early activation marker MRP14, the macrophage/microglia phagocytosis marker CD68, the pro-inflammatory surface marker CD86 and the anti-inflammatory surface markers CD206 and CD163. The number of positively stained cells in the centre of primary lesions was counted manually under the light microscope. The cell density is depicted as boxplot (median ± interquartile range) comparisons between multiple sclerosis and CALD. For cases where more than one tissue section was counted, the mean was used for calculation. For statistical analysis, logarithmic transformation was used to normalize the distribution of MRP14 and CD206 positive data sets. *P ≤ 0.05 (two-tailed unpaired Student’s t-test). Coloured dots indicate the cases used for immunohistochemistry in C: red dot = childhood CALD Case 2; yellow dot = adult CALD Case 4; green dot = multiple sclerosis Case 9. (B) Number of cells expressing the activation markers CD86, CD206 and CD163, respectively, in relation to the total number of CD68 positive macrophages in the counted fields. For statistical analysis, logarithmic transformation was used to normalize the ratio data. *P ≤ 0.05 (two-tailed unpaired Student’s t-test). (C) Top row: Classical active multiple sclerosis brain lesion (Case 9); middle row: primary inflammatory childhood CALD brain lesion (Case 2); bottom row: primary inflammatory adult CALD spinal cord lesion (Case 4). The columns show immunohistochemical single staining for MRP14, CD68, CD86, CD206 and CD163, as used for the quantification in A. Arrows point to positive cells for which magnified views are shown in the insets. (D) Double immunohistochemistry for CD86 and CD206 in the same regions as shown in C. Arrowhead points to a double-positive macrophage, representing an intermediate inflammatory phenotype, which was observed in multiple sclerosis but hardly present in the CALD cases. Arrows point to the few CD206-single-positive cells detected in multiple sclerosis and CALD. Scale bars = 50 µm; inset scale bars = 25 µm."
      }
    ]
  },
  {
    "id": "PMC6062720_multi",
    "image": [
      "images/PMC6062720-f1.png",
      "images/PMC6062720-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Long-Term Cholic Acid Therapy in Zellweger Spectrum Disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Liver histology of patient 1 during CA therapy and liver histology of patient 2 before CA therapy. Patient 1: a Portal areas are prominent due to delicate septal fibrosis. Pale pseudonodules are composed of hyperglycogenated hepatocytes (arrow). Trichrome stain, ×50. b Pale hepatocytes with expanded cytoplasm contain excess glycogen, further accentuated in scattered glycogen pseudonodules (arrow). PAS-diastase, ×100. c The portal area contains clusters of macrophages with abundant slate-gray granular cytoplasm highlighted by PAS stain (arrows). PAS-diastase stain, ×400. d Hepatocyte cytoplasm contains excess glycogen granules that displace normal-appearing mitochondria. Peroxisomes are absent. The Kupffer cell (arrow) contains multiple dense polymorphous secondary lysosomes with unusual angulated crystalline profiles. Uranium acetate and lead citrate, ×2,500. Patient 2: e The portal areas are expanded by delicate fibrous septa. Hepatocyte cytoplasmic clarity is due to mild excess of glycogen. Inset: Expanded cytoplasm in a rare Kupffer cell is storage cell-like with needle-shaped linear inclusions. Main panel: Trichrome stain, ×100. Inset: PAS-diastase stain, ×800. CA, cholic acid.\n\nFigure 2: Figure 2. Liver histology of patient 3 before and during CA therapy. Before CA therapy: a Lobular architecture is accentuated by vague pseudonodularity and focal periportal fibrosis. Trichrome stain, ×50. b Hepatocyte cytoplasm is clear and mildly expanded. Nuclear glycogen inclusions are prominent in zone 1. H&E stain, ×200. c All hepatocytes contain mild excess of secondary lysosomes (lipofuscin granules). Scattered portal (arrow) and sinusoidal macrophages contain abundant granular secondary lysosomes. PAS-diastase, ×320. During CA therapy: d Vague pseudonodularity is due to mild delicate periportal incomplete septal fibrosis. Trichrome stain, ×50. e Hepatocyte appearance is unchanged compared to before CA therapy, including prominence of glycogen nuclear pseudoinclusions in zone 1. Macrophages with slate-gray cytoplasm aggregate in the portal zone (arrow). H&E stain, ×200. CA, cholic acid."
      }
    ]
  },
  {
    "id": "PMC6076216_multi",
    "image": [
      "images/PMC6076216-f1.png",
      "images/PMC6076216-f2.png",
      "images/PMC6076216-f3.png",
      "images/PMC6076216-f4.png",
      "images/PMC6076216-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of SCFTIR1/AFBs E3 ligase assembly by S-nitrosylation of Arabidopsis SKP1-like1 impacts on auxin signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. In silicoanalysis of predicted localization and conservation of ASK1 Cys. (A) Cartoon representation of the N-term CUL1-ASK1-TIR1 interaction where Cys residues in ASK1 are represented by green spheres. Detailed views of the interfaces between (B) ASK1-TIR1 and (C) ASK1-CUL1 are shown. ASK1, CUL1 and TIR1 are represented in yellow, blue and red, respectively. S-nitrosylation of Cys residues are modeled and proximal residues are shown as stick models colored by element (yellow: sulphur; cyan: nitrogen; red: oxygen). Crystallographic data from Protein Data Bank were used to build the model, ASK1 (3ogl), TIR1 (2p1q), CUL1 (1ldk). (D) Sequence conservation among SKP family members across phylogeny. Partial sequence alignments of representative SKP1 sequences showing regions including conserved Cys. Residues aligned with ASK1 Cys37, Cys59 and Cys118 are boxed. The phylogenetic tree was constructed using the complete protein sequences. Bootstrap values higher than 60% (1000 replicates over) are shown. Shaded residues correspond to conservation higher than 50%; more intense shading represent higher degree of conservation. (E) Tree of life representing the occurrence of SKP1, CUL1, TIR1 and the conservation of the ASK1 Cys37 residue in the SKP1 homologs. (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.).\n\nFigure 2: Figure 2. S-nitrosylation of recombinant ASK1 recombinant. ASK1 recombinant protein was incubated with increasing concentrations of NO-Cys for 15 min and subjected to biotin-switch assay. S-nitrosylated proteins were detected by immunoblot using an anti-biotin antibody (upper panels). Sypro ruby staining is shown as a loading control (lower panels). Controls of the biotin switch assay minus ascorbate (Asc), minus biotin, minus methyl methanethiosulfonate (MMTS) and with DTT reduction before the biotin switch are shown. (A) Representative experiment and (B) quantification of the biotin signal of three independent experiments are shown. (C) ASK1 recombinant protein was incubated with 100 µM GSNO, 100 µM GSSH and 100 µM H2O2 for 15 min and subjected to redox fluorescence switch assay to detect reversibly oxidized Cys. Modified proteins were detected by their fluorescent maleimide signal (upper panel). Coomassie staining is shown as a loading control (lower panel). (D) Quantification of fluorescence signal of three independent experiments. Different letters indicate a significant difference at P ≤ 0.05 (one way ANOVA, post hoc Tukey).\n\nFigure 3: Figure 3. S-nitrosylation of recombinant ASK1 and its mutants in Cys37, Cys59 and Cys118. (A, B) Double Cys mutants of ASK1 recombinant protein were incubated with (A) 100 µM NO-Cys or (B) 10 µM NO-Cys for 15 min and subjected to biotin switch assay. S-nitrosylated proteins were detected by immunoblot using an anti-biotin antibody (upper panel). Ponceau staining is shown as a loading control (lower panel). The experiment was repeated three times with similar results. Treatment without ascorbate (Asc) reveals the specificity of the biotn switch assay. (C, D) MS/MS spectra showing fragmentation patterns that correspond with ions of the y (blue) and the b (red) series of (C) S-nitrosylated ask1Q27K Cys37 peptide and (D) S-biotinylated ask1Q27K Cys118 peptide. m, methionine sulfoxide.\n\nFigure 4: Figure 4. S-nitrosylation on Cys37 and Cys118 modulates assembly of ASK1 in an SCF E3 ubiquitin ligase complex. (A) Pull-down reactions were performed using in vitro synthesized TIR1-myc and recombinant GST-ASK1 proteins. Reactions were carried out without any addition or in the presence of 100 µM NO-Cys in combination or not with DTT. TIR1 protein was detected using anti-myc antibody. Coomassie blue-stained GST–ASK1 was used as a loading control (lower panel). (B, D) Yeast two-hybrid assays were carried out with cells co-transformed with the indicated constructs and grown on SD–U–H–T selective media plus the addition of 100 and 300 µM SNP and X-Gal to develop β-galactosidase activity. (C, E) Yeast two-hybrid interaction experiments between the different ASK1 Cys mutants, and TIR1-AFB2 or CUL1, respectively. The experiment was repeated at least three times with similar results. (F) Densitometry of yeast two-hybrid activity (n = 3; * p < 0.01, t-test).\n\nFigure 5: Figure 5. ASK1 Cys37 and Cys118 impact on auxin signaling activation. (A) ASK1 WT or its mutants in Cys37, Cys59 and Cys118 were transiently expressed in leaves of 4-week-old N. benthamiana plants. Leaves were sprayed with 10 µM IAA or mock solution as control 24 h post-infiltration. The expression of a subset of early auxin response genes (NbGH3.6 -Niben101Scf13270g03004.1-; NbGH3.2 -Niben101Scf12751g00003.1-; NbGH3.1 -Niben101Scf12751g00003.1-; NbIAA3 -Niben101Scf12159g09021.1-; NbIAA19 -Niben101Scf02572g04006.1-; NbEF-1α -Niben101Scf12941g01003.1-) was analyzed by qPCR 1 h later in three independent experiments. Box-plot (median, 1 –3 interquartile range and 95% confidence interval) of normalized expression of the subset of early auxin response genes relative to EF1. The significance of the effect of auxin treatment and Cys mutation in two-way ANOVA is indicated (post-hoc Dunnet compare to ASK1 *p < 0.05; **p < 0.01). (B) A model for redox regulation of SCFTIR1-AFBs complex assembly. S-nitrosylation of Cys37 and Cys118 residues in ASK1 impacts on its binding with CUL1 and the F-box proteins, TIR1 and AFB2, leading to enhanced SCFTIR1and SCFAFB2 assembly. In addition, S-nitrosylation of TIR1 increases its interaction with Aux/IAA [80]. This redox-mediated complex stabilization augments the ubiquitination/degradation of Aux/IAA proteins which, in turn, directs the activation of auxin-response genes. ASK1, TIR1, CUL1, RBX1 and IAA7 peptide are colored in yellow, red, blue, orange and green, respectively. IAA is shown in grey."
      }
    ]
  },
  {
    "id": "PMC6076216_multi_2",
    "image": [
      "images/PMC6076216-f7.png",
      "images/PMC6076216-f8.png",
      "images/PMC6076216-f9.png",
      "images/PMC6076216-f10.png",
      "images/PMC6076216-f11.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of SCFTIR1/AFBs E3 ligase assembly by S-nitrosylation of Arabidopsis SKP1-like1 impacts on auxin signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. Multiple sequence alignment of ASK proteins of Arabidopsis thaliana. Residues aligned with ASK1 Cys37, Cys59 and Cys118 are boxed. Phylogenetic tree with bootstrap test results (1000 replicates) for the alignment of the complete 21 sequences is shown. Shaded residues correspond to conservation higher than 50%; more intense shading represent higher degree of conservation.\n\nFigure 8: Figure 8. Multiple sequence alignment of rice SKP1 proteins. Residues aligned with ASK1 Cys37, Cys59 and Cys118 are boxed. Phylogenetic tree with bootstrap test results (1000 replicates) for the alignment of the complete 22 sequences is shown. Shaded residues correspond to conservation higher than 50%; more intense shading represent higher degree of conservation.\n\nFigure 9: Figure 9. S-nitrosylation of the ASK1 recombinant protein by NO donors, GSNO and DEANO. ASK1 recombinant protein was incubated with increasing concentrations of (A) GSNO and (B) DEANO for 15 min and subjected to fluorescence switch or biotin switch assay, respectively. S-nitrosylated proteins were detected by their fluorescent maleimide signal (A, upper panel) or immunoblot using an anti-biotin antibody (B, upper panel). Coomassie and Sypro Ruby staining are shown as a loading control (lower panels) in A and B, respectively. The experiment was repeated at least three times with similar results.\n\nFigure 10: Figure 10. S-nitrosylation of recombinant ask1Q27K protein. Recombinant protein ask1Q27K was incubated with 100 µM NO-Cys for 15 min and subjected to biotin switch assay. Control of the biotin switch assay minus ascorbate (Asc) is shown. S-nitrosylated proteins were detected by immunoblot using an anti-biotin antibody (upper panel). Ponceau staining is shown as a loading control (lower panel). The experiment was repeated three times with similar results.\n\nFigure 11: Figure 11. Mass spectrometry analysis of S-glutathionylated Cys37 and Cys118. ask1Q27K recombinant protein was incubated with 10 µM GSNO for 15 min and analyzed by MS after tryptic digestion. MS/MS spectra of S-glutathionylated (A) ask1Q27K Cys37 or (B) Cys118 peptide is shown. Fragmentation patterns that correspond with ions of the y (blue) and the b (red) series are included as inserts."
      }
    ]
  },
  {
    "id": "PMC6076216_multi_3",
    "image": [
      "images/PMC6076216-f12.png",
      "images/PMC6076216-f13.png",
      "images/PMC6076216-f14.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of SCFTIR1/AFBs E3 ligase assembly by S-nitrosylation of Arabidopsis SKP1-like1 impacts on auxin signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 12: Figure 12. Secondary structure analysis of ASK1 and mutated versions. (A) Circular dichroism (CD) far-UV spectra of ASK1 and mutants, ask1C37A and ask1C118A. (B) Coomassie of ASK1 and mutated proteins analyzed by CD. (C) CD far-UV spectra of ASK1 protein S-nitrosylated by 100 µM GSNO (GSH was used as control).\n\nFigure 13: Figure 13. Densitometry of yeast two-hybrid assays carried out in the presence of SNP. (A), (B) Analysis of three independent experiments corresponding to treatments indicated in Fig. 4 B and D, respectively. *p < 0.01, t-test.\n\nFigure 14: Figure 14. Protein-protein interactions of askC118A and ask1C37A with TIR1 and CUL1, respectively. (A) The recombinant GST-ask1C118A protein was used in pull-down reactions with TIR1-myc protein. TIR1-myc protein was detected using anti-myc antibody. Coomassie blue-stained GST-fusion proteins were used as a loading control (lower panel). (B) The recombinant GST-ask1C37A protein was used in pull-down reactions with HIS-N-terminal CUL1 protein. HIS-CUL1 protein was detected using anti-HIS antibody. Coomassie blue-stained GST-fusion proteins were used as a loading control (lower panel). The experiments were repeated at least three times with similar results."
      }
    ]
  },
  {
    "id": "PMC6109082_multi",
    "image": [
      "images/PMC6109082-f1.png",
      "images/PMC6109082-f2.png",
      "images/PMC6109082-f3.png",
      "images/PMC6109082-f4.png",
      "images/PMC6109082-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Dysregulation of the NUDT7-PGAM1 axis is responsible for chondrocyte death during osteoarthritis pathogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. NUDT7, a peroxisomal gene, is suppressed during osteoarthritis (OA) pathogenesis. a Staining with Alcian blue or safranin O and immunohistochemistry of Collagen C1-2C, Aggrecan Neoepitope, and matrix metalloproteinase (MMP)-13 using non-OA and OA cartilage from human patients with OA pathogenesis (n = 5 per group). Scale bar, 50 μm. b Transcription levels of 94 peroxisome-related genes in human OA chondrocytes (n = 15 per group) compared with those in normal chondrocytes (n = 8 per group). c Immunostaining of NUDT7, and the mRNA level of NUDT7 in human OA chondrocytes (n = 20 per group) compared with that in normal chondrocytes (n = 13 per group). Scale bar, 50 μm. d Transcription level of NUDT7 in normal chondrocytes infected with lentivirus containing each NUDT7 short hairpin RNA (shRNA). e Transcription level of matrix-degrading enzymes in normal chondrocytes infected with lentivirus containing an NUDT7 shRNA (shNUDT7) (n = 3). f, g Analysis of cell proliferation (n = 4 per group) and apoptotic cell death (n = 6 per group) in normal chondrocytes infected with lentivirus containing NUDT7 or NUDT7 shRNA. h, i Activities of catalase and glutathione peroxidase (GPx) in normal chondrocytes infected with lentivirus containing NUDT7 or NUDT7 shRNA (n = 6 per group). Values are means + s.d. An unpaired Student’s t test was used for statistical analysis. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001\n\nFigure 2: Figure 2. Nudt7−/− mice have severe cartilage degradation and chondrocyte degeneration. a Staining of Collagen C1-2C, Aggrecan Neoepitope, and matrix metalloproteinase (MMP)-13 of paraffin sections from the articular cartilage of Nudt7+/+ and Nudt7−/− mice (n = 5 per group). Scale bars, 50 μm. b Analysis of cartilage thickness, Mankin score, and chondrocyte number using destabilization of the medial meniscus (DMM)-induced Nudt7+/+ or Nudt7−/− mice under a normal- (NCD) or phytol-enriched diet (PED) from Fig. 2a (n = 5 per group). c Positive cell number of Collagen C1-2C, Aggrecan (ACAN) Neoepitope, and MMP-13 in DMM-induced Nudt7+/+ or Nudt7−/− mice under a NCD or PED from Fig. 2a (n = 5 per group). d Staining of Alcian blue, PMP70, BODIPY493/508 using iMACs of Nudt7+/+ and Nudt7−/− mice at postnatal day 6 under a control (CON) or 50 mM phytol treatment (phytol; n = 5 per group). Scale bars, 10 μm. e Quantification of Alcian blue staining extracted with 6M Guanidine-HCl was measured in 650 nm absorbance (n = 5 per group). f Analysis of apoptotic cell death in iMACs of Nudt7−/− mice at postnatal day 6 under CON or phytol conditions compared with those of Nudt7+/+ mice (n = 6 per group). g Transcription level of MMP-13 and -9, ADAMTS-4 and -5 in CON and phytol in iMACs of Nudt7−/− mice at postnatal day 6 under CON or phytol conditions compared with those of Nudt7+/+ mice (n = 3 per group). Values are means + s.d. A one-way ANOVA was used for statistical analysis (b, c, e and f). Values are means + s.d. An unpaired Student’s t test was used for statistical analysis (g). *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001\n\nFigure 3: Figure 3. NUDT7 deficiency affects glycolysis via upregulation of phosphoglycerate mutase 1 (PGAM1) expression during osteoarthritis (OA) pathogenesis. a Comparison of RNA sequencing between human OA chondrocyte and cartilage of Nudt7−/− mice, and possible pathological signaling pathways using Ingenuity Pathway Analysis (IPA). b Transcription level (ΔCt value) of PGAM1 in human OA chondrocytes (n = 15) compared with that in normal chondrocytes (n = 8). c Immunohistochemistry of PGAM1 in human OA cartilages (n = 5 per group) and cartilages of Nudt7−/− mice (n = 5 per group) under NCD or PED conditions. Scale bars, 50 μm. d Positive cell number of PGAM1 in human OA cartilages (n = 5 per group) and cartilages of Nudt7−/− mice (n = 5 per group) under NCD or PED conditions from Fig. 3c. e–g Analysis of 2-phosphoglycerate, acetyl-CoA, and malonyl-CoA in immature murine articular chondrocytes (iMACs) of Nudt7−/− mice at postnatal day 6 (n = 6 per group). Values are means + s.d. An unpaired Student’s t test was used for statistical analysis. **P < 0.01, ***P < 0.001, ****P < 0.0001\n\nFigure 4: Figure 4. Upregulation of phosphoglycerate mutase 1 (PGAM1) expression induces pro-inflammatory cytokines. a Immunostaining of interleukin (IL)-1β in human OA chondrocyte compared with non-OA chondrocyte (n = 5 per group). b Immunostaining of IL-1β cartilage of DMM-induced Nudt7−/− mice (n = 5 per group). c Transcription levels of IL-1β, -6, and TNFα in iMACs of Nudt7−/− mice at postnatal day 6 under CON and phytol conditions (n = 3 per group). d Immunoblotting of cleaved caspase-3 and -9 with the introduction of PGAM1 into iMACs of Nudt7+/+ mice. e, f Analysis of apoptotic cell death and cell proliferation with the introduction of PGAM1 into iMACs of Nudt7+/+ mice (n = 6 per group). g Transcriptional level of IL-1β, -6, and TNFα in iMACs of Nudt7+/+ mice at postnatal day 6 transfected with PGAM1 dose dependent (n = 3 per group). h Transcriptional levels of MMP-13, COL2A1, ACAN, and COMP transfected with PGAM1. Scale bars, 50 μm. Values are means + s.d. An unpaired Student’s t test was used for statistical analysis. **P < 0.01, ***P < 0.001, ****P < 0.0001\n\nFigure 5: Figure 5. Histone 3 lysine trimethylation (H3K4me3) is involved in the transcriptional activation of phosphoglycerate mutase 1 (PGAM1). a, b Immunohistochemistry of H3K4me3 in human OA cartilage (n = 5 per group; scale bars, 100 μm) and cartilage of Nudt7−/− mice (n = 5 per group; scale bars, 200 μm). c Immunocytochemistry of H3K4me3 and counting of H3K4me3-positive cells in immature murine articular chondrocytes (iMACs) of Nudt7−/− mice (n = 6 per group; scale bars, 100 μm). d H3K4me3 binding assay on the PGAM1 promoter using a chromatin immunoprecipitation (ChIP) assay (n = 3 per group). Values are means + s.d. An unpaired Student’s t test was used for statistical analysis. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001"
      }
    ]
  },
  {
    "id": "PMC6118397_multi",
    "image": [
      "images/PMC6118397-f1.png",
      "images/PMC6118397-f2.png",
      "images/PMC6118397-f3.png",
      "images/PMC6118397-f4.png",
      "images/PMC6118397-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Repertoire of plant RING E3 ubiquitin ligases revisited: New groups counting gene families and single genes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A, Schematic representation of a canonical RING finger domain shows the eight residues involved in zinc coordination as cysteine (C) residues numbered from one to eight as well as the conventional number of amino acids represented by an x between them. Between the third and fourth zinc ligands, one to three residues were considered for all types of RING fingers. Between the fourth and fifth zinc ligands, two to three residues were considered for RING-H2, RING-HC, RING-D and RING-S/T, four to five residues for RING-C2 and seven residues for RING-v. Zinc ligand substitutions C>H, C>D, C>S, C>T or C>G were taken into account. For each RING-type, a consensus and the number of retrieved proteins are shown; data from Stone et al., 2005 was taken from S1 Table. B, Number of genes arranged in families or as a single gene is displayed. Described genes are shown in green and undescribed genes are shown in gray. Described families implied that there is a citation for at least one gene in the family (Table 2).\n\nFigure 2: Figure 2. The tree was generated with the RING finger domain from 508 RING finger polypeptide sequences of A. thaliana by the NJ (left) or ML (right) methods. RING-H2 and RING-HC domains are highlighted in gray and blue shades, respectively. Color codes highlighting RING-v, RING-C2, RING-D, RING-S/T, and RING-G are indicated. Misplaced sequences are denoted with arrowheads followed by the family code name. From proteins that contain two RING domains, the sequence from the domain that is present in all members of the family was used to build the tree (12 out the 38 RING sequences from FCH01, five out the six RING sequences from FCH07, one RING sequence from both LHC01 and LHC04; see S1 Table).\n\nFigure 3: Figure 3. Trees are displayed that were generated by the NJ method (A, C) and the ML method (B, D) from 258 A. thaliana RING-H2 (A, B) and 197 RING-HC domain sequences (C, D). A wide range of colors were used to distinguish each family. Misplaced sequence are denoted with arrowheads followed by the family name.\n\nFigure 4: Figure 4. Three regions of multiple consensus sequences alignment from the 41 RING-H2 or the 49 RING-HC groups that encompass the residues involved in zinc ligation are displayed. The circled numbers indicate the residues involved in zinc ligation. The amino acid length of three regions from the RING finger domain is shown: five residues encompassing ligands 1 and 2; 14 to 17 residues from the central region encompassing ligands 3, 4, 5 and 6; and five residues encompassing ligands 7 and 8. The shaded blocks indicate common residues to most RING fingers; J corresponds to any hydrophobic residue. The location of proline residues previously described in ATL and BTL families is enclosed by a rectangle. The symbol * denotes regions that deviate in length from the canonical sequence (FHC01, two extra residues; FHC02, two extra residues; FHC03, two extra residues in 50% of the proteins; FCH10, three proteins show the canonical distances and two proteins show an extra residue between the 4th histidine and 5th cysteine; FHC21, two extra residues). The symbol ** represents the alignment denoting a substitution of one of the zinc ligation residues in all members of the family (FHH11, C to D; FHC05, C to H). The underscore indicates a gap within the alignment.\n\nFigure 5: Figure 5. An alignment of four sequence LOGOs that include the GLD and GLD-like conserved motifs obtained from RING-H2 or RING-D finger proteins (from top to bottom: LOGO #4, #11, #173, and #2 FD; see S3 Table). The location of sequence homology among LOGOs is highlighted by the blue square in the diagram representation. Except for Group LHH15, in all cases the LOGO sequences were located upstream and adjacent to the RING domain. The average distance between the LOGO and the start of the RING finger domain is presented in numbers of amino acids (aas). The symbol * depicts groups for which at least 50% of the members included sequence LOGO #4."
      }
    ]
  },
  {
    "id": "PMC6118397_multi_2",
    "image": [
      "images/PMC6118397-f6.png",
      "images/PMC6118397-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Repertoire of plant RING E3 ubiquitin ligases revisited: New groups counting gene families and single genes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The phylogenetic relationship between thirteen viridiplantae (two green algae and eleven embryophyta), thirteen animal (six vertebrates, three basal animals, two basal vertebrates, two invertebrates), two fungal, and two protist genomes was based on data from the National Center of Biotechnology Information (NCBI) taxonomy server (http://www.ncbi.nlm.nih.gov/Taxonomy). The color code for a selected group of organisms is displayed at the branches. The identifiers for each RING-type are displayed in S1 Table and a list of retrieved genes in S4 Table. The total number of RING finger proteins is shown at the last column.\n\nFigure 7: Figure 7. A heat map shows the number of proteins in each of the 107 RING groups. The fprequency of RING proteins is shown according to a pale green-red scale. The species tree is shown in Fig 6. A detailed distribution of RING identifiers within the groups is displayed in S4 Table."
      }
    ]
  },
  {
    "id": "PMC6154794_multi",
    "image": [
      "images/PMC6154794-f1.png",
      "images/PMC6154794-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Importance and usage of chromosomal microarray analysis in diagnosing intellectual disability, global developmental delay, and autism; and discovering new loci for these disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Presentation of CNV’s on Chromosome Ideogram with Major Clinical Findings. (Deletions: red, duplications: green) The figure was created via Microsoft® PowerPoint software\n\nFigure 2: Figure 2. Case 23 with 22q11.2 homozygote duplication. a Pedigree of the family. b Dysmorphic features of the case 23. c Note the overfolded helix. d MLPA shows tetrasomy of 22q11.2 region. e T2 weighed MRI shows basillar impression and hypoplasia of clivus"
      }
    ]
  },
  {
    "id": "PMC6182659_multi",
    "image": [
      "images/PMC6182659-f1.png",
      "images/PMC6182659-f2.png",
      "images/PMC6182659-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The peroxisome: an update on mysteries 2.0\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic overview of the molecular machineries and proteins localized at the membranes of peroxisomes in mammals. Adapted from Schrader and Fahimi (2008). See text for further details. Matrix protein import: after synthesis on free ribosomes, cargo proteins containing the peroxisomal targeting signals PTS1 or PTS2 bind to the corresponding cytosolic receptors Pex5 or Pex7 and form receptor–cargo complexes. The Pex7–cargo complex requires accessory factors for import (Pex5pL, a long isoform of Pex5p, in mammals and plants, Pex18p and Pex21p in S. cerevisiae, Pex20p in Neurospora crassa, Yarrowia lipolytica, and Hansenula polymorpha). Pex9 is a new Pex5-like yeast peroxisomal targeting receptor. Import is achieved by a complex set of integral or peripheral PMPs that form the matrix protein import machinery, which mediates docking of the cargo-bound import receptor at the peroxisomal membrane, cargo translocation into the matrix of the organelle by a dynamic translocon, and export of the receptor back to the cytosol. Recycling of the receptor involves its ubiquitination (ub) and extraction from the membrane by an AAA–ATPase complex (Pex1, Pex6). Pex4 is an ubiquitin-conjugating enzyme that is bound to Pex22. Pex6 binds to Pex15 in S. cerevisiae or to Pex26 in humans. The DnaJ-like protein Djp1p assists in matrix protein import. Membrane assembly and insertion of PMPs (containing an mPTS) depend on Pex19, Pex3 and Pex16. Pex19 functions as a cycling receptor/chaperone, which binds the PMPs in the cytosol and interacts with Pex3 at the peroxisomal membrane. Yeast Pex36 is a new functional homolog of mammalian Pex16. Proliferation, growth and division: Pex11α, Pex11β and Pex11γ are involved in the regulation of peroxisome size and number (proliferation) in mammals. In Y. lipolytica (Pex23, Pex24) and S. cerevisiae (Pex25, Pex27-Pex32, Pex34, Pex35) several other peroxins have been identified which influence the size and number or organization of peroxisomes. Mammalian Pex11β remodels the peroxisomal membrane and interacts with the membrane adaptors Mff and Fis1, which recruit the dynamin-like fission GTPase Drp1 (DRP3A in plants, Vps1p, Dnm1p in S. cerevisiae) to peroxisomes, which is activated by Pex11β. Additional adaptor proteins are involved in yeast (Mdv1, Caf4) and plants (PMD1; see text). Motility and inheritance: mammalian peroxisomes move along microtubules, and Miro1 serves as membrane adaptor for the microtubule-dependent motor proteins kinesin and dynein. Inp1 and Inp2 are involved in the inheritance and motility of peroxisomes in S. cerevisiae and Y. lipolytica. Inp2 is the membrane receptor for the type V myosin motor Myo2 on peroxisomes, which drives peroxisomes along actin filaments. The GTPase Rho1 binds to Pex25 and is involved in the recruitment of actin to peroxisomes in S. cerevisiae. Tethering: ACBD5 and ACBD4 interact with ER-resident VAPA/B to mediate peroxisome–ER contacts in mammals. In yeast, Inp1, Pex3, Pex30 and Pex34 are involved in inter-organelle contacts (ER and mitochondria) (see also Fig. 3). Metabolite transport: uptake of fatty acids is mediated by ABC transporter proteins (ABCD1-3 in mammals; Pxa1-2 in yeast) (ALD, adrenoleukodystrophy protein; ALDR, ALD-related protein). Other transporter and membrane proteins/enzymes: OCTN3, organic cation/carnitine transporter 3; MCT1/2, monocarboxylate transporter 1/2; Opt2, yeast oligopeptide transporter (Elbaz-Alon et al. 2014); PMP52 (Tmem135) and PMP24 (PxmP4) belong to the Tim17 family (Žárský and Doležal 2016); members of the PMP22 family are Mpv17, Mpv17-like (ML-P), S. cerevisiae Sym1 (mitochondrial) and WSC (Woronin body sorting complex) in N. crassa; ACSL1/4, acyl-CoA synthetase long chain family member 1/4; Ant1, peroxisomal adenine nucleotide transporter 1; mARC2 (Mosc2), mitochondrial amidoxime reducing component 2; ATAD1/Msp1, ATPase family AAA (ATPase associated with various cellular activities) domain-containing protein 1; Atg37, autophagy-related protein 37 (Nazarko et al. 2014); FALDH, fatty aldehyde dehydrogenase (Costello et al. 2017a, b, c); FAR1, fatty acyl-CoA reductase 1 (ether lipid biosynthesis); GDAP1, ganglioside-induced differentiation-associated protein 1; MAVS, mitochondrial antiviral signalling protein; TRIM37, tripartite motif-containing protein 37; USP30, ubiquitin-specific protease 30 (Marcassa et al. 2018). Proteins with a dual localization to both peroxisomes and mitochondria are marked with an asterisk. Pex, peroxin; PMP, peroxisomal membrane protein\n\nFigure 2: Figure 2. Schematic overview of the molecular machineries and proteins localized at the membranes of yeast peroxisomes. Adapted from (Schrader and Fahimi 2008). See legend Fig. 1 and text for further details\n\nFigure 3: Figure 3. Contact zones between peroxisomes and other organelles described in mammals and yeast species. Identified tethering complexes and (hypothetical) associated functions are shown next to the symbolized interactions. a In mammalian species, peroxisome interactions have been reported for the ER (Costello et al. 2017; Hua et al. 2017), mitochondria (Neuspiel et al. 2008; Braschi et al. 2010; Fan et al. 2016), lysosomes (Chu et al. 2015), lipid droplets (Schrader 2001; Valm et al. 2017), peroxisomes themselves (Bonekamp et al. 2012) and the ER + mitochondria in triple contacts (Horner et al. 2015). b For yeasts, peroxisome interactions have been described for the plasma membrane (Shai et al. 2018), the ER (Knoblach et al. 2013; Mast et al. 2016), mitochondria (Mattiazzi Ušaj et al. 2015; Shai et al. 2018), the vacuole (Shai et al. 2018), lipid droplets (Binns et al. 2006) and ER + mitochondria (Cohen et al. 2014). PO, peroxisomes; MITO, mitochondria; LD, lipid droplets"
      }
    ]
  },
  {
    "id": "PMC6189217_multi",
    "image": [
      "images/PMC6189217-f1.png",
      "images/PMC6189217-f2.png",
      "images/PMC6189217-f3.png",
      "images/PMC6189217-f4.png",
      "images/PMC6189217-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin ligase TRIM25 regulates adipocyte differentiation via proteasome-mediated degradation of PPARγ\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Silver staining of PPARγ and its associated proteins. FLAG-tagged PPARγ was purified using FLAG M2 agarose. b The PPARγ complexes were immunopurified from adipocytes, and endogenous TRIM25 was detected by western blotting. c GST-fused fragments of PPARγ (A/B, LBD, DBD/H, and FL) were incubated with cell lysates containing TRIM25. The GST-fragment complexes were analyzed by western blotting. d HA-tagged deletion mutants of TRIM25 were generated and expressed with PPARγ in HEK-293 cells. From the HA-TRIM25 complexes, PPARγ was analyzed by western blotting\n\nFigure 2: Figure 2. a, b TRIM25 represses the transcriptional activity of PPARγ. HEK-293 cells were transfected with TRIM25WT and TRIM25CS with PPARγ (a) or siRNAs against TRIM25 (#1 and #2) with PPARγ (b) with or without rosiglitazone. Cells were analyzed with a luminometer (n = 3). c The TRIM25 protein level was increased by TRIM25 siRNAs in HCT116 cells. The PPARγ and TRIM25 protein levels were analyzed by western blotting, and their mRNA levels were analyzed by real-time quantitative PCR (RT-qPCR) (n = 3). d HEK-293 cells were transfected with PPARγ, TRIM25WT, or TRIM25CS. The interaction between TRIM25 and PPARγ was analyzed by western blotting. Relative PPARγ protein levels were measured using ImageJ (bottom graphs). e HEK-293 cells were transfected with TRIM25WT or TRIM25CS with PPARγ in dose-dependent manner. Indicated proteins were measured by western blotting. f HEK-293 cells were transfected with TRIM25WT with PPARγ in dose-dependent manner with or without MG132 (10 μM for 6 h). The indicated proteins were measured by western blotting. All error bars shown are the s.e.m. (*p < 0.05, **p < 0.01, ***p < 0.001)\n\nFigure 3: Figure 3. HCT116 cells were transfected with TRIM25WT and TRIM25CS (a) or siRNAs against TRIM25 (#1 and #2) (b) in the presence or absence of CHX (50 μg/ml for the indicated time). The indicated proteins were measured by western blotting. Relative PPARγ protein levels were measured using ImageJ (bottom graphs)\n\nFigure 4: Figure 4. a 3T3-L1 cells were stably expressed with TRIM25WT or TRIM25CS and differentiated for 6 days. Cells were treated with MG132 for 6 h. Cell lysates were incubated with an α-PPARγ antibody, and ubiquitination of PPARγ was analyzed by western blotting. b HEK-293 cells were transfected with TRIM25WT or TRIM25CS. Cell lysates were incubated with an α-FLAG antibody, and ubiquitination of PPARγ was analyzed by western blotting. c Ubiquitination of PPARγ by TRIM25 in vitro. Purified GST-tagged PPARγ was incubated with E1, E2, ubiquitin (Ub), TRIM25WT, or TRIM25CS in the absence and presence of ATP as indicated. Ubiquitination of PPARγ was analyzed by western blotting using the indicated antibodies\n\nFigure 5: Figure 5. a Immunoblot analysis of TRIM25, PPARγ, and adipogenic markers during 3T3-L1 cell differentiation. Relative TRIM25 protein levels were measured using ImageJ (bottom graphs). b Real-time quantitative PCR analysis of the mRNA expression of TRIM25, PPARγ, and adipogenic markers during 3T3-L1 cell differentiation. c Immunoblot analysis of TRIM25 and PPARγ in white adipose tissue (WAT) of normal chow-fed (NC) vs. high-fat-fed (HFD) mice. d Immunoblot analysis of TRIM25 and PPARγ in WAT of control vs. ob/ob mice. Relative TRIM25 and PPARγ protein levels were measured using ImageJ (right graphs). e Pearson correlation coefficients between TRIM25 and PPARγ levels within human subcutaneous fat samples were calculated. All error bars shown are the s.e.m. (*p < 0.05, **p < 0.01, ***p < 0.001)"
      }
    ]
  },
  {
    "id": "PMC6189217_multi_2",
    "image": [
      "images/PMC6189217-f6.png",
      "images/PMC6189217-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin ligase TRIM25 regulates adipocyte differentiation via proteasome-mediated degradation of PPARγ\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Stably expression of TRIM25WT and TRIM25CS (a–c) or shRNAs (#1 and #2) for TRIM25 (d–f) in 3T3-L1 pre-adipocytes was induced for 6 days. a, d Differentiated cells were stained by Oil Red O. b, e The protein expression of TRIM25, PPARγ, and adipogenic markers was analyzed by western blotting. c, f The mRNA expression of adipogenic markers was analyzed by real-time quantitative PCR. All error bars shown are the s.e.m. (*p < 0.05, **p < 0.01, ***p < 0.001)\n\nFigure 7: Figure 7. TRIM25-knockout MEFs were induced for adipocyte differentiation. a Differentiated cells were stained with Oil Red O. b The mRNA expression of adipogenic markers was analyzed by real-time quantitative PCR. c The protein expression of TRIM25, PPARγ, and adipogenic markers was analyzed by western blotting. Relative PPARγ protein levels were measured using ImageJ (bottom graphs). All error bars shown are the s.e.m. (*p < 0.05, ***p < 0.001)"
      }
    ]
  },
  {
    "id": "PMC6203080_multi",
    "image": [
      "images/PMC6203080-f1.png",
      "images/PMC6203080-f2.png",
      "images/PMC6203080-f3.png",
      "images/PMC6203080-f4.png",
      "images/PMC6203080-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Identification and Localization of Peroxisomal Biogenesis Proteins Indicates the Presence of Peroxisomes in the Cryptophyte Guillardia theta and Other “Chromalveolates”\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. —Pex7-binding site and domain structure of Pex5. (A) Alignment of the Pex7-binding domain identified in Guillardia theta with corresponding sequences from Homo sapiens and Arabidopsis thaliana. Each motif contains four highly conserved amino acids: Lys2, Ser6, Phe11, and Gly18. (B) Structural alignment of identified “chromalveolate” Pex5 sequences with indicated functional domains detected via NCBI conserved domain search. (C) Structural alignment of Pex5 from the model plant Arabidopsis thaliana. Numbers indicate amino acid positions. Abbreviations: Gt, Guillardia theta; Hs, Homo sapiens; At, Arabidopsis thaliana; Eh, Emiliania huxleyi; Pt, Phaeodactylum tricornutum; Es, Ectocarpus siliculosus, Cv, Chromera velia; WxxxF/FxxxW, putative Pex14/Pex13 interaction sites; TPR, tetratricopeptide repeat.\n\nFigure 2: Figure 2. —Localization studies of Phaeodactylum tricornutum Pex16-GFP via confocal and electron microscopy. (A) A confocal microscopic analysis of the Pt_Pex16-GFP expression in P. tricornutum (two clones) revealed that the fusion protein localized in small dot-like structures near the complex plastid, which are typical for a peroxisomal localization. TL, transmitted light; PAF, plastid autofluorescence; GFP, green fluorescent protein; Merge, overlay of PAF and GFP. (B) Transmission electron microscopy with a Pex16-GFP overexpressing P. tricornutum clone showed a specific labeling of two electron dense circular structures (arrowhead) near the mitochondrion and complex plastid of the diatom. Pt, Phaeodactylum tricornutum; M, mitochondrion; P, plastid; PM, plasma membrane.\n\nFigure 3: Figure 3. —Heterologous localization studies of Guillardia theta peroxin-GFP fusion proteins in Phaeodactylum tricornutum. With the exception of the cytosolic PTS2 receptor Pex7, all G. theta peroxins expressed as fusion proteins with C-terminal GFP localized to small dot-like structures within P. tricornutum, most likely representing peroxisomal structures. Please see supplementary figures S3–S5, Supplementary Material online, for further information about observed localization patterns of G. theta peroxins in P. tricornutum and the effect of GFP positioning on targeting. TL, transmitted light; PAF, plastid autofluorescence; GFP, green fluorescent protein; Merge, overlay of PAF and GFP.\n\nFigure 4: Figure 4. —Transmission electron microscopic investigation of the Guillardia theta Pex16-GFP localization in Phaeodactylum tricornutum. Cross-section of a P. tricornutum cell expressing Gt_Pex16-GFP. The white arrowhead indicates a specifically immunogold-labeled electron dense structure in proximity to the nucleus and complex plastid, most likely representing a peroxisome (see fig. 2B for comparison). Gt, Guillardia theta; M, mitochondrion; P, plastid; PM, plasma membrane.\n\nFigure 5: Figure 5. —Phylogenetic analysis of Pex4. The tree shown is the consensus tree obtained with Phylobayes 4.1 with ML bootstrap values (left) and Bayesian posterior probabilities (right) mapped onto the nodes. Bootstrap values >50% are shown, while only posterior probabilities >0.6 are indicated. The tree is midpoint rooted and the scale bar shows the inferred number of amino acid substitutions per site. Sequences are colored according to their taxonomic affiliation (see box)."
      }
    ]
  },
  {
    "id": "PMC6203080_multi_2",
    "image": [
      "images/PMC6203080-f6.png",
      "images/PMC6203080-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Identification and Localization of Peroxisomal Biogenesis Proteins Indicates the Presence of Peroxisomes in the Cryptophyte Guillardia theta and Other “Chromalveolates”\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. —Phylogenetic analysis of Pex5. The tree shown is the consensus tree obtained with Phylobayes 4.1 with ML bootstrap values (left) and Bayesian posterior probabilities (right) mapped onto the nodes. Bootstrap values >50% are shown, while only posterior probabilities >0.6 are indicated. The tree is midpoint rooted and the scale bar shows the inferred number of amino acid substitutions per site. Sequences are colored according to their taxonomic affiliation (see box).\n\nFigure 7: Figure 7. —Model for peroxisomal protein import in Guillardia theta and other “chromalveolates.” (A) Soluble peroxisomal PTS1 or PTS2 proteins are recognized by receptor proteins—Pex5 or Pex7—in the cytoplasm. Whereas the Pex5-PTS1-cargo-complex is able to bind the docking complex (Pex14) by means of internal Pex14 interaction sites (WxxxF/Y) to generate a transient pore to transfer the cargo into the peroxisomal matrix, Pex7 requires a coreceptor (Pex5 including a Pex7-binding domain) for cargo transport. After release of the cargo into the peroxisomal matrix, Pex5 is ubiquitinated by the RING complex, consisting of the E3 ubiquitin ligases Pex2, Pex10, and Pex12 together with the ubiquitin conjugating enzyme Pex4 (which might also play further roles aside from peroxisomal protein import) and its membrane anchor Pex22, and extracted into the cytoplasm. The latter step is energy-dependent and performed by the action of the two homo-hexameric AAA-ATPases Pex1 and Pex6. Back in the cytoplasm, the PTS1 receptor Pex5 is either degraded by the proteasome (polyubiquitinated Pex5, not shown), or deubiquitinated (monoubiquitinated Pex5) and recycled to enter a new round of peroxisomal protein import. Note that some “chromalveolates” (diatoms and haptophytes) do not contain a PTS2 import pathway (Pex7 absent, Pex14 lacking as well or highly derived). (B) Model for peroxisomal membrane protein import: The receptor for membrane proteins of peroxisomes might bind its substrates (PMP) in the cytoplasm to transfer the proteins into the peroxisomal membrane by an unknown mechanism after docking to the internal membrane protein Pex3 (and perhaps Pex16, membrane integration unclear). The farnesylation of G. theta and/or “chromalveolate” Pex19 is hypothetical. Numbers indicate peroxins (Pex). Note that G. theta isoforms of Pex19 and Pex11 were omitted from the model for simplicity. Abbreviations: PTS1/2, peroxisomal targeting signal type 1/2; PM, peroxisomal membrane; PMP, peroxisomal membrane protein. Parts of the figure were adapted from Kim and Hettema (2015)."
      }
    ]
  },
  {
    "id": "PMC6238561_multi",
    "image": [
      "images/PMC6238561-f1.png",
      "images/PMC6238561-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Giant Axonal Neuropathy: Clinical, Radiological, and Genetic Features\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Characteristic hair seen in the three patients\n\nFigure 2: Figure 2. Magnetic resonance imaging brain. (a-c) T2-weighted axial section, T2-weighted sagittal section, and fluid-attenuated inversion recovery axial section of patient 2 showing demyelination in frontoparietal and cerebellar white matter. Cavum septum pellucidum is seen. Dentate nucleus and globus pallidus hyperintensities are appreciated. (d) Extensive periventricular white matter hyperintense changes seen on fluid-attenuated inversion recovery axial section of patient 1. (e and f) Fluid-attenuated inversion recovery axial sections show involvement of dentate nucleus and parieto-occipital white matter in patient 3"
      }
    ]
  },
  {
    "id": "PMC6245796_multi",
    "image": [
      "images/PMC6245796-f1.png",
      "images/PMC6245796-f2.png",
      "images/PMC6245796-f3.png",
      "images/PMC6245796-f4.png",
      "images/PMC6245796-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"TRIM59 promotes breast cancer motility by suppressing p62-selective autophagic degradation of PDCD10\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) The fold change of TRIM family genes across 12 cancer types (y-axis) compared with their paired controls (obtained from adjacent non-tumorigenic tissues) based on TCGA dataset analysis. The color intensity indicates the range of fold change, and black boxes indicate a significant difference in gene expression between tumor and adjacent non-tumorigenic tissues (fold change > 1.5 and P value < 0.05). Upper bars show the frequency of cancer types, with up-regulation (red) and down-regulation (blue) for each TRIM family gene. Top hit TRIM59 was highlighted by red arrowhead. (B) Quantitative analysis of TRIM59 IHC staining in 87 paired tumor/non-tumor samples. (C) Representative IHC staining images of adjacent normal tissues and breast cancerous tissues probed with the anti-TRIM59 antibody. A total of 154 patient samples were stained and analyzed. (D) Analysis of TRIM59 staining intensity in association with clinical stages of breast tumor samples (Grade I, n = 18; Grade I–II, n = 26; Grade II and higher, n = 110). An IHC score less than or equal to 0.75 was defined as “Low IHC ratio” or Down-regulation/No change and a value greater than 0.75 was defined as “High IHC ratio” or Up-regulation. (E) Kaplan–Meier survival curves for breast cancer patients based on the scores of TRIM59 IHC staining. High intensity of TRIM59 immunostaining strongly associates with poor patient survival, P = 0.0244. Data in B and D are presented as means ± SD; *P < 0.05, **P < 0.01, ***P < 0.001. The underlying data can be found in S1 Data. BLCA, urothelial bladder cancer; BRCA, breast invasive carcinoma; COAD, colon adenocarcinoma; ESCA, esophageal carcinoma; HNSC, heck and neck squamous cell carcinoma; IHC, immunohistochemistry; KIRC, kidney renal clear cell carcinoma; KIRP, kidney renal papillary cell carcinoma; LIHC, liver hepatocellular carcinoma; LUAD, lung adenocarcinoma; LUSC, lung squamous cell carcinoma; STAD, stomach adenocarcinoma; TCGA, the Cancer Genome Atlas; THCA, thyroid carcinoma; TRIM, tripartite motif.\n\nFigure 2: Figure 2. (A) IB analysis of TRIM59 expression in the noncancerous mammary epithelial cell line (MCF10A) and breast cancer cell lines (MCF7 and MDA-MB-231). (B and C) IB analysis of TRIM59 expression in shRNA or CRISPR/Cas9 lentivirus-transduced control, TRIM59 KD (shTRIM59-2, KD efficiency confirmed by qPCR; B, middle) and TRIM59 KO MCF7 (B, left), or TRIM59-overexpressing (OE) MDA-MB-231 stable cells (C). sgRNA targeting TRIM59 was confirmed by Sanger sequencing (B, right). A dinucleotide GT insertion (underlined) caused an early abortion of TRIM59 translation, as further validated by immunoblotting (B, lane 4). (D and E) Graphic representation of 96-hour MTS proliferation assays of WT (non-transduced), control (transduced with non-targeting shRNA/sgRNA), shTRIM59 and TRIM59 KO MCF7 cells (D), and WT or TRIM59 OE MDA-MB-231 cells (E). (F and G) Colony formation assay in 3D Matrigel culture was performed to assess the rate of colony formation of control, shTRIM59, and TRIM59 KO MCF7 cells at day 8 (F) or WT and TRIM59 OE MDA-MB-231 cells at day 4 (G). Bar graphs show the number of colony-forming units (n = 8). Scale bars: 100 μm. (H and I) Scratched wound healing assays were performed to assess the rates of migration for control, shTRIM59, and TRIM59 KO MCF7 cells at 72 hours (H) or WT and TRIM59 OE MDA-MB-231 cells at 36 hours (I). Bar graphs show the percentage of migration rate (n = 8). Scale bars: 100 μm. (J and K) Transwell invasion assay was performed in Matrigel-coated 8-μm pore size transwell plates to assess the invasion ability of control, shTRIM59, and TRIM59 KO MCF7 cells (J) or WT and TRIM59 OE MDA-MB-231 cells (K). Bar graphs show the numbers of invaded cells (n = 8). Scale bars: 100 μm. Data in B, D-K are presented as means ± SD; *P < 0.05, **P < 0.01 versus controls. The underlying data can be found in S1 Data. CRISPR/Cas9, clustered regularly interspaced short palindromic repeats (CRISPR)-associated protein-9 nuclease; IB, immunoblot; KD, knockdown; KO, knockout; MTS, 3-(4,5-dimethylthiazol-2-yl)-5-(3-carboxymethoxyphenyl)-2-(4-sulfophenyl)-2H-tetrazolium; OD, optical density; OE, overexpressing; qPCR, quantitative polymerase chain reaction; sgRNA, single guide RNA; shRNA, short hairpin RNA; TRIM59, tripartite motif 59; WT, wild-type.\n\nFigure 3: Figure 3. (A and B) Representative tumor images (A) and tumor volume at indicated time points (B) in nude mice that were orthotopically injected into mammary fat-pad with control (non-targeting shRNA) or shTRIM59 MCF7 cells (1 × 107 cells/mouse). n = 9 mice per group. (C and D) Representative tumor images (C) and tumor size quantification at indicated time points (D) in NSG mice that were orthotopically injected into mammary fat-pad with control and TRIM59 OE MDA-MB-231 cells (5 × 106 cells/mouse). n = 5 mice per group. (E and F) Representative image of shControl or shTRIM59 MCF7 xenografts (E) and control or TRIM59 OE MDA-MB-231 (F) xenograft tumors stained with HE and Ki-67. Scale bars: 20 μm. (G) Cell cycle analysis on Control, shTRIM59, and TRIM59 KO MCF7 cells by flow cytometry. The population of cells at each stage was shown in the bar graph. n = 6. **P < 0.01 versus control. (H and I) Apoptotic assessment of shControl, shTRIM59, and TRIM59 KO MCF7 cells. Apoptosis was assayed with Annexin V/7-AAD staining and measured by flow cytometry (H). Statistical analysis of cell populations at early or late stages of apoptosis (I). Live, 7’AAD−AnnexinV−; Early, 7’AAD−AnnexinV+; Late, 7’AAD+AnnexinV+. n = 6. (J) Representative images of cleaved-caspase3 expression in paraffin sections from xenograft tumors made of shControl or shTRIM59 MCF7 cells (top) and WT or TRIM59 OE MDA-MB-231 cells (bottom). n = 6. Scale bars: 10 μm. (K) IB analysis of cell cycle/apoptosis regulators (p53 and MAP kinase pathway members) expression in shControl or shTRIM59 MCF7 cells. Data in B, D, G, and I are presented as means ± SD. *P < 0.05, **P < 0.01 versus controls. The underlying data can be found in S1 Data. Casp3, caspase3; HE, hematoxylin–eosin; Ki-67, marker of proliferation; KO, knockout; MAP, mitogen-activated protein; NSG, NOD scid gamma; OE, overexpressed; p-ERK, phosphorylation of extracellular signal–regulated kinase (ERK); p-JNK, phosphorylation of c-Jun N-terminal kinase (JNK); p-P38, phosphorylation of P38 MAP kinase; p53, tumor protein 53; shRNA, short hairpin RNA; TRIM59, tripartite motif 59; WT, wild-type.\n\nFigure 4: Figure 4. (A) Representative images of cell morphology changes upon TRIM59 deletion (T59 KO) in MCF7 cells (upper, left) or overexpression (T59 OE) in MDA-MB-231 cells (bottom, left). Scale bars: 20 μm. Quantification of the cell area of MCF7 (upper, right) and MDA-MB-231 cells (bottom, right). n = 6. (B) Representative confocal images of MCF7 cells depleted of TRIM59 and stained for F-actin, pSer19-MLC, and E-cadherin. Scale bars: 20 μm. (C) IB analysis of E-cadherin, pSer19-MLC expression in WT and TRIM59-KO MCF7 cells. (D) Representative confocal images of TRIM59 overexpressing (T59 OE) MDA-MB-231 cells with IRES-GFP stained for pSer19-MLC (red). Scale bars: 10 μm. (E) Representative confocal images of p-ERM expression (green) in WT and TRIM59-deleted MCF7 cells. Scale bars: 10 μm. (F) IB analysis of p-ERM and total ERM levels in WT, TRIM59 KD, or TRIM59 KO MCF7 cells (lanes 1–3) and WT or TRIM59 OE MDA-MB-231 cells (lanes 4–6). (G) Representative IHC staining images for p-ERM in tissue sections from xenograft tumors of TRIM59 KO MCF7 cells or TRIM59 OE MDA-MB-231 cells compared with control cells. Scale bars: 200 μm. (H) Spearman correlation between TRIM59 expression and ezrin phosphorylation (p-S148, p-S366) levels. (I) Representative images showing HE and CK8 staining of lung micro-metastases of xenograft tumors in the indicated groups (WT versus TRIM59 OE or TRIM59 KO in MCF7 or MDA-MB-231 cells). Scale bars: 100 μm (HE); 20 μm (CK8). Red arrow: pulmonary metastatic foci. Statistical analysis of the number of lung metastases was shown in the right panel. n = 6. (J and K) Representative luminescent images of the primary and metastases acquired with an IVIS imaging system. Luminescence imaging in NSG mice was followed after inoculation with breast cancer cells into the mammary fat-pad at the indicated time points (n = 3). Note, 10-week-old NSG mice inoculated with TRIM59 OE MDA-MB-231-luc died without bioluminescent imaging. (L) Gene expression analysis of TRIM59 in primary and lymph node metastases (GSE30480 dataset). (M) Representative TRIM59 IHC staining images in paired primary breast cancer and metastatic lymph nodes from breast cancer patients (n = 19). Statistical analysis of paired patient samples (primary versus metastatic tissues in the same patient) were shown on the right. Data in A, I, L, and M are presented as means ± SD. *P < 0.05, **P < 0.01 versus controls. The underlying data can be found in S1 Data. CK8, cytokeratin 8; ERM, Ezrin (Thr567)/Radixin (Thr564)/Moesin (Thr558); HE, hematoxylin–eosin; IB, immunoblot; IHC, immunohistochemistry; IRES, internal ribosome entry site; GFP, green fluorescent protein; IVIS, in vivo imaging system; KD, knockdown; KO, knockout; Min, minimum; Max, maximum; NSG, NOD scid gamma; OE, overexpressed; p-ERM, phosphorylation of ERM; pSer19-MLC, phosphorylation of MLC at serine 19; TRIM59, tripartite motif 59; WT, wild-type.\n\nFigure 5: Figure 5. (A) Yeast two-hybrid screening to confirm the interaction between TRIM59-BD and PDCD10-AD. Transformed and mated cells were grown on–Leu–Trp medium (bottom). Interaction of TRIM59 with PDCD10 was verified on high-stringency plates (–Leu–Trp–His–Ade) and with a β-galactosidase filter assay and Aureobasidin A (AbA) (top). Interaction of p53 and SV40 large T-antigen (LTA) was used as positive control. (B) Co-IP and IB analysis of extracts of MCF7 cells with the indicated antibodies. IP with IgG was added as a negative control. (C) Co-IP and IB analysis of extracts of HEK293T cells transfected with FLAG-PDCD10 along with HA-tagged TRIM59 variants (full-length WT or deletions [ΔR, ΔTM, B, and CC] as shown on the top cartoon). (D) IB and qPCR analysis of PDCD10 protein expression (left) and mRNA levels (right) in shControl and shTRIM59 MCF7 cells (D, lane 1 versus 2) or in control and TRIM59 OE MDA-MB-231 cells (D, lane 3 versus 4). Data are presented as means ± SD. NS versus controls. The underlying data can be found in S1 Data. (E) Representative immunofluorescent staining of PDCD10 (green) in sections from xenograft of shControl or shTRIM59 MCF7 cells. DAPI, DNA-intercalating dye, indicates the nucleus (blue). Scale bars: 100 μm. n = 4. (F) IB analysis of PDCD10 expression in MCF7 WT or TRIM59 KO cell fractions. β-actin and LaminB1 were used as markers for the cytosolic and nuclear fractions, respectively. (G) IB analysis of PDCD10 expression in WT or TRIM59 KO MCF7 cells treated with DMSO or 10 μM MG132 (proteasome inhibitor) or 200 nM BafA1 (autophagy inhibitor). See S4C Fig for similar experiments using TRIM59 KD cells. ΔR, TRIM59 without RING domain; ΔTM, TRIM59 without the predicted transmembrane domain; AbA, Aureobasidin A; AD, transcription activation domain;–Ade, adenine dropout; B, B-box-type zinc finger domain; BafA1, bafilomycin A1; BD, DNA-binding domain; C, cytosolic fraction; CC, coiled-coil domain; co-IP, co-immunoprecipitation; HA, hemagglutinin;–His, histidine dropout; IB, immunoblot; IgG, immunoglobulin G; IP, immunoprecipitation; KD, knockdown; KO, knockout;–Leu, Leucine dropout; LTA, large T-antigen; N, nuclear fraction; NS, not significant; OE, overexpressing; PDCD10, programmed cell death protein 10; p53, tumor protein 53; qPCR, quantitative polymerase chain reaction; SV40, polyomavirus simian virus 40; TM, transmembrane domain; TRIM59, tripartite motif 59;–Trp, tryptophan dropout; WT, wild-type."
      }
    ]
  },
  {
    "id": "PMC6245796_multi_2",
    "image": [
      "images/PMC6245796-f6.png",
      "images/PMC6245796-f7.png",
      "images/PMC6245796-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"TRIM59 promotes breast cancer motility by suppressing p62-selective autophagic degradation of PDCD10\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A and B) Representative xenograft images of MCF7 cells depleted with TRIM59 or PDCD10 compared with WT control (A) and tumor volume at indicated time points (B) in NSG mice; 5 × 106 cells/mouse. n = 4 mice per group. IB analysis of PDCD10 expression in WT and KO MCF7 cells was shown (A, right). (C) Kaplan–Meier survival curves were analyzed based on the expression of PDCD10 (Affymetrix ID: 210907_s_at), according to an online survival analysis tool using breast cancer microarray data (see Materials and methods for more details). n > 100. P = 0.0025. (D) Quantitative PCR to evaluate the expression of PDCD10 downstream genes in WT, TRIM59 KO, and PDCD10 KO MCF7 cells. n = 4. (E) IB analysis of phosphorylation of ERK5, total ERK5, and TRIM59 expression in WT and TRIM59 KO MCF7 cells. (F) IB analysis of FLAG-PDCD10 expression in MCF7 TRIM59 KO cells transduced with a lentiviral expression construct expressing FLAG-PDCD10. (G and H) Representative immunofluorescent staining (G, n = 3) or IB analysis (H) of p-ERM and total ERM in WT or TRIM59 KO MCF7 cells treated with RhoA-ROCK1 signaling inhibitor Y-27632 or ectopic expression of PDCD10 (P10 OE). Scale bars: 20 μm. (I) IB analysis of p-ERM and total ERM in WT or TRIM59 overexpressing MDA-MB-231 cells transduced with control shRNA or PDCD10 shRNA (shPDCD10). (J and K) Colony formation assay in 3D Matrigel culture (J) and Transwell invasion assay (K) were performed to assess the colony formation and invasion of WT, TRIM59 KO MCF7 cells with or without ectopic expression of FLAG-PDCD10. Bar graphs showed the number of colony-forming units (J) and the number of invaded cells (K) (n = 5). Scale bars: 10 μm (J); 100 μm (K). (L and M) Representative xenograft images of WT, TRIM59-depleted (T59 KO), PDCD10 overexpressing (P10 OE), and T59 KO reconstituted with P10 OE (T59 KO+P10 OE) MCF7 cells (L) and tumor volume at indicated time points (M) in NSG mice; 1 × 107 cells/mouse. n = 4 mice per group. Data in B, D, J, K, and M are presented as means ± SD. NS, not significant, *P < 0.05, **P < 0.01 versus controls. The underlying data can be found in S1 Data. ERK5, extracellular signal–regulated kinase 5; ERM, Ezrin (Thr567)/Radixin (Thr564)/Moesin (Thr558); HR, hazard ratio; IB, immunoblot; KO, knockout; NS, not significant; NSG, NOD scid gamma; OE, overexpressing; PDCD10, programmed cell death protein 10; p-ERM, phosphorylation of ERM; RhoA, Ras homolog family member A; ROCK1, Rho-associated coiled-coil kinase 1; shRNA, short hairpin RNA; TRIM59, tripartite motif 59; WT, wild-type.\n\nFigure 7: Figure 7. (A) Co-IP and IB analysis of extracts of HEK293T cells transfected with FLAG-PDCD10, along with expression vectors for cargo receptors HA-p62, HA-NBR1, HA-HDAC6, HA-NIX, HA-NDP52, or HA-OPTN. (B) IB analysis of PDCD10, p62, and LC3 expression in WT, p62 KO, and LC3 KO MCF7 cells. (C) IB analysis of PDCD10 expression in WT and p62 KO HEK293T cells with or without overexpression of TRIM59 (WT versus TRIM59 OE). (D) Co-IP and IB analysis of extracts of HEK293T cells transfected with HA-p62, FLAG-PDCD10, along with empty vector or Myc-TRIM59. (E) IB analysis of WT, PDCD10 OE, TRIM59 OE, and RNFT1 KO MCF7 cells using anti-E-cadherin, anti-p-ERM, anti-ERM, or anti-PDCD10 antibodies. (F) Co-IP and IB analysis of extracts of WT or RNFT1 KO MCF7 cells with indicated antibodies. (G and H) Co-IP and IB analysis of extracts of WT or TRIM59 OE MDA-MB-231 cells (G) and WT or TRIM59 KO MCF7 cells (H) with indicated antibodies and IgG controls. Cells were treated with BafA1 to maintain PDCD10 levels. (I) Co-IP and IB analysis of extracts of WT or TRIM59 OE stable HEK293T cells transfected with control shRNA or shRNFT1, along with expression vectors for FLAG-PDCD10, HA-K63. Cells were treated with BafA1 to maintain PDCD10 levels. (J) IB analysis of extracts of HEK293T cells transfected with FLAG-PDCD10 WT or mutants (K132R, K179R, and K183R), along with empty vector control (C) or vector for overexpressing (OE) TRIM59. Conserved lysine residues within the FAT-H domain (aa 92–212) were highlighted. The relative expression levels of FLAG-PDCD10 WT or mutants were indicated below the blot images after performing densitometric scanning of blots with subsequent normalization to β-actin. (K) Co-IP and IB analysis of extracts of HEK293T cells transfected with FLAG-PDCD10 WT or mutants (K132R, K179R, K183R), along with the expression vector for HA-K63-Ub. BafA1, bafilomycin A1; C, empty vector control; co-IP, co-immunoprecipitation; DD, dimerization domain (aa 1–92); ERM, Ezrin (Thr567)/Radixin (Thr564)/Moesin (Thr558); EV, empty vector; FAT-H, focal adhesion targeting-homology; HA, hemagglutinin; HDAC6, histone deacetylase 6; IB, immunoblot; IgG, immunoglobulin G; IP, immunoprecipitation; KO, knockout; K63-Ub, lysine 63-linked polyubiquitin; LC3, microtubule-associated protein 1A/1B-light chain 3; Myc, avian myelocytomatosis virus oncogene cellular homolog; NBR1, neighbor of BRCA1 gene 1; NDP52, nuclear Domain 10 Protein 52; NIX, BCL2 interacting protein 3 like; OE, overexpressing; OPTN, optineurin; PDCD10, programmed cell death protein 10; p-ERM, phosphorylation of ERM; p62, phosphotyrosine-independent ligand for the Lck SH2 domain of 62 kDa; RNFT1, RING finger and transmembrane domain-containing protein 1; shRNA, short hairpin RNA; TRIM59, tripartite motif 59; WCL, whole cell lysate; WT, wild-type.\n\nFigure 8: Figure 8. TRIM59 is essential for breast cancer cell mesenchymal movement and cell survival by maintaining low cell adhesion and high Wnt signaling of breast cancer cells. TRIM59 stabilizes PDCD10 by inhibiting K63 ubiquitination induced by RNFT1 at the lysine 179 site, and subsequently suppresses p62-selective autophagy degradation. TRIM59 deficiency facilitates PDCD10 degradation to overcome its inhibitory effect on Rho/ROCK signaling, thereby causing hyperactivated MLC and ERM and mesenchymal to amoeboid transition (MAT). TRIM59 deficiency also promotes excessive E-cadherin expression and reduces β-catenin expression, leading to high cell adhesion, low Wnt signaling, and high cell death to ultimately curtail tumor formation and metastasis. ERM, Ezrin (Thr567)/Radixin (Thr564)/Moesin (Thr558); KO, knockout; K63-Ub, lysine 63-linked polyubiquitin; LC3, microtubule-associated protein 1A/1B-light chain 3; MAT, mesenchymal to amoeboid transition; MLC, myosin light chain; PDCD10, programmed cell death protein 10; p-ERM, phosphorylation of ERM; p-MLC, phosphorylation of MLC; p62, phosphotyrosine-independent ligand for the Lck SH2 domain of 62 kDa; Rho/ROCK, Ras homolog/Rho-associated coiled-coil kinase; RNFT1, RING finger and transmembrane domain-containing protein 1; TRIM59, tripartite motif 59; Ub, ubiquitin; WT, wild-type."
      }
    ]
  },
  {
    "id": "PMC6276768_multi",
    "image": [
      "images/PMC6276768-f1.png",
      "images/PMC6276768-f2.png",
      "images/PMC6276768-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Long-Term Cholic Acid Treatment in a Patient with Zellweger Spectrum Disorder\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Liver biopsy at age 2 years shows periportal fibrosis with septa formation and pericellular fibrosis. Hepatocytes are slightly swollen and inflammation is minimal. Masson Trichrome stain. Inset shows scattered enlarged sinusoidal macrophages containing PAS+ inclusions. Diastase-PAS stain. b MRI image reveals small liver containing two well-defined tumor masses interpreted as HCC.\n\nFigure 2: Figure 2. Highest level of urinary bile acid during each year of cholic acid (CA) treatment. Urinary bile acid was assessed ≥1 time each year through 16 years of treatment. The highest value obtained in each year is shown. The FAB-MS mass spectra at baseline and post-treatment were assessed as normal (score 0) or as showing slight (score 1), significant (score 2), or marked (score 3) increases in the levels of atypical bile acids [7].\n\nFigure 3: Figure 3. Overview of metabolic abnormalities reported in liver of mice with peroxisome biogenesis defects. Reprinted with permission from Baes and Van Veldhoven [11]. AMPK, AMP-activated protein kinase; DCA, dichloroacetate; DHA, docosahexaenoic acid; ER, endoplasmic reticulum; PGC1α, peroxisome proliferator-activated receptor gamma coactivator 1-alpha; PPARα, proliferator-activated receptor alpha; VLCFA, very long chain fatty acids."
      }
    ]
  },
  {
    "id": "PMC6277683_multi",
    "image": [
      "images/PMC6277683-f1.png",
      "images/PMC6277683-f2.png",
      "images/PMC6277683-f2-2.png",
      "images/PMC6277683-f4.png",
      "images/PMC6277683-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome biogenesis deficiency attenuates the BDNF-TrkB pathway-mediated development of the cerebellum\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic representation of the Pex14 genome locus (top), targeting vector (pMC-KO, middle), and targeted allele of the mutated locus following the homologous recombination (bottom). Exon sequences are indicated by black bars and boxes. (B) PCR-based genotyping using tail-derived DNA of wild-type (+/+), heterozygous (+/ΔC), and homozygous (ΔC/ΔC) Pex14 mutant mice. Arrows indicate the sequences used for primers described in the Materials and Methods section. Primers P14F (F) and P14R (R) amplify a 599-bp fragment, and primers F and KN52-2 (K) amplify a 169-bp fragment specific for the recombined Pex14 gene. (C) Schematic structure of predicted Pex14p proteins in wild-type mice, Pex14 mutant mice (Pex14p-Mut), and patients with a Pex14 nonsense mutation, C553T (Pex14p-Q185X). Gray bar, Pex5p-binding domain; brown bar, transmembrane domain (TM); yellow bar, coiled-coil domain (CC); shaded area, altered amino acid sequence caused by a frameshift mutation (129–163). (D) Phenotypic appearance of Pex14 mutant mice ∼12 h after birth. Scale bar, 1 cm. (E) Postnatal body weights were determined at P0.5. The number of pups with each genotype is indicated. ***P < 0.001, by Dunnett's test compared with +/+. (F) Cresyl violet staining of a coronal section of the cortex from a P0.5 mouse. The open arrows indicate accumulated neurons in the intermediate zone (IZ). Scale bar, 100 μm. (G) Enlarged view of the boxed regions in F. Cortical layers are indicated on the left. The boundaries of the cortical plates are indicated by dashed lines. Scale bar, 50 μm. CP, cortical plate; DT-A, diphtheria toxin A cassette; Neor, Neomycin-resistant gene; VZ, ventricular zone.\n\nFigure 2: Figure 2. (A) Peroxisomal proteins were analyzed by Western blotting. A truncated form of Pex14p was detected by immunoblotting with an anti-Pex14pN antibody of the cell lysate of fibroblasts from a patient with a PEX14 mutation (Q185X, left panel, arrowhead). The full-length Pex14p was undetectable with an anti-Pex14pC antibody (middle panel). Peroxisomal protein import was assessed by immunoblotting with antibodies to AOx and ADAPS (right panels). Intraperoxisomal conversion of AOx A-chain to B-chain and C-chain and processing from a larger precursor to mature ADAPS were impaired in the patient-derived cells. Dot, a non-specific band. (B) Fibroblasts were stained with antibodies to PTS1, catalase, and PMP70. The catalase was diffused throughout the cytosol, and the fluorescence intensity of PTS1 was reduced in the fibroblasts from the patient. In addition, a smaller number of enlarged puncta labeled with the anti-PMP70 antibody were detected, suggesting that peroxisomal matrix protein import was partially defective. Scale bar, 10 μm. (C–E) VLCPC (C), PlsEtn (D), and DHA-PLs (E) of total phospholipids in skin fibroblasts were quantified by LC-ESI-MS/MS analysis and shown as the levels relative to those of control fibroblast (n = 3). VLCPC was elevated in the fibroblasts from the patient, whereas the reduced levels of PlsEtn and DHA-PLs were milder than those observed in fibroblasts obtained from patients with ZS. ***P < 0.001, by t test compared with control fibroblasts (C–E). Source data are available for this figure.\n\nFigure 2: Figure 2. Immunofluorescence labeling of the cortex in wild-type (+/+) and Pex14ΔC/ΔC (ΔC/ΔC) mice. (A–D) The coronal sections of brains were stained with antibodies to PTS1 (green) and Pex14pC (red) (A), ADAPS (green) and Pex14pC (red) (B), PMP70 (green) and catalase (red) (C), or Pex14pN (green) and Pex14pC (red) (D). Staining with Hoechst 33242 (blue) and the merged view are also shown. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown (insets). Scale bar, 2 μm. (E) Brain lysates prepared from wild-type, heterozygous (+/ΔC), and homozygous Pex14 mutant mice were subjected to SDS–PAGE and immunoblotting analysis using antibodies against Pex14pN, Pex14pC, AOx, and α-tubulin. Arrowhead indicates C-terminally truncated Pex14p corresponding to Pex14p-Mut. AOx is synthesized as a 75-kD A-chain and converted to a 53-kD B-chain and a 22-kD C-chain in peroxisomes. AOx A and AOx B chains are shown in immunoblots. Dots, non-specific bands. (F–H) Total amounts of PlsEtn (F), VLCPC (G), and DHA-PLs (H) are represented relative to those in the wild-type mouse brain (n = 3). **P < 0.01, ***P < 0.001, by Dunnett's test compared with +/+. Source data are available for this figure.\n\nFigure 4: Figure 4. Cresyl violet staining of coronal sections of the brains from wild-type (+/+, left panel) and Pex14ΔC/ΔC (ΔC/ΔC, right panel) mice (P0.5). Scale bar, 1 mm.\n\nFigure 3: Figure 3. (A) Percentage of pups surviving at postnatal days. The survival days were based on the pups of 22 wild-type (+/+) and 25 Pex14ΔC/ΔC (ΔC/ΔC) BL/ICR mice. (B) Body weights of pups at postnatal days were plotted. (C) Hematoxylin and eosin staining of the sagittal sections of the cerebellum (P7). Arrowheads indicate the shallow cerebellar folia in the cerebellum of the Pex14ΔC/ΔC BL/ICR mouse (lower panel). Scale bar, 500 μm. (D) The sagittal section of the cerebellum at P7 was stained with hematoxylin and eosin. Scale bar, 20 μm. (E) Thickness of EGL was quantified (n = 3). (F, G) Confocal microscopy images of the sagittal sections of the cerebellum at P3 labeled with an antibody to calbindin-D28k, a Purkinje cell marker. Arrows indicate axons of wild-type Purkinje cells and arrowheads indicate swollen axons of Pex14 mutant Purkinje cells. Scale bar, 10 μm. (H) Percentage of swollen axons was quantified (+/+, n = 54; ΔC/ΔC, n = 52). (I) Confocal microscopy images of sagittal sections of the cerebellum at P7 labeled with an antibody to calbindin-D28k are shown. Arrows indicate axons of wild-type Purkinje cells and arrowheads indicate axonal reticular structures of Pex14 mutant Purkinje cells. Scale bar, 10 μm. ***P < 0.001, by t test (E) and χ2 test (H). EGL, external granular layer; IGL, internal granular layer; ML, molecular layer; PCL, Purkinje cell layer."
      }
    ]
  },
  {
    "id": "PMC6277683_multi_2",
    "image": [
      "images/PMC6277683-f4-2.png",
      "images/PMC6277683-f5.png",
      "images/PMC6277683-f6.png",
      "images/PMC6277683-f9.png",
      "images/PMC6277683-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome biogenesis deficiency attenuates the BDNF-TrkB pathway-mediated development of the cerebellum\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 4: Figure 4. (A) SH-SY5Y cells were treated with a control siRNA (siControl) or siRNAs against PEX5 (#1 and #2) and cultured for 48 h. PEX5 mRNA level was determined by real-time PCR (n = 3). (B) Cells were stained with anti-catalase (green) and Pex14pC (red) antibodies. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown (inset). Scale bar, 2 μm. (C) SH-SY5Y cells treated with siRNAs were cultured in the presence or absence of the recombinant extracellular domain of p75NTR (p75ECD-His, amino acid sequence at 1–747) and stained with anti-Tuj-1 antibody (green). Arrows indicate neurons with neurite outgrowth. Percentage of neurons with neurite outgrowth were determined and shown on the right (n > 100 cells; three cultures each). Scale bar, 100 μm. (D) mRNA levels of neurotrophins in SH-SY5Y cells were assessed by real-time PCR (n = 3). (E) SH-SY5Y cell lysates were analyzed by SDS-PAGE and immunoblotting with antibodies against Pex5p, BDNF, and LDH. (F) Conditioned medium was obtained from the culture of SH-SY5Y cells treated with siRNAs that had been cultured for 2 d. SH-SY5Y cells were incubated in the collected conditioned medium in the presence or absence of p75ECD-His for 2 d. Percentages of neurons with neurite outgrowth were determined and shown on the right (n > 100 cells; three cultures each). Scale bar, 100 μm. (G) SH-SY5Y cells were cultured in the presence or absence of recombinant BDNF (rBDNF) and p75ECD-His. Cells were stained with anti-Tuj-1 antibody (green, upper panels). Percentages of neurons with neurite outgrowth were shown in a lower panel (n > 100 cells; five cultures each). Scale bar, 100 μm. Data represent means ± SD. *P < 0.05, **P < 0.01, ***P < 0.001, by Tukey–Kramer test (C, F, G) and Dunnett's test (D). Source data are available for this figure.\n\nFigure 5: Figure 5. (A) Sagittal sections of the cerebellum from wild-type (+/+) and Pex14ΔC/ΔC (ΔC/ΔC) BL/ICR mice were labeled with anti-calbindin-D28k (left panels, green) and BDNF (middle panels, red) antibodies. Merged views of the two different proteins and staining with Hoechst 33242 (blue) are shown on the right. Scale bar, 50 μm. (B) Relative fluorescent intensity of BDNF was quantified (n = 4). (C) Primary cerebellar neurons were cultured in the absence or presence of 50 ng/ml BDNF for 14 DIV. The cells were fixed and stained with antibody against calbindin-D28K. Reverse images of Purkinje cells are shown. Scale bar, 100 μm. Higher magnification image of the boxed region is shown in the inset. Arrows indicate swollen axons of Purkinje cell. Scale bar, 20 μm. (D, E) Statistical analyses were performed for neuronal axon length (D) and the number of collaterals per 100-μm axon (E). Data represent means ± SEM. (F) The percentage of swollen axons (>2 μm diameter) was quantified. (G) Enlarged view of the reverse images of Purkinje cell bodies are shown (upper and lower panels). Scale bar, 20 μm. (H) Areas of the cell body and dendrites of Purkinje cells were measured (+/+: n = 64; +/+, rBDNF: n = 42; ΔC/ΔC: n = 110; ΔC/ΔC, rBDNF: n = 109). Data represent means ± SEM. ns, not significant, *P < 0.05, **P < 0.01, ***P < 0.001, by t test (B), Tukey–Kramer test (D, E, H), and χ2 test (F).\n\nFigure 6: Figure 6. (A) Sagittal sections of the cerebellum from wild-type (+/+) and Pex14ΔC/ΔC (ΔC/ΔC) BL/ICR mice were labeled with anti-TrkB (green) and calbindin-D28k (red) antibodies. Scale bar, 20 μm. Higher magnification images of the boxed regions are shown and cell boundaries were indicated as a dashed line (inset). Scale bar, 5 μm. (B) TrkB-positive dots (arrowheads) were quantified (n = 13). (C) Sagittal sections of the cerebellum at P3 were stained with antibodies against vGlut2 (red) and calbindin-D28k (white). The number of dots stained with anti-vGlut2 antibody was quantified (lower panel, n = 4). Scale bar, 10 μm. (D) Sagittal sections of the cerebellum at P3 were stained with antibodies against TrkB (green), vGlut2 (red), and calbindin-D28k (blue). Scale bar, 10 μm. Higher magnification images of the boxed regions are shown (inset). Scale bar, 5 μm. Arrowheads indicate TrkB-positive punctate structures that partly coincided with or are located adjacent to vGlut2-positive punctate structures. (E) Cerebellum lysates were analyzed by SDS-PAGE and immunoblotting with antibodies against TrkB, Pex14pC, and α-tubulin (left panel). TrkB-TK+, full-length TrkB; TrkB-T1, a truncated isoform of TrkB. Amounts of TrkB-TK+ and TrkB-T1 are presented relative to those of TrkB-TK+ in the control mice (middle panel, n = 6). A schematic view of TrkB variants is shown on the right (right panel). TK, tyrosine kinase domain. (F, G) mRNA levels of TrkB-TK+ (F) and TrkB-T1 (G) were quantified by real-time PCR (n = 6). ns, not significant, **P < 0.01, ***P < 0.001, by t test (B, C, E–G). Source data are available for this figure.\n\nFigure 9: Figure 9. (A) Sagittal sections of the cerebellum of wild-type (+/+) and Pex14ΔC/ΔC (ΔC/ΔC) BL/ICR mice at P7 were stained with anti-TrkB (green) and calbindin-D28k (red) antibodies. TrkB-positive punctate structures that were observed at P3 (Fig 6A) were not detected in the wild-type mouse cerebellum at P7, suggesting that climbing fiber terminals shifted to the Purkinje cell dendritic compartment. Scale bar, 10 μm. (B) Sagittal sections of the cerebellum at P7 were stained with antibodies against vGlut2 (red) and calbindin-D28k (white). The number of dots stained with anti-vGlut2 antibody was quantified (right panel, n = 4). Scale bar, 10 μm. (C, D) Primary cerebellar neurons from a wild-type mouse at P0.5 were cultured for five DIV and then treated with 50 ng/ml BDNF for two DIV. Levels of TrkB-TK+ (C) and TrkB-T1 (D) mRNAs were determined by real-time PCR (n = 5). (E) Relative mRNA levels of c-fos and c-jun in the cerebellum at P3 were analyzed by real-time PCR (n = 3). (F) Cerebellar lysates of wild-type and Pex14ΔC/ΔC BL/ICR mice at P0.5, P3, P5, and P7 were analyzed as in Fig 6E. TrkB-TK+, full-length TrkB; TrkB-T1, truncated isoform of TrkB; Dot, a non-specific band. (G) Amounts of TrkB-TK+ and TrkB-T1 were normalized by α-tubulin level and presented relative to those of TrkB-TK+ in control mice at P0.5 (n = 3). (H) Cerebellum lysates from wild-type and Pex14ΔC/ΔC BL/ICR mice at P5 and P7 were analyzed by SDS–PAGE and immunoblotting with antibodies against TrkB (lower panels) and phosphorylated Trk (p-TrkB-TK+, Y496, upper panels). (I) Total ERK1/2 (lower panels) and phosphorylated ERK1/2 (p-ERK1 and 2, T202, and Y204, respectively, upper panels) at P5 and P7 were analyzed as in Fig 7C. The amount of phosphorylated ERK1/2 relative to total ERK1/2 is represented (P5; n = 3, P7; n = 4). (J, K) Sagittal sections of the cerebellum from wild-type (upper panels) and Pex14ΔC/ΔC (lower panels) BL/ICR mice at P3 (J) and P7 (K) were stained with anti-calbindin-D28k antibody (green) and phalloidin-TRITC (red). Scale bar, 10 μm. Higher magnification images of the boxed regions are shown (inset). Scale bar, 5 μm. Actin-positive structures located on the dendrites (arrowheads) were decreased in Pex14ΔC/ΔC BL/ICR mice. ns, not significant, *P < 0.05, ***P < 0.001, by t test (B, C–E, G, and I). Source data are available for this figure.\n\nFigure 7: Figure 7. (A) Cerebellum lysates from wild-type (+/+) and Pex14ΔC/ΔC (ΔC/ΔC) BL/ICR mice were analyzed by SDS–PAGE and immunoblotting with antibodies against TrkB, phosphorylated Trk (p-TrkB-TK+, Y496), PLCγ1, phosphorylated PLCγ1 (p-PLCγ1, Y783), ERK, phosphorylated ERK (p-ERK1 and 2, T202 and Y204, respectively), AKT, and phosphorylated AKT (p-AKT, S473). Dots, non-specific bands. (B–E) The amount of phosphorylated TrkB-TK+ to total TrkB-TK+ (B), phosphorylated ERK1/2 relative to total ERK1/2 (C), phosphorylated AKT to total AKT (D), and phosphorylated PLCγ1 to total PLCγ1 (E) were represented (n = 3). ns, not significant, **P < 0.01, ***P < 0.001, by t test (B–E). Source data are available for this figure."
      }
    ]
  },
  {
    "id": "PMC6277683_multi_3",
    "image": [
      "images/PMC6277683-f8.png",
      "images/PMC6277683-f12.png",
      "images/PMC6277683-f13.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome biogenesis deficiency attenuates the BDNF-TrkB pathway-mediated development of the cerebellum\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 8: Figure 8. (A) mRNA levels of Bdnf and Nt-4 relative to those of Rpl13a in the cerebellum from wild-type (+/+) and Pex14ΔC/ΔC (ΔC/ΔC) BL/ICR mice at P3 were determined by real-time PCR (n = 4). (B) Sagittal sections of the cerebellum at P7 were stained with antibodies to GFAP (green) and BDNF (red). Merged views of the two different proteins and staining with Hoechst 33242 (blue) are shown. Scale bar, 20 μm. (C) In situ hybridization analysis of Bdnf mRNA in the brain stem region of wild-type (upper panels) and Pex14ΔC/ΔC (lower panels) mice at P0.5. Arrows indicate ION. Insets are higher magnification images of the dashed-line boxed regions. Scale bar, 100 μm. (D) Relative intensity of Bdnf mRNA staining by in situ hybridization shown in C was presented (n = 3). (E) Sagittal sections of the brain stem at P3 were stained with anti-BDNF antibody (red) and Hoechst 33242 (blue). Scale bar, 20 μm. (F) Fluorescent intensity of BDNF staining on the ION shown in E was quantified (n = 3). (G) The mRNA level of Bdnf in the brain stem region was quantified by real-time PCR (n = 3). (H) Brain stem lysates were analyzed by SDS–PAGE and immunoblotting using antibodies against BDNF and α-tubulin. The BDNF band was quantified (lower panel, n = 4). ns, not significant, *P < 0.05, **P < 0.01, by t test (A, D, F–H). Source data are available for this figure.\n\nFigure 12: Figure 12. (A) Lysates of the cortex from wild-type and Pex14ΔC/ΔC mice at P0.5 were analyzed by SDS–PAGE and immunoblotting with antibodies against TrkB, α-tubulin, and BDNF. (B) Amounts of TrkB-TK+ and TrkB-T1 were normalized by α-tubulin level and presented relative to those of TrkB-TK+ in wild-type mice at P0.5 (n = 4). (C) Amount of BDNF was normalized by α-tubulin level and presented relative to that in wild-type mice at P0.5 (n = 4). (D, E) Lysates of the cortex from wild-type and Pex14ΔC/ΔC mice at P0.5 were analyzed as in (A) with antibodies against ERK (D), phosphorylated ERK (p-ERK1 and 2, T202, and Y204, respectively) (D), AKT (E), and phosphorylated AKT (p-AKT, S473) (E). Amounts of phosphorylated ERK1/2 relative to total ERK1/2 (D) and phosphorylated AKT to total AKT (E) were shown on the respective lower panels (n = 4). Dot, a non-specific band. ns, not significant, by t test (B–E). Source data are available for this figure.\n\nFigure 13: Figure 13. In the wild-type cerebellum (left), BDNF targets to TrkB-TK+ on the surface of Purkinje cells. The cytosolic tyrosine kinase domain (TK) then undergoes autophosphorylation and activates MAPK/ERK and PI3K/AKT signaling, leading to the dendritic arborization of Purkinje cells. In the Pex14ΔC/ΔC mouse, the BDNF level is increased around the Purkinje cells through the climbing fiber from ION neurons. On the Purkinje cells of the Pex14ΔC/ΔC mouse (right), TrkB-T1 is up-regulated and dominant-negatively inhibits autophosphorylation of TrkB-TK+. Decrease of TrkB-TK+ phosphorylation deactivates the MAPK/ERK and PI3K/AKT signaling, resulting in the dysmorphogenesis of Purkinje cells."
      }
    ]
  },
  {
    "id": "PMC6282458_multi",
    "image": [
      "images/PMC6282458-f1.png",
      "images/PMC6282458-f2.png",
      "images/PMC6282458-f3.png",
      "images/PMC6282458-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Late adult-onset adrenomyeloneuropathy evolving with atypical severe frontal lobe syndrome: Importance of neuroimaging\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Family tree. The presented case is marked with an arrow. Subject II,4; II,8; III,2; III,9 were affected by ALD/AMN; II,1 and II,3 are female carriers. ALD = adrenoleukodystrophy; AMN = adrenomyeloneuropath.\n\nFigure 2: Figure 2. (A-D) Brain MRI. Axial turbo spin-echo (TSE) T2-weighted image (A) well depicts bilateral and confluent white matter fronto-parietal hyperintensities more extensive and characterized by a higher signal in the frontal lobes. The anterior limb of the internal capsule is also clearly affected, bilaterally. The ventricular system and the fronto-insular subarachnoid spaces are enlarged. Axial diffusion-weighted imaging (DWI) eADC map (B) shows a marked hypointensity of the deep frontal white matter, rather than the parietal one. Axial TSE T2-weighted image at subtentorial level (C) reveals a bilateral hyperintense signal of the middle cerebellar peduncles associated to a subtle hyperintensity of the ventral pons that results quite atrophic. Sagittal TSE T2-weighted image shows thinning of the entire corpus callosum with abnormal hyperintense signal of the isthmus, the genu and the anterior part of the body (D). eADC = exponential Apparent Diffusion Coefficient; MRI = magnetic resonance imaging.\n\nFigure 3: Figure 3. Spine MRI. Sagittal TSE T2-weighted image shows thinning of the dorsal spinal cord, with relative sparing of the conus medullaris. MRI = magnetic resonance imaging.\n\nFigure 4: Figure 4. Positron emission tomography (PET) transaxial images of [18F]FDG uptake in the patient at 4 different sections (A) show a clear relative hypometabolism involving the associative cerebral cortex, mostly the frontal lobe and the anterior cingulate region, and the cerebellar hemispheres (azure color). To a lesser extent, [18F]FDG uptake appears also reduced in the thalamus and the striatum, bilaterally. These findings are highlighted by the results of single subject statistical parametric mapping (SPM) analysis obtained in our patient in comparison to a group of controls (age range of controls: 27-70, age was considered in the statistical model of SPM as nuisance covariate) and rendered as clusters of reduced relative metabolism (P < .01 uncorrected) onto the sagittal (B), coronal (C) and transaxial (D, E) T1-MRI SPM images spatially normalized to the Montreal Neurological Institute (MNI) space. FDG = fluoro-2-deoxy-d-glucose; MRI = magnetic resonance imaging."
      }
    ]
  },
  {
    "id": "PMC6310492_multi",
    "image": [
      "images/PMC6310492-f1.png",
      "images/PMC6310492-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Case report of dysregulation of primary bile acid synthesis in a family with X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The electropherograms of exon 1 sequencing in ABCD1 gene in family members showing position 659 of the coding DNA sequence. X-ALD = X-linked adrenoleukodystrophy.\n\nFigure 2: Figure 2. Plasma bile acids and sterol profiles in blood plasma in the family members."
      }
    ]
  },
  {
    "id": "PMC6317813_multi",
    "image": [
      "images/PMC6317813-f1.png",
      "images/PMC6317813-f2.png",
      "images/PMC6317813-f3.png",
      "images/PMC6317813-f4.png",
      "images/PMC6317813-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Non-proteolytic ubiquitin modification of PPARγ by Smurf1 protects the liver from steatosis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) HE and Oil Red-O staining of liver sections of WT, SF1KO, and SF2KO mice from the BL background at the age of 9–12 months. Bar = 40 μm. (B) Histological scores of steatosis of mice in (A). For each group, n = 15 (7 males and 8 females). Scores: 0, no steatosis; 1, minimal; 2, mild; 3, moderate; 4, severe. (C) Liver TG, CHO, and FFA content of the above male mice (n = 7 per group). (D) BW, eWAT/BW ratio, and Liver/BW ratio of the above male mice (n = 7 per group). (E) Liver ALT and AST activities of the above mice (n = 10; 5 males, 5 females per group). (F) Glucose and (G) insulin tolerance tests in male mice at the age of 9–12 months (n = 8 per group). All data are presented as mean ± SD; statistical significance of difference is indicated as *p < 0.05, **p < 0.01, ***p < 0.001. Original raw data can be found in S1 Data. ALT, alanine transaminase; AST, aspartate transaminase; BL, mixed black Swiss × 129/SvEv background; BW, body weight; CHO, total cholesterol; eWAT/BW, epididymal WAT weight to body weight; FFA, free fatty acid; HE, hematoxylin–eosin; KO, knockout; Liver/BW, liver weight to body weight; ns, not significant; Smurf, Smad ubiquitin regulatory factor; SF1KO, Smurf1 KO; SF2KO, Smurf2 KO; TG, triglyceride; WAT, white adipose tissue; WT, wild-type.\n\nFigure 2: Figure 2. (A–C) Loss of Smurf1 exacerbates HFD-induced steatosis in mice. (A) BW, Fat/Lean ratio, Liver/BW ratio, and histological scores of steatosis in male WT and SF1KO mice from BL background reared on either a ND (n = 7 per group) or HFD (n = 8 per group), beginning at 10–12 weeks of age for 8 weeks. Liver sections were scored as in Fig 1B. (B) HE staining of representative liver sections of the above BL mice at the end of diet treatment. Bar = 100 μm. (C) Liver TG levels of BL mice from (A). Data are presented as mean ± SD; statistical significance of differences is indicated as *p < 0.05, **p < 0.01, ***p < 0.001. Original raw data can be found in S1 Data. (D–E) Low SMURF1 expression in human livers is inversely correlated to high BMI values. (D) Human liver tissues from the LCI cohort with low levels of SMURF1 expression show a significantly higher BMI than those with high SMURF1 expression. Non-tumor liver samples from the LCI cohort were grouped into SMURF1 High (top 25%, n = 61) and SMURF1 Low (bottom 25%, n = 59) groups. (E) Inverse correlation between SMURF1 low and BMI high was also observed in non-tumor liver samples from the TCGA-LIHC cohort. Non-tumor liver samples (n = 37) from the TCGA-LIHC cohort were grouped into SMURF1 High (above the median, n = 18) and SMURF1 Low (below the median, n = 19) groups. Data are presented using box and whisker plot; centerline represents the median, whiskers represent 10th–90th percentile. Nonparametic t tests between the two groups were performed; p-values are indicated in the graph. BL, mixed black Swiss × 129/SvEv background; BMI, body mass index; BW, body weight; Fat/Lean, fat mass to lean mass; HE, hematoxylin–eosin; HFD, high-fat diet; KO, knockout; LCI, Liver Cancer Institute; Liver/BW, liver weight to body weight; ND, normal diet; ns, not significant; SF1KO, Smurf1 KO; Smurf, Smad ubiquitin regulatory factor; TG, triglyceride; TCGA-LIHC, the cancer genome atlas-liver hepatocellular carcinoma; WT, wild-type.\n\nFigure 3: Figure 3. (A) Venn diagram of genes that were differentially expressed (fold > 1.5, FDR < 0.1) in Smurf1KO and Smurf2KO livers from the BL background relative to their WT counterparts at 11 months of age. For a detailed list, see S3 Table. (B) Heat map of a group of lipid metabolism–related genes that were differentially expressed in Smurf1KO livers and the KEGG pathway analysis of differentially expressed genes from BL-Smurf1KO livers. Enrichment score (p-value (−log10)) is indicated on the x-axis. (C) qRT-PCR analyses of Pparγ1, Pparγ2, and Pparα in livers from BL-WT, Smurf1KO, and Smurf2KO mice (n = 7 per group). (D) Western blot showing the increase of the PPARγ protein in livers of BL-Smurf1KO mice. Quantitation of PPARγ expression against loading control Hsc70 is shown at the bottom. (E) qRT-PCR analyses showing the increase of total Pparγ mRNA in livers and epididymal WAT but not skeletal muscle of BL-Smurf1KO mice, n = 7 per group. (F) qRT-PCR analyses showing up-regulation of a group of PPARγ target genes in livers of BL-Smurf1KO mice (n = 7 per group). Data from qRT-PCR are presented using box and whisker plot showing all points; centerline represents the median. All mice were analyzed at 9–11 months of age, and statistical significance of difference between WT and Smurf1KO is indicated as *p < 0.05, **p < 0.01, and ***p < 0.001. Original raw data can be found in S1 Data. BL, mixed black Swiss × 129/SvEv background; FDR, false discover rate; Hsc70, heat shock 70 kDa protein 8; KEGG, Kyoto Encyclopedia of Genes and Genomes; KO, knockout; ns, nonspecific band; PPAR, peroxisome proliferator-activated receptor; qRT-PCR, quantitative real-time PCR; SF1KO, Smurf1 KO; SF2KO, Smurf2 KO; Smurf, Smad ubiquitin regulatory factor; WAT, white adipose tissue; WT, wild-type.\n\nFigure 4: Figure 4. (A) Western blots showing that knockdown of Smurf1 but not Smurf2 in Hep3B and AML12 cells increased PPARγ protein level. (B) qRT-PCR analyses showing that knockdown of Smurf1 but not Smurf2 increased Pparγ mRNA level in AML12 cells. (C) qRT-PCR analyses showing that knockdown of Smurf1 in AML12 cells increased expression of Fabp1, Cd36, Acacb, and Apoc3 in a PPARγ-dependent manner. (D) Fatty acid uptake in AML12 cells as measured by 3H-palmitate incorporation (n = 3). (E) Lipid synthesis in AML12 cells as measured by incorporation of 3H-acetate into lipid (n = 3). (F) In vivo fatty acid uptake after intraperitoneal injection of BODIPY-FL-C16. The BODIPY-FL-C16 accumulation in the liver, epididymal WAT, and skeletal muscle was normalized to tissue weight (n = 8 per group). (G) Lipogenesis in primary hepatocytes as measured by the incorporation of 3H-acetate into lipid (n = 6 per group). Data are presented as mean ± SD; statistical significance of difference is indicated as *p < 0.05, **p < 0.01, ***p < 0.001. Original raw data can be found in S1 Data. BODIPY-FL-C16, 4,4-Difluoro-5,7-Dimethyl-4-Bora-3a,4a-Diaza-s-Indacene-3-Hexadecanoic Acid; eWAT, epididymal WAT; HSC70, heat shock cognate 71 kDa protein; NS, non-silencing control; PPAR, peroxisome proliferator-activated receptor; qRT-PCR, quantitative real-time PCR; RFU, relative fluorescence units; Rxr, retinoid x receptor; SF1KO, Smurf1 KO; siNS, non-silencing control siRNA; Smurf, Smad ubiquitin regulatory factor; WAT, white adipose tissue; WT, wild-type.\n\nFigure 5: Figure 5. (A) Co-immunoprecipitation showing interaction between endogenous Smurf1 and PPARγ in AML12 cells. *nonspecific band. (B) PY motif in PPARγ contributes to the interaction between Smurf1 and PPARγ. Myc-tagged Smurf1, Flag-tagged PPARγ2, and its ΔPY mutant were transfected into AML12 cells as indicated. WCL were immunoprecipitated with Flag-M2 beads and followed by western blot analyses. (C) Smurf1 but not Smurf2 promotes polyubiquitination of PPARγ1 and PPARγ2. Flag-PPARγ were immunoprecipitated from transfected AML12 and resolved by SDS-PAGE. Western blot analyses were carried out to detect HA-ubiquitin (top) and Flag-PPARγ1 or -γ2 (second panel) in the precipitates. The levels of total HA-Ub, Flag-PPARγ, Myc-Smurfs, and endogenous Hsc70 (loading control) in the WCL were also analyzed and are shown in the bottom panels. *nonspecific band. (D) E3 ligase activity of Smurf1 is required for Smurf1-mediated polyubiquitination of PPARγ. Flag-PPARγ2 and WT Myc-Smurf1 and its mutant Myc-Smurf1(CA) were transfected into the Smurf1KO MEFs along with HA-Ub. Ubiquitination of PPARγ2 was analyzed by western blot after Flag-M2 immunoprecipitation, as in C. (E) In vitro ubiquitination assay using recombinant proteins showing that PPARγ is a direct substrate of Smurf1-mediated polyubiquitination. (F) Smurf1 induces K63-linked polyubiquitination of PPARγ. Purified ubiquitin with no lysine residue (K0) or with single lysine residue at indicated position was used in the in vitro ubiquitination assay. E3, ubiquitin ligase; HA, human influenza hemagglutinin; Hsc70, heat shock cognate 71 kDa protein; IB, immunoblot; IP, immunoprecipitation; K, lysine; KO, knockout; MEF, mouse embryonic fibroblast; PPAR, peroxisome proliferator-activated receptor; PY, PPxY; SDS-PAGE, sodium dodecyl sulfate-polyacrylamide gel electrophoresis; Smurf, Smad ubiquitin regulatory factor; Ub, ubiquitin; WCL, whole cell lysate; WT, wild-type."
      }
    ]
  },
  {
    "id": "PMC6317813_multi_2",
    "image": [
      "images/PMC6317813-f6.png",
      "images/PMC6317813-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Non-proteolytic ubiquitin modification of PPARγ by Smurf1 protects the liver from steatosis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) Smurf1 inhibits PPARγ-induced transcriptional activity in AML12 cells. Relative luciferease activities were measured 1 day after transfection. Data are presented as mean ± SD; statistical significance of differences is indicated by *p < 0.05, **p < 0.01, ***p < 0.001. Expression of transfected Smurf1 and PPARγ in these cells is shown at right. (B) E3 ligase activity of Smurf1 is required for its inhibition of PPARγ transcriptional activity. Luciferase activities were measured and showed as above. Expression of transfected Smurf1 and PPARγ in these cells are shown at right. (C) ChIP analyses of PPARγ binding to its own or Fabp1 promoter in AML12 cells after transfecting the plasmids as indicated. (D) ChIP analyses of PPARγ binding to its own or Fabp1 promoter in liver tissues from WT and Smurf1KO mice (n = 8 per group). Data are presented as mean ± SD; statistical significance of difference is indicated by *p < 0.05, **p < 0.01, ***p< 0.001. Original raw data can be found in S1 Data. ChIP, chromatin immunoprecipitation; E3, ubiquitin ligase; Hsc70, heat shock cognate 71 kDa protein; IgG, Immunoglobulin G; KO, knockout; PPAR, peroxisome proliferator-activated receptor; PPRE-Luc, PPAR response element-luciferase reporter; SF1KO, Smurf1 KO; Smurf, Smad ubiquitin regulatory factor; WT, wild-type.\n\nFigure 7: Figure 7. (A) BW of male mice from the BL background before (age 7–9 months) and after 60 days (age 9–11 months) of GW9662 treatment (n = 8 per group). (B) Fat/Lean and Liver/BW ratios and histological score of steatosis of the above mice after GW9662 treatment, compared with those of untreated control mice at the same age (n = 8 per group). (C) Representative HE-stained sections of the above mice. Bar = 100 μm. (D) Serum TG and CHO contents of the above mice, n = 8 per group. (E) Liver TG, CHO, and FFA contents of the above GW9662-treated mice. (F) qRT-PCR analysis of expression of Pparγ2 and relevant lipid metabolism genes in the livers of GW9662-treated mice. Data are presented as mean ± SD; statistical significance of difference is indicated by *p < 0.05, **p < 0.01, ***p < 0.001. Original raw data can be found in S1 Data. BL, mixed black Swiss × 129/SvEv background; BW, body weight; CHO, total cholesterol; Ctrl, control; Fat/Lean, fat mass to lean mass; FFA, free fatty acid; GW, GW9662; HE, hematoxylin–eosin; KO, knockout; Liver/BW, liver weight to BW; ns, not significant; PPAR, peroxisome proliferator-activated receptor; qRT-PCR, quantitative real-time PCR; SF1KO, Smurf1 KO; Smurf, Smad ubiquitin regulatory factor; TG, triglyceride; WT, wild-type."
      }
    ]
  },
  {
    "id": "PMC6333749_multi",
    "image": [
      "images/PMC6333749-f1.png",
      "images/PMC6333749-f2.png",
      "images/PMC6333749-f3.png",
      "images/PMC6333749-f4.png",
      "images/PMC6333749-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Phenotype-Driven Virtual Panel Is an Effective Method to Analyze WES Data of Neurological Disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The flow chart of phenotype-driven designing virtual panel.\n\nFigure 2: Figure 2. Phenotype of the patients. (a) large ear; (b) internal strabismus; (c) inverted nipples; (d) fat pad in the buttock.\n\nFigure 3: Figure 3. MRI result of the patient. (a) Coronal T1W image. Black arrows pointed the anterior limb of the internal capsule. The faint hyperintense signal of T1W indicated delayed myelination of the patient. (b) Sagittal T1W image. The patient presented cerebellar atrophy.\n\nFigure 4: Figure 4. Chest CT result of the patient. It is shown that the patient had spine kyphosis.\n\nFigure 5: Figure 5. The mass spectrum result of the metabolite in urine. The result of the urine metabolite indicated liver abnormality of patient."
      }
    ]
  },
  {
    "id": "PMC6333749_multi_2",
    "image": [
      "images/PMC6333749-f6.png",
      "images/PMC6333749-f7.png",
      "images/PMC6333749-f8.png",
      "images/PMC6333749-f9.png",
      "images/PMC6333749-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Phenotype-Driven Virtual Panel Is an Effective Method to Analyze WES Data of Neurological Disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The blood test result of the patient’s serum. Alleviation of alanine aminotransferase (ALT) and Aspartate aminotransferase (AST) and deduction of plasma cholinesterase indicated liver dysfunction of the patient.\n\nFigure 7: Figure 7. Pedigree of family members. The elder sister of the patient also had similar phenotypes.\n\nFigure 8: Figure 8. Next-Generation result of patient. The result shows the two heterozygous mutations in the PMM2 gene. (a) c.640G > C; (b) c.430T > G.\n\nFigure 9: Figure 9. Sanger Sequence result of the patient’s family. The result shows that (A) the proband’s father was the heterozygous carrier of the c.430T > C mutation, while (B) the proband’s mother carried the c.640G > C mutation. The proband’s sister is also the carrier of the compound heterozygous mutations.\n\nFigure 10: Figure 10. Indicated splicing change by MutationTaster (Schwarz et al., 2014). This mutation might disturb the exon-intron border."
      }
    ]
  },
  {
    "id": "PMC6335716_multi",
    "image": [
      "images/PMC6335716-f1.png",
      "images/PMC6335716-f2.png",
      "images/PMC6335716-f3.png",
      "images/PMC6335716-f4.png",
      "images/PMC6335716-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"RiboTag translatomic profiling of Drosophila oenocytes under aging and induced oxidative stress\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Characterization of age-related changes in ROS production in Drosophila oenocytes. a Fluorescent image of GFP-labeled oenocytes from one fly dorsal abdomen dissected from a PromE-Gal4; UAS-CD8::GFP female. The dashed line indicates the location of the fly abdomen. Scale bar: 100 μm. b ROS levels indicated by DHE staining in female oenocytes under aging and paraquat (PQ) treatment. Young: 10-day-old, Aged: 30-day-old. DAPI stains for nuclei. Scale bar: 10 μm. c Quantification of DHE staining from Panel (b). One-way ANOVA (**** p < 0.0001, ** p < 0.01, ns = not significant ). N = 5\n\nFigure 2: Figure 2. Oenocyte-specific translatomic profiling through RiboTag sequencing. a Schematic diagram showing RiboTag procedures. FLAG-tagged ribosomal protein RpL13A was first ectopically expressed in oenocytes. Translating RNAs were immunoprecipitated using anti-FLAG antibodies. RNAs were further purified and used in RNA-seq analysis. b Oenocyte-specific transcript desat1-E highly expressed in anti-FLAG immunoprecipitated sample (IP) compared to the input (whole body lysate). c The transcripts of brain-specific gene Dilp2 was enriched in head samples compared to oenocyte RiboTag samples. One-way ANOVA ( *** p < 0.001, * p < 0.05, ns = not significant). N = 3. d RNA concentrations of various immunoprecipitated samples. ND: Not detected. 200 female flies were used in each condition. Three biological replicates per condition\n\nFigure 3: Figure 3. Differential gene expression analysis reveals common and distinct translational regulation by aging and oxidative stress. a Principal component analysis (PCA) on four oenocyte translatomes. b-d Correlation analysis on the gene expression between H2O-Young and H2O-Aged; H2O-Young and PQ-Young; H2O-Aged and PQ-Aged. Log10 (FPKM) was used in the analysis e-f Venn diagram and GO terms for the genes commonly and differentially regulated by aging and paraquat. g-h Venn diagram and GO terms for the genes commonly and differentially regulated by paraquat at young and old ages. i Hierarchy clustering analysis on oenocyte translatome. j Gene ontology analysis on cluster 3, 5, 10 in panel (i). OXPHOS: oxidative phosphorylation. FA: fatty acid\n\nFigure 4: Figure 4. GSEA analysis revealed up- and down-regulated pathways under aging. a List of the pathways up-regulated in aged oenocytes. b List of the pathways down-regulated in aged oenocytes. ES: Enrichment score. c-h GSEA enrichment profiles of six pathways: DNA replication, oxidative phosphorylation, proteasome, peroxisome, glutathione S-transferase, cytochrome P450. i-k Heatmaps for mitochondrial ribosomal subunits, glutathione S-transferase, cytochrome P450\n\nFigure 5: Figure 5. Peroxisome pathway is translationally deregulated in aged oenocytes. a Schematic diagram showing peroxisome pathway and the role of each peroxin (PEX) genes. b and c Log2 (fold change) of the expression of PEX genes under aging and paraquat treatment, based on oenocyte RiboTag sequencing results. d and e Log2 (fold change) of the expression of genes involved in other peroxisome functions during oenocyte aging. f-h qRT-PCR verification of three peroxisome genes (Pex5, Pex19, Cat). One-way ANOVA (** p < 0.01, ns = not significant). N = 3"
      }
    ]
  },
  {
    "id": "PMC6335716_multi_2",
    "image": [
      "images/PMC6335716-f6.png",
      "images/PMC6335716-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"RiboTag translatomic profiling of Drosophila oenocytes under aging and induced oxidative stress\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Ketogenesis and fatty acid elongation are enriched in both oenocytes and liver. a List of ketogenesis genes that are enriched in both oenocytes and liver. b Schematic diagram showing ketogenesis pathway. c List of genes in microsomal fatty acid elongation pathway that are enriched in both oenocytes and liver. d Schematic diagram showing microsomal fatty acid elongation pathway (in smooth ER). Oenocyte-enriched genes are highlighted in red. Liver-enriched genes are highlighted in blue\n\nFigure 7: Figure 7. Conservation of age-related translational and transcriptional changes between oenocytes and liver. a Venn diagram comparing genes/proteins differentially expressed in aged human liver and aged fly oenocytes. GO terms for age-regulated proteins in human liver were shown in the lower panel. b Venn diagram comparing genes differentially expressed in aged mouse liver and aged fly oenocytes. GO terms for age-regulated genes in mouse liver were shown in the lower panel. OXPHOS: oxidative phosphorylation. c and d List of all genes in Ras/MAPK signaling pathway that were down-regulated in aged fly oenocytes and mouse liver. Protein network was generated using STRING (with kmeans clustering option). Continuum edge indicates a high confidence score. Dashed edge indicates a low confidence score"
      }
    ]
  },
  {
    "id": "PMC6372518_multi",
    "image": [
      "images/PMC6372518-f1.png",
      "images/PMC6372518-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Broadening the Spectrum of Adulthood X-Linked Adrenoleukodystrophy: A Report of Two Atypical Cases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. BRAIN MRI (CASE 1): (A) Sagittal 3D Magnetization Prepared Rapid Acquisition Gradient Echo (MPRAGE) T1-w with axial (B), and coronal (C) reconstructions showing partial corpus callosum agenesis, right fornix, and mammillary body hypoplasia, hypogenesis of bilateral lateral ventricles (colpocephaly). (D) Turbo Spin Echo Fluid-Attenuated Inversion Recovery (TSE FLAIR) T2-w axial and coronal (FLAIR T2-w & T1-w) scans showing nodular heterotopic foci. (E) TSE FLAIR T2-w & T1-w coronal scan showing right frontal parasagittal cortical thickening. (F) Susceptibility Weighted Imaging (SWI) axial scan with Maximum Intensity Projection (MIP) reconstruction showing right frontal parasagittal venous drainage abnormality with telangiectasia.\n\nFigure 2: Figure 2. Skin Biopsy Immunoflorescence (Case 2) showing prevalently somatic small fiber neuropathy (SFN). A confocal study of epidermal innervation in the patient and a control subject: leg epidermal innervation disclosed by confocal microscope (×40) in an age-matched control subject (left panel), and the x-ALD patient case 2 (right panel). Nerve fibers are marked in red by a pan-neuronal marker PGP 9.5 whereas, the collagen staining is shown in green. The basement membrane separating epidermis from dermis is marked by collagen staining. Free-ending PGP immunoreactive fibers are evident in the epidermis of the control (arrows) whereas, the patient showed a marked decrease of such fibers, often fragmented (arrows). PGP, protein gene product; COLL, collagen."
      }
    ]
  },
  {
    "id": "PMC6374869_multi",
    "image": [
      "images/PMC6374869-f1.png",
      "images/PMC6374869-f2.png",
      "images/PMC6374869-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"First Record Mutations in the Genes ASPA and ARSA Causing Leukodystrophy in Jordan\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigrees of the studied cases. The dead proband TF106_1 belongs to first-cousin parent once removed. The patient TF107_1 belongs to a first-cousin parent.\n\nFigure 2: Figure 2. Segregation analysis of the identified variant in the patient TF106_1.\n\nFigure 3: Figure 3. Segregation analysis of the identified variant in the patient TF107_1."
      }
    ]
  },
  {
    "id": "PMC6400567_multi",
    "image": [
      "images/PMC6400567-f1.png",
      "images/PMC6400567-f2.png",
      "images/PMC6400567-f3.png",
      "images/PMC6400567-f4.png",
      "images/PMC6400567-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Deubiquitinating enzyme USP30 maintains basal peroxisome abundance by regulating pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Overexpressed USP30 localizes to peroxisomes. (A and B) COS7 cells expressing USP30-Flag (red) and mitochondrial marker OMP-25-GFP (A) or stained for peroxisome marker PMP70 (green; B). (C) Schematic of USP30-Flag, PMP34-USP30-Flag, and TOM20-USP30-Flag constructs show the site of the catalytic mutation (*C77S). (D) COS7 cells expressing TOM20-USP30-Flag or PMP34-USP30-Flag (red) and stained for PMP70 (green). (E) Thresholded MCC of PMP70-stained peroxisomes (MPO) colocalized with USP30-Flag, PMP34-USP30, TOM20-USP30, or ATP5A (mock). (F) COS7 cells expressing SA-PEX16-GFP (green) with mitochondrial proteins FIS1-Myc, TOM20-Cer, USP35-HA, or USP30 constructs (red) as indicated. Mitochondrial localization shown in Fig. S1 G. (G) COS7 coexpressing USP30-Flag (red), sa-PEX16 (green), and OMP25-Cer (blue). Statistical significance (Student’s t test): ****, P ≤ 0.0001; ns, P ≥ 0.05 (n = 3; 30 cells/trial). White boxes indicate zoomed region. Bars: 10 µm; 5 µm in zoom.\n\nFigure 2: Figure 2. Overexpressed USP30 reduces peroxisome loss induced by starvation. (A) Immunofluorescence of HeLa cells transfected with USP30-Flag, PMP34-USP30-Flag, or TOM20-USP30-Flag or mock transfected. Cells grown in DMEM or HBSS for 24 h, stained for PMP70 and Flag. (B) Quantification of the peroxisome density in A and E, relative to mock DMEM (n = 3; 30 cells/trial). (C) HeLa lysates expressing USP30-Flag, analyzed by immunoblotting for PEX14 and GAPDH. (D) Quantification of PEX14/GAPDH density ratio in C compared with mock DMEM (n = 6). (E) HeLa cells expressing USP30-Flag C77S or PMP34-USP30-Flag C77S, costained for PMP70. (F and G) HeLa cells expressing PEX26-RG alone (F) or coexpressed with USP30-Flag (G). (H) Quantification of average percent lysosomal peroxisomes (n = 3; 50 cells/trial). Statistical significance (Student’s t test): *, P ≤ 0.05; **, P ≤ 0.01; ***, P ≤ 0.001; ****, P ≤ 0.0001. Bars: 20 µm (A and E); 10 µm (F and G).\n\nFigure 3: Figure 3. Silencing USP30 induces pexophagy and is opposed by PEX2. (A) Confocal immunofluorescent images of PMP70 in HeLa cells treated with siRNA against USP30 (siUSP30) or a nontargeting siRNA (siCTRL) grown in DMEM or HBSS for 24 h. (B) Quantification of the relative peroxisome density in A, relative to siCTRL DMEM. (C) Immunoblots of PEX14 and GAPDH in HeLa cells treated with siRNA as in A. (D) Average PEX14 levels in C, compared with GAPDH levels and normalized to siCTRL DMEM. (E) ATG5 WT and ATG5−/− MEFs, treated with siCTRL or siUSP30, under DMEM or HBSS, stained for PMP70. (F) Quantification of E, with all treatment values relative to siCTRL ATG5 WT. (G) HeLa cells treated with siCTRL or siUSP30 were incubated with 5 µM of chloroquine (CQ) and stained for PMP70. (H) Quantification of G relative to siCTRL −CQ. (I) HeLa cells treated with siATG12 or siNBR1 cotreated with either siCTRL or siUSP30, stained for PMP70. (J) Quantification of I relative to siCTRL treatment. (K) Cells treated with siRNA against PEX2 (siPEX2) and codepleted of siUSP30 or siCTRL. Cells were grown in either DMEM or HBSS for the final 24 h and stained for PMP70. (L) Quantification of K, with all treatment groups relative to DMEM siCTRL. Statistical significance (Student’s t test): **, P ≤ 0.01; ***, P ≤ 0.001; ****, P ≤ 0.0001; ns, P ≥ 0.05; n = 3; 50 cells/trial. Bars, 20 µm.\n\nFigure 4: Figure 4. Knockdown of USP30 results in increased ubiquitined PEX5 and PMP70. (A) Knockdown of PEX5 (siPEX5) in HeLa cells, with overexpression of USP30-GFP grown in DMEM or HBSS for 24 h. Cells stained for PMP70. (B) Quantification of A, all treatment values relative to siCTRL DMEM. (C) Immunoprecipitation of HA-Ub, performed in HEK293 cells stably expressing HA-Ub. Cells were mock-treated or treated with siCTRL or siUSP30 under DMEM and HBSS conditions, probing for PMP70, PEX5, and catalase. (D) Quantification of PEX5 and PMP70 levels immunoprecipitated in C, relative to mock-treated DMEM. Each condition was normalized to the input. (E) HeLa cells stained for endogenous NBR1 (green) and PMP70 (red), either mock transfected or overexpressing USP30-GFP (white). (F) MCC of PMP70 (or Mpo) colocalized with NBR1 representative images in E. Statistical significance (Student’s t test): *, P ≤ 0.05; **, P ≤ 0.01, ***, P ≤ 0.001; ns, P ≥ 0.05; n = 3; 30 cells/trial. Bars: 20 µm and 5 µm in zoom.\n\nFigure 5: Figure 5. USP30 overexpression can rescue peroxisome levels induced by mutation of the AAA ATPase. (A) HeLa cells treated with siRNA against PEX1 (siPEX1) or siCTRL, then mock-transfected or transfected with USP30-Flag, costained for PMP70. (B) Quantification of A with all treatment values calculated relative to mock siCTRL. Representative images for PMP34-USP30 are found in Fig. S2 A. (C) Human fibroblast cells from healthy (WT) or PEX1 G843D mutation overexpressing USP30-Flag and imaged as in A. (D) Quantification of peroxisome density with respect to mock-treated WT cells in C. (E) Model of PEX2 and USP30 in pexophagy. Peroxisomes are maintained by a balance between the action of USP30 and PEX2. Excess of PEX2 results in pexophagy. (F) PEX2 is responsible for ubiquitinating PMP70 and PEX5. PMP70 is deubiquitinated by USP30, while PEX5 can be removed by the AAA ATPase or deubiquitinated by USP30. Statistical significance (Student’s t test): **, P ≤ 0.01; ***, P ≤ 0.001; ****, P ≤ 0.0001; ns, P ≥ 0.05; n = 3; 30 cells/trial. Bars, 20 µm."
      }
    ]
  },
  {
    "id": "PMC6438966_multi",
    "image": [
      "images/PMC6438966-f1.png",
      "images/PMC6438966-f2.png",
      "images/PMC6438966-f3.png",
      "images/PMC6438966-f4.png",
      "images/PMC6438966-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of liver receptor homologue-1 by DDB2 E3 ligase activity is critical for hepatic glucose metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. LRH-1 protein is degraded by the ubiquitin proteasome pathway. (A) FLAG-mLRH-1 or FLAG-hLRH-1 was transfected into HEK293T cells. After 24 h, cells were treated with DMSO (vehicle control) or MG-132 (10 μM) for 24 h. Cell lysates were analyzed by immunoblotting with the anti-LRH-1-N antibody. (B) HepG2 cells were serum-starved overnight and treated with MG-132 (0–40 μM) for 6 h. Protein levels of endogenous LRH-1 were detected by immunoblotting with the anti-LRH-1 antibody. Numbers below the blot are the relative densitometric values normalized to those of β-actin. (C) FLAG-mLRH-1 or empty vector (−) was co-transfected with HA-Ub into HEK293T cells. After 24 h, cells were treated with MG-132 (10 μM) for 24 h. Cell lysates were immunoprecipitated with the anti-LRH-1-N antibody and immunoblotted with the anti-LRH-1-N or anti-HA. (D) FLAG-mLRH-1 was co-transfected with empty vector (−) or HA-Ub [wild type (WT), lysine-less Ub mutant (K0), lysine 48 Ub mutant (K48), or lysine 63 Ub mutant (K63)] into HEK293T cells. Cell lysates were analyzed by immunoblotting with the anti-LRH-1-N antibody. (E) FLAG-mLRH-1 was co-transfected with HA-Ub [WT, lysine 48 to arginine Ub mutant (K48R), lysine 63 to arginine Ub mutant (K63R), or double lysines mutant (K48/63R)] or empty vector in HEK293T cells. After 24 h, cells were treated with MG-132 (10 μM) for 24 h. Cell lysates were immunoprecipitated with the anti-LRH-1-N antibody and immunoblotted with the anti-LRH-1-N or anti-HA antibodies. Asterisk indicates heavy chain IgG background. Uncropped images of blots were shown in Supplementary Fig. S5.\n\nFigure 2: Figure 2. CRL4 ubiquitin ligases regulate LRH-1 protein degradation. (A) FLAG-mLRH-1 was transfected into HEK293T cells. After 24 h, cells were treated with DMSO (vehicle control) or MLN4924 (10 μM) for 24 h. Cell lysates were analyzed by immunoblotting with the anti-LRH-1-N antibody. Numbers below the blot are the average of densitometric values normalized to those of GAPDH. (B) HepG2 cells were serum-starved overnight and treated with DMSO or MLN4924 for 24 h. Protein levels of endogenous LRH-1 were determined by immunoblotting with the anti-LRH-1 antibody. Numbers below the blot are the average of densitometric values normalized to those of GAPDH. (C) FLAG-mLRH-1 was co-transfected with FLAG-tagged dominant negative constructs of Cullin 1, 2, 3, 4A, 4B, and 5 or empty vector (−) into HEK293T cells. After 48 h, cell lysates were subjected to immunoblotting analysis with anti-LRH-1-N or anti-FLAG antibodies. β-actin was used as the loading control. Uncropped images of blots were shown in Supplementary Fig. S6.\n\nFigure 3: Figure 3. CUL4-DDB1-DDB2 ubiquitin ligase complex affects LRH-1 protein degradation. (A) HEK293T cells transduced with shRNA specific for CUL4A, CUL4B, DDB1 or LacZ (negative control) were transfected with FLAG-hLRH-1. Cell lysates were analyzed by immunoblotting with antibodies as specified. (B) HepG2 cells were transduced with the specified shRNA and cell lysates were analyzed by immunoblotting with antibodies as specified. (C) HepG2 cells were transduced with shRNA specific for DDB2 or LacZ. Endogenous protein levels were analyzed by immunoblotting with anti-LRH-1 or anti-DDB2 antibodies. (D) FLAG-mLRH-1 was co-transfected with Myc-DDB2, FLAG-DDB1 or vector into HEK293T cells. After 48 h, cell lysates were subjected to immunoblotting analysis with anti-LRH-1-N, anti-Myc or anti-FLAG antibodies. Numbers below the blot are the relative densitometric values normalized to those of GAPDH. Uncropped images of blots were shown in Supplementary Fig. S7.\n\nFigure 4: Figure 4. LRH-1 interacts with DDB2 through its DNA binding domain. (A) EGFP-hLRH-1 and/or Myc-DDB2 or empty vector were transfected into HEK293T cells. After 42 h, cells were incubated with MG-132 (10 μM) for 6 h, and cell lysates were immunoprecipitated with the anti-Myc antibody and immunoblotted with antibodies as indicated. (B) HepG2 cell lysates were immunoprecipitated with the anti-DDB2 antibody or control (IgG) antibody and immunoblotted with antibodies as indicated. (C) EGFP-mLRH-1 or EGFP-hLRH-1 were transfected into HEK293T cells. After 48 h, cell lysates were incubated with bead-bound GST or GST-DDB2. Bound protein was subjected to immunoblotting with anti-LRH-1-N or anti-GST antibodies. (D) EGFP-mLRH-1 truncated constructs or empty vectors were transfected into HEK293T cells. After 48 h, cell lysates were incubated with bead-bound GST-DDB2 and immunoblotted with the anti-GFP antibody. The results are summarized below the blot. Uncropped images of blots were shown in Supplementary Fig. S8.\n\nFigure 5: Figure 5. DDB2 promotes LRH-1 ubiquitination and destabilizes LRH-1 protein turnover. (A) EGFP-hLRH-1 was co-transfected with empty vector (−) or Myc-DDB2 into HEK293T cells. After 42 h, cells were treated with DMSO or MG-132 (10 μM) for 6 h. Cell lysates were immunoprecipitated with the anti-LRH-1-N antibody and immunoblotted with indicated antibodies. (B) FLAG-hLRH-1 was co-transfected with empty vector or Myc-DDB2 into HEK293T cells. After 24 h, cells were treated with 100 μg/ml cycloheximide (CHX) for the specified periods of time. Cell lysates were immunoblotted with anti-LRH-1-N or anti-Myc antibodies. Quantification of the levels of LRH-1 protein was done by normalizing densitometric values to those of GAPDH. Values were mean ± SEM of four independent experiments. Uncropped images of blots were shown in Supplementary Fig. S9."
      }
    ]
  },
  {
    "id": "PMC6438966_multi_2",
    "image": [
      "images/PMC6438966-f6.png",
      "images/PMC6438966-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Regulation of liver receptor homologue-1 by DDB2 E3 ligase activity is critical for hepatic glucose metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Insulin increases LRH-1 protein levels. (A) HepG2 cells were serum-starved overnight, and treated with various concentrations of insulin for 2 h. Cell lysates were immunoblotted with the anti-LRH-1 antibody. (B) HepG2 cells were serum-starved overnight and incubated with 75 ng/ml insulin for specified periods of time. Protein levels of endogenous LRH-1 were determined by immunoblotting with the anti-LRH-1 antibody and quantified by normalizing densitometric values to those of β-actin. Data are expressed as mean ± SEM relative to control 0 h of three independent experiments (lower panel). *P < 0.05 compared to control. (C) HepG2 cells were serum-starved overnight, followed by MG-132 (10 μM) treatment for 30 minutes prior to insulin (100 nM) incubation for 2 h. Cell lysates were immunoprecipitated with the anti-LRH-1 antibody and immunoblotted with indicated antibodies. (D) HepG2 cells stable for Myc-DDB2 or control Myc were serum-starved for overnight and treated with 200 ng/ml insulin for 90 minutes. Cell lysates were analyzed by immunoblotting with antibodies as indicated. Uncropped images of blots were shown in Supplementary Fig. S10.\n\nFigure 7: Figure 7. Effects of DDB2 on LRH-1-mediated gene expression and glucose metabolism. (A) Myc-DDB2 or empty control vector (Myc) was transfected into HepG2 cells. Protein levels of endogenous LRH-1 and Myc-DDB2 were analyzed by immunoblotting. (B) mRNA levels of LRH-1, CYP7A1, SHP, and GCK were quantified by RT-qPCR. Data are expressed as mean ± SEM relative to control of four independent experiments. *P < 0.05 compared to control. (C) The SHP or Gck promoter-luciferase construct was co-transfected with plasmids expressing indicated proteins or control empty vector (EV) into HEK293T cells. After 24 h, luciferase activity was measured. Data are represented as mean ± SEM of five independent experiments. *P < 0.05. (D~F) HepG2 cells were transduced with shRNA specific for DDB1, DDB2, CUL4A, CUL4B or control LacZ as indicated. (D) mRNA levels of LRH-1 and GCK were quantified by RT-qPCR (n = 6). (E) Protein levels were determined by immunoblotting with the indicated antibody. (F) Glucose consumption was analyzed (n = 3). (G) Glucose-6-phosphate levels were measured (n = 5). Data are expressed as mean ± SEM. *P < 0.05, **P < 0.001, ***P < 0.0001 compared to control. Uncropped images of blots were shown in Supplementary Fig. S11."
      }
    ]
  },
  {
    "id": "PMC6463464_multi",
    "image": [
      "images/PMC6463464-f1.png",
      "images/PMC6463464-f2.png",
      "images/PMC6463464-f3.png",
      "images/PMC6463464-f4.png",
      "images/PMC6463464-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Myricanol rescues dexamethasone‐induced muscle dysfunction via a sirtuin 1‐dependent mechanism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MY rescues DEX‐induced muscle atrophy in C2C12 myotubes. (A) Chemical structure of MY. (B) Cell viability of C2C12 myotubes treated with DEX and different concentrations of MY. (C) Expression levels of MyHC, atrogin‐1, and MuRF1. GAPDH was used as a loading control. Data are shown as mean ± SD, n = 6–9. *P < 0.05, **P < 0.01, MY vs. DEX. # P < 0.05, ## P < 0.01, control vs. DEX. DEX, dexamethasone; MuRF1, muscle ring finger 1; MY, myricanol; MyHC, myosin heavy chain.\n\nFigure 2: Figure 2. MY protects against DEX‐induced muscle atrophy through activating SIRT1. (A) MY increased SIRT1 expression dose‐dependently in DEX‐treated C2C12 myotubes. (B) Interactive sites between MY and SIRT1 by docking analysis. (C) MY enhanced SIRT1 deacetylase activity in C2C12 myotubes. (D) EX‐527 almost reversed MY‐induced changes of SIRT1, MuRF1, and atrogin‐1 expression in DEX‐treated myotubes. (E) MY increased phosphorylation of Akt and FoxO3a in DEX‐treated C2C12 myotubes. GAPDH was used as a loading control. Data are shown as mean ± SD, n = 6–9. *P < 0.05, **P < 0.01, MY or EX‐527 vs. DEX. ## P < 0.01, control vs. DEX. DEX, dexamethasone; MY, myricanol; SIRT1, sirtuin 1.\n\nFigure 3: Figure 3. MY reverses DEX‐induced loss of mitochondrial content and function in C2C12 myotubes. (A) MY increased mitochondrial content in DEX‐treated C2C12 myotubes, as assessed by MitoTracker Green staining. Scale bar = 100 μm. The images were captured using a Leica TCS SP8 Confocal Laser Scanning Microscope System with a 10× objective. (B) The effect of MY on ATP concentration in DEX‐treated C2C12 myotubes. (C) MY increased the expression levels of Cox2, Tom20, UCP3, and PGC‐1α. GAPDH was used as a loading control. (D) MY reversed DEX‐induced decrease of PGC‐1α expression and increase of acetylated PGC‐1α level, which were abolished by co‐treatment of EX‐527. (E) MY reversed DEX‐induced increases of total and acetylated FoxO3a levels, which were abolished by co‐treatment of EX‐527. (F) MY increased OCR in DEX‐treated C2C12 myotubes, as assessed by Seahorse assay. Data are shown as mean ± SD, n = 6–9. *P < 0.05, **P < 0.01, MY vs. DEX. # P < 0.05, ## P < 0.01, control vs. DEX or EX‐527. DEX, dexamethasone; MY, myricanol; OCR, oxygen consumption rate; UCP3, uncoupling protein 3.\n\nFigure 4: Figure 4. Effects of MY on apoptosis and autophagy in DEX‐treated C2C12 myotubes. (A) MY elevated the expression of autophagy‐related proteins LC3 and Beclin1 and suppressed the expression of p62. (B) MY increased lysosome content in DEX‐treated C2C12 myotubes, as assessed by LysoTracker fluorescence staining. Scale bar = 100 μm. The images were captured using a Leica TCS SP8 Confocal Laser Scanning Microscope System with a 10× objective. (C) Expression of apoptosis‐associated proteins, Bcl‐2, Bax, cleaved caspase‐3. GAPDH was used as a loading control. (D) Co‐treatment of EX‐527 abolished the effect of MY on expression of apoptosis‐associated proteins. Data are shown as mean ± SD, n = 6–9. *P < 0.05, **P < 0.01, MY or EX‐527 vs. DEX. ## P < 0.01, control vs. DEX. DEX, dexamethasone; MY, myricanol.\n\nFigure 5: Figure 5. MY protects against DEX‐induced muscle dysfunction in mice. (A) Body weight. [two‐way ANOVA: time effect F (10, 180) = 60.98, P < 0.0001; treatment effect F (6, 18) = 11.96, P < 0.0001; interaction F (60, 180) = 11.26, P < 0.0001]. (B) Grip strength. [two‐way ANOVA: time effect F (5, 140) = 81.00, P < 0.0001; treatment effect F (7, 28) = 152.00, P < 0.0001; interaction F (35, 140) = 6.40, P < 0.0001]. (C) Forced swimming time. (D) Comparison of representative samples of dissected skeletal muscle, including Gast, soleus, EDL, Quad, and TA. (E) The ratios of Gast and Quad muscle weight to body weight. (F) Representative H&E staining of myofiber cross section of Gast. Scale bar = 100 or 50 μm on top and bottom, respectively. A microscope with a 10× or 20× objective was used to capture the images. (G) The cross‐sectional diameter of Gast muscle fibre. Ctrl: PEG 400 solution; ctrl + MY‐50: PEG 400 solution with 50 mg/kg MY; DEX: PEG 400 solution with 25 mg/kg dexamethasone; DEX + MY‐5: DEX solution with 5 mg/kg MY; DEX + MY‐50: DEX solution with 50 mg/kg MY; DEX + EX‐527: DEX solution with 10 mg/kg EX‐527; DEX + MY‐50 + EX‐527: DEX solution with 50 mg/kg MY and 10 mg/kg EX‐527. Data are shown as mean ± SD, n = 6. *P < 0.05, **P < 0.01, DEX + MY‐5 vs. DEX. & P < 0.05, && P < 0.01, DEX + MY‐50 vs. DEX. # P < 0.05, ## P < 0.01, control vs. DEX. ANOVA, analysis of variance; DEX, dexamethasone; EDL, extensor digitorum longus; Gast, gastrocnemius; MY, myricanol; Quad, quadriceps; TA, tibialis anterior."
      }
    ]
  },
  {
    "id": "PMC6463464_multi_2",
    "image": [
      "images/PMC6463464-f6.png",
      "images/PMC6463464-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Myricanol rescues dexamethasone‐induced muscle dysfunction via a sirtuin 1‐dependent mechanism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Western blotting analysis of key proteins in Gast muscle. (A) The expression of SIRT1, atrogin‐1, MuRF1, phosphorylated Akt, total Akt, phosphorylated FoxO3a, and total FoxO3a. (B) The expression of LC3, Beclin1, p62, cleaved caspase‐3, Bcl‐2, and Bax. (C) The expression of PGC‐1α, Tom20, UCP3, and Cox2. β‐actin was used as a loading control. Data are shown as mean ± SD, n = 6. *P < 0.05, **P < 0.01, DEX + MY‐5 vs. DEX. & P < 0.05, && P < 0.01, DEX + MY‐50 vs. DEX. # P < 0.05, ## P < 0.01, control vs. DEX. DEX, dexamethasone; MuRF1, muscle ring finger 1; MY, myricanol; SIRT1, sirtuin 1; UCP3, uncoupling protein 3.\n\nFigure 7: Figure 7. Schematic models of molecular targets of MY in DEX‐induced muscle atrophy. DEX, dexamethasone; MY, myricanol."
      }
    ]
  },
  {
    "id": "PMC6525147_multi",
    "image": [
      "images/PMC6525147-f1.png",
      "images/PMC6525147-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Unloosing the Gordian knot of peroxisome formation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic overview of the molecular machineries involved in the biogenesis of mammalian peroxisomes. Matrix protein import: After synthesis on free ribosomes, cargo proteins containing the peroxisomal targeting signals PTS1 or PTS2 bind to the corresponding cytosolic receptors Pex5 or Pex7 and form receptor-cargo complexes. The Pex7–cargo complex requires Pex5L, the long isoform of Pex5, for import. Import is achieved by a complex set of integral or peripheral PMPs that form the matrix protein import machinery, which mediates docking of the cargo-bound import receptor at the peroxisomal membrane, cargo translocation into the matrix of the organelle by a dynamic translocon, and export of the receptor back to the cytosol. Recycling of the receptor involves its ubiquitination (ub) and extraction from the membrane by an AAA-ATPase complex (Pex1, Pex6). Membrane assembly and insertion of PMPs (containing an mPTS) depends on Pex19, Pex3 and Pex16. Pex19 functions as a cycling receptor/chaperone, which binds the PMPs in the cytosol and interacts with Pex3 at the peroxisomal membrane. Proliferation, growth and division: Pex11α, Pex11β and Pex11γ are involved in the regulation of peroxisome size and number. Pex11β remodels the peroxisomal membrane, and interacts with the membrane adaptors Mff and Fis1, which recruit the dynamin-like fission GTPase Drp1 to peroxisomes, which is activated by Pex11β. Motility and Inheritance: Miro1 serves as membrane adaptor for the microtubule-dependent motor proteins kinesin and dynein [19•, 38••, 64••]. Tethering: ACBD5 and ACBD4 interact with ER-resident VAPA/B to mediate peroxisome-ER contacts. Membrane transporter: only the ABC transporter proteins involved in fatty acid uptake are shown. Proteins with a dual localisation to both peroxisomes and mitochondria are marked with an asterisk.\n\nFigure 2: Figure 2. Schematic representation of mechanisms for peroxisome formation in mammalian cells. Peroxisome formation by growth and division follows a multistep maturation process involving peroxisomal membrane remodelling and elongation, membrane constriction and final scission. Membrane expansion requires peroxisome-ER contact (red line) and lipid transfer (red arrow), generating a membrane compartment which imports newly synthesised PMPs and matrix proteins. De novo peroxisome formation: In the absence of pre-existing peroxisomes, preperoxisomal vesicles can be generated at the ER (EDV) and mitochondria (MDV), which may fuse and mature into new import-competent peroxisomes. These newly formed peroxisomes will further multiply by growth and division. In the presence of peroxisomes, preperoxisomal vesicles may fuse with growing or existing peroxisomes to supply certain proteins and lipids. EDV, ER-derived vesicles; MDV, mitochondria-derived vesicles; newly formed peroxisomes are coloured in light green."
      }
    ]
  },
  {
    "id": "PMC6554619_multi",
    "image": [
      "images/PMC6554619-f1.png",
      "images/PMC6554619-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Lipid Droplet and Peroxisome Biogenesis: Do They Go Hand-in-Hand?\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) De novo peroxisome biogenesis in yeast and mammalian cells. PPVs containing the docking complex proteins are generated independently of Pex3 and Pex19 at ER subdomains containing Pex30. PPVs containing ring complex proteins are generated in a Pex3- and Pex19-dependent manner. ESCRT-III complex is required for scission of PPVs from the ER membrane. The two pools of PPVs fuse to form an import competent mature peroxisome. In mammals, Pex16-containing PPVs from ER and Pex3 and Pex14-containing PPVs from mitochondrial outer membrane fuse to form a functional peroxisome. (B) Lipid droplet biogenesis. Neutral lipid synthesizing enzymes generate sterol esters (SE) and triglycerides (TG) to form a lens-like structure in the lipid bilayer. The ER regions are enriched with seipin, FIT proteins, and Pex30/MCTP2. As the lens grows the LD buds into the cytoplasm. In yeast, LDs remain attached to the ER subdomains containing Pex30/MCTP2 and seipin but no FIT proteins.\n\nFigure 2: Figure 2. Link between peroxisome and LD biogenesis: The formation of new Pex14-containing PPVs and LDs occur at the same ER subdomains, which are positive for Pex30/MCTP2 proteins. Mature peroxisomes also physically associate with LDs. Tethers identified so far include ABCD1 on peroxisomes, which interacts with Spastin on LDs. Other tethers may also be involved in peroxisome-LD contacts. Pex19 is a cytosolic protein required for peroxisomal protein targeting, which when farnesylated targets a LD protein UBXD8 to LDs."
      }
    ]
  },
  {
    "id": "PMC6557986_multi",
    "image": [
      "images/PMC6557986-f1.png",
      "images/PMC6557986-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Dynamics of Peroxisome Homeostasis and Its Role in Stress Response and Signaling in Plants\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The life cycle of peroxisome. a: Some PMPs are targeted to the ER and localized in special ER subdomains, where new preperoxisomes subsequently bud off. b: The remainder of PMPs are directly inserted into the peroxisomal membrane through a PEX3/PEX19-dependent pathway or another unknown pathway. c: PTS1 and PTS2 proteins interact with their receptor, PEX5 or PEX7, respectively. The receptor/cargo complex is then transported into the peroxisome lumen through the docking complex, composed of PEX13 and PEX14 in Arabidopsis. After unloading its cargo protein, PEX5 is mono-ubiquitinated by the PEX4/PEX22 (E2 ubiquitin conjugases) and PEX2/PEX12/PEX10 (E3 ligases) complexes. Subsequently, Pex5 is retrotranslocated to the cytosol by the PEX1/PEX6 complex for recycling. d: Mature peroxisomes elongate and divide into two new peroxisomes. e: Oxidative or obsoleted peroxisomes can be degraded by pexophagy under the action of ATGs.\n\nFigure 2: Figure 2. H2O2-mediated retrograde signaling. Chloroplasts, mitochondria, and peroxisomes are linked together to facilitate the shuttling of intermediate metabolites between them. When plants are subjected to environmental stresses, a large amount of H2O2 is produced in these three organelles. H2O2 can be used as a signal molecule to regulate the expression of nuclear response genes through the MAPK cascade or potentially through other unknown pathways. H2O2 in chloroplasts also promotes the dissociation of the transcription factor PTM from the chloroplast membrane to regulate nuclear gene expression. M, mitochondria; C, chloroplast; P, peroxisome; N, nucleus."
      }
    ]
  },
  {
    "id": "PMC6587667_multi",
    "image": [
      "images/PMC6587667-f1.png",
      "images/PMC6587667-f2.png",
      "images/PMC6587667-f3.png",
      "images/PMC6587667-f4.png",
      "images/PMC6587667-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomes and Oxidative Stress: Their Implications in the Modulation of Cellular Immunity During Mycobacterial Infection\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Host pathogen interaction: pathogenic Mtb enters the host via interaction between different host surface receptors like Toll like receptors (TLRs), mannose receptors (MRs), scavenger receptors (SRs), complement receptors (CRs) and so on and cognate Mtb ligands. These interactions modulates the phagosome maturation, downstream signaling molecules (like MYD88, IRAK-4, etc.), signaling pathways (like MAPK, autophagy, apoptosis, etc.) and transcription factors (like PPARG and NFκB) to favor bacillary persistence and reduced antigen presentation inside host cells.\n\nFigure 2: Figure 2. (A) Oxidative stress response. Following entry of Mtb into host cells results in the generation of oxidative stress responses. Mtb employs several strategies to combat these stress mechanisms, which includes activation of anti-oxidant enzymes (like superoxide dismutase, catalase/peroxidase, etc.), redox-sensors (like DosR regulon system) and redox buffering system. Phagocytosis of Mtb leads to formation of superoxide radical via NADPH oxidase. As evasion strategy, Mtb genes reduce the superoxide radical into less toxic intermediates using anti-oxidant enzymes. The pathway eventually inhibits the process of autophagy, apoptosis and cellular damage. (B) Mycobacterial oxidative stress response gene family protein, WhiB, combats the redox and nitrosative stress via the Fe–S clusters while DosS and T gene from DosR regulon senses the redox imbalance and activates the DosR to furtheractivate the dormancy pathway.\n\nFigure 3: Figure 3. Crosstalk between mitochondria and peroxisome: the pathogenic Mtb enters into the macrophage cells via different PRRs like mannose receptor (MRs) or TLRs. After phagocytosis, Mtb modulates cellular oxidative stress mechanisms. Inside the mitochondria, NOX2 generates the superoxide radicals during the ETC cycle. These superoxide radicals are then metabolized to hydrogen peroxide by superoxide dismutase. Anti-oxidant enzyme catalase eventually breaks down the toxic H2O2 into water and molecular oxygen. This phenomenan helps to increase the bacillary count inside the cells. In peroxisomes, the bacteria metabolize the stored fatty acids and lipids for its survival. During the peroxisomal β- fatty acid oxidation, acyl CoA oxidases, and other peroxisomal oxidases metabolizes the very long chain fatty acids (VLCFA) into short chain fatty acids (SCHFA) and acetylCoA. The SCHFA is exported into the mitochondria for further metabolism to generate ATP. The acetyl CoA is used as an intermediate molecule in the glyoxylate shunt pathway. In addition to generation of SCHFA, cellular ROS is formed which is further catalyzed by the array of anti-oxidant enzymes in peroxisomes like catalase, glutathione peroxidise (GPX), and so on. This phenomenon further provides a favorable niche for the bacilli to survive.\n\nFigure 4: Figure 4. De novo biogenesis of peroxisomes: peroxisomes originate from endoplasmic reticulum (ER) and mitochondria. With the help of different peroxins like PEX3, 16, 19, and also peroxisomal membrane proteins (PMPs) active organelle is formed. Balance in cellular oxidative metabolism results in balanced redox interplay between pro- and anti-oxidants of peroxisomes thereby helping in the proper growth and division of daughter peroxisomes from pre-existing peroxisomes via the expression of PEX11, DLP-1, Fis, and Mff.\n\nFigure 5: Figure 5. A representation for Pexophagy: PEX5 is stabilized by the mono-ubiquitination at K464 position via TRIM37, which further helps in maintaining the peroxisome homeostasis. In response to peroxisomal ROS, PEX5 undergoes polyubiquitination via activation of ATM-kinase. PEX5 is degraded via proteosome lysis thereby inducing Pexophagy via activation of autophagy adaptor molecules SQSTM1/p62 and NBR1. Degradation of PEX5, leads to peroxisomal disintegration and removal of PEX3 and other peroxins. Removal of PEX3 initiates peroxisome sequestration via activation of PEX14, which acts as a docking site for LC3II. The interaction eventually leads to degradation of bulky and damaged organelles via Pexophagy."
      }
    ]
  },
  {
    "id": "PMC6603303_multi",
    "image": [
      "images/PMC6603303-f1.png",
      "images/PMC6603303-f2.png",
      "images/PMC6603303-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Applications of Genome Editing Technology in Animal Disease Modeling and Gene Therapy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Genome editing exploit endogenous DNA repair mechanism. A) Genome editing nucleases (ZFNs, TALENs and CRISPR-Cas9) induce DSBs at targeted sites. DSBs are repaired by NHEJ or, in the presence of donor template, HDR. NHEJ will induce indels at editing site and HDR could insert predicted DNA fragments. The inhibition of NHEJ key enzyme DNA ligase IV could increase the efficiency of HDR. B) NHEJ and HDR would occur in different stages of cell cycle.\n\nFigure 2: Figure 2. Schematic overview of constructing disease animal model in four major ways. A) Cultured embryonic stem cells (ESCs) can be used to introduce morbigenous mutations using genome editing tools. The edited ESCs can be injected into host blastocysts, whereafter are implanted into pseudo-pregnant to produce disease animal; B) Animal zygote is directly edited and the edited zygote is developed into diseased model; C) Disease animal could be generated by combining somatic cell genome editing and somatic cell nuclear transfer (SCNT) technology; D) Genome editing elements are packaged by viral vectors. Disease animal can be generated by administration of engineered virus.\n\nFigure 3: Figure 3. Ex vivo and in vivo genome editing therapy. Top: in ex vivo editing therapy, cells are isolated from the patient to be treated, edited and then re-engrafted. Bottom: for in vivo editing therapy, engineered nucleases are delivered by viral or non-viral approaches and directly injected into the patient for systemic or targeted tissues effect."
      }
    ]
  },
  {
    "id": "PMC6657955_multi",
    "image": [
      "images/PMC6657955-f1.png",
      "images/PMC6657955-f2.png",
      "images/PMC6657955-f3.png",
      "images/PMC6657955-f4.png",
      "images/PMC6657955-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"SIRT1 activation alleviates brain microvascular endothelial dysfunction in peroxisomal disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. ABCD1 or HSD17B4 silencing leads to molecular biomarker alteration and SIRT1 downregulation in HBMECs; an effect mimicked by SIRT1 inhibition using sirtinol. Representative western blot images as well as intensity quantification showing SIRT1, tight-junction protein (Claudin 5) and adhesion molecule (ICAM1 and VCAM1) changes in (A) ABCD1 or (B) HSD17B4 silenced HBMECs with or without sirtinol (20 µM) treatment at (C) basal or (D) TNF-α (10 ng/ml) treated condition. Data are the mean ± standard deviation of three different experiments. *P<0.05, **P<0.01 and ***P<0.001 vs. NT control group. NT, non-targeting; ABCD, ATP binding cassette subfamily D member 1; HBMECs, human brain microvascular endothelial cells; TNF, tumor necrosis factor; ICAM, intracellular cellular adhesion molecule; VCAM, vascular cellular adhesion molecule; NT, non-targeting.\n\nFigure 2: Figure 2. SIRT1 activation by resveratrol restores protein biomarker changes in HBMECs after ABCD1 or HSD17B4 silencing. Representative western blot images as well as intensity quantification showing SIRT1, tight-junction protein (Claudin 5) and adhesion molecule (ICAM1 and VCAM1) changes in (A) ABCD1 or (B) HSD17B4 silenced HBMECs with or without resveratrol (20 µM) treatment at (C) basal or (D) TNF-α (10 ng/ml) treated condition. Data are presented as the mean ± standard deviation of three different experiments. *P<0.05, **P<0.01 and ***P<0.001 vs. NT control group. #P<0.05 and ##P<0.01. NT, non-targeting; ABCD, ATP binding cassette subfamily D member 1; HBMECs, human brain microvascular endothelial cells; TNF, tumor necrosis factor; ICAM, intracellular cellular adhesion molecule; VCAM, vascular cellular adhesion molecule; si, small interfering; SIRT1, sirtuin1; NT, non-targeting.\n\nFigure 3: Figure 3. SIRT1 expression levels in HBMECs modulate endothelial-monocyte interactions. (A) Representative images showing adherence of fluorescent THP-1 cells to endothelial monolayers at different treatment condition. (B) Quantification of calcein AM labelled THP-1 cells that adhere to HBMECs at different conditions with or without TNF-α (10 ng/ml) treatment. Data are presented as the mean ± standard deviation of three different experiments. *P<0.05 and **P<0.01 vs. NT control group. #P<0.05. Scale bar: 10 µm. HBMECs, human brain microvascular endothelial cells; TNF, tumor necrosis factor; si, small interfering; SIRT1, sirtuin1.\n\nFigure 4: Figure 4. Regulation of SIRT1 on NF-κB and KLF4 following ABCD1 or HSD17B4 silencing. (A) Representative western blot images as well as (B) intensity quantification of p-IκBα, nuclear NF-κB and nuclear KLF4 in ABCD1 or HSD17B4 silenced HBMECs with or without sirtinol (20 µM) treatment at basal condition. (C) Representative western blot images as well as (D) intensity quantification of p-IκBα, nuclear NF-κB and nuclear KLF4 in ABCD1 or HSD17B4 silenced HBMECs with or without resveratrol (20 µM) treatment at basal condition. *P<0.05 and **P<0.01 vs. NT control group. #P<0.05. NT, non-targeting; ABCD, ATP binding cassette subfamily D member 1; HBMECs, human brain microvascular endothelial cells; TNF, tumor necrosis factor; NF, nuclear factor; si, small interfering; KLF4, Krüppel-like factor 4; NF, nuclear factor; p-IκBα, phosphorylated-inhibitor of NF-κB; NT, non-targeting.\n\nFigure 5: Figure 5. Regulation of SIRT1 on NF-κB and KLF4 following ABCD1 or HSD17B4 silencing at TNF-α treated condition. (A) Representative western blot images as well as (B) intensity quantification of p-IκBα, nuclear NF-κB and nuclear KLF4 in ABCD1 or HSD17B4 silenced HBMECs with or without sirtinol (20 µM) treatment at TNF-α (10 ng/ml) treated condition. (C) Representative western blot images as well as (D) intensity quantification of p-IκBα, nuclear NF-κB and nuclear KLF4 in ABCD1 or HSD17B4 silenced HBMECs with or without resveratrol (20 µM) treatment at TNF-α (10 ng/ml) treated condition. **P<0.01 and ***P<0.001 vs. the NT control group. #P<0.05 and ##P<0.05. NT, non-targeting; ABCD, ATP binding cassette subfamily D member 1; HBMECs, human brain microvascular endothelial cells; TNF, tumor necrosis factor; NF, nuclear factor; si, small interfering; KLF4, Krüppel-like factor 4; p-IκBα, phosphorylated-inhibitor of NF-κB; NT, non-targeting."
      }
    ]
  },
  {
    "id": "PMC6660958_multi",
    "image": [
      "images/PMC6660958-f1.png",
      "images/PMC6660958-f2.png",
      "images/PMC6660958-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Humanized yeast genetic interaction mapping predicts synthetic lethal interactions of FBXW7 in breast cancer\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Network representation of HYGIN. Genes are grouped into clusters with an extra central node, which represents the category name (GO slim term; see Additional file 4: Table S3). Edges connect categories (clusters) only\n\nFigure 2: Figure 2. Breast cancer sub-network of SL interactions. a Volcano plot of the average change of expression per gene expressed as log2 (cancer/normal) plotted against the log10 of the adjusted Wilcoxon P-value. Dots in red represent genes that have an average 2-fold or more decrease in expression. Back dots represent the 15 genes that are also in the HYGIN network. b Flow diagram showing the flow of data and methods used to generate the breast cancer specific subnetwork. The final breast cancer network had 15 genes that are down-regulated in breast cancer and 115 genes that interact with them. As a result, there are 130 genes (nodes) total in the breast cancer subnetwork. c Visualization of the breast cancer specific subnetwork generated using 15 genes in HYGIN that were found to be down-regulated in breast cancer (yellow) and their corresponding SL gene pairs. Edges represent proposed SL interactions between genes, and nodes (coloured based on GO slim terms) represent SL partners of the 15 genes\n\nFigure 3: Figure 3. Analyses of SL interactions of FBXW7. a TCGA gene expression of FBXW7 in 24 cancer types and corresponding normal tissue as calculated from RNA-seq data by expectation-maximization (log2). The averages of normal and tumor expression of FBXW7 for the same tissue type are plotted beside each other and colour-coded based on cancer type. Numbers of patient samples are indicated in the x-axis labels. b Box plot classifying multiple cell lines from the cancerRXgene database based on the expression of FBXW7; up-regulated (red) and down-regulated (blue). c-d Drug kill curves for cell lines where FBXW7 is down-regulated in blue, and cell lines that have up-regulated FBXW7 in red. c Drug curves for Cabozantinib, and (d) Selumetinib"
      }
    ]
  },
  {
    "id": "PMC6669072_multi",
    "image": [
      "images/PMC6669072-f2.png",
      "images/PMC6669072-f3.png",
      "images/PMC6669072-f4.png",
      "images/PMC6669072-f5.png",
      "images/PMC6669072-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Deficiency or activation of peroxisome proliferator-activated receptor α reduces the tissue concentrations of endogenously synthesized docosahexaenoic acid in C57BL/6J mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. Data are the mean ± SD, n = 8. Comparisons were based on the mRNA levels relative to WT (taken as 1). Values without a common superscript differed (P < 0.05). WT, wild-type mice; HZ, heterozygous mice; KO, knockout mice.\n\nFigure 3: Figure 3. Data are the mean ± SD, n = 8. Values without a common superscript differed (P < 0.05). WT, wild-type mice; HZ, heterozygous mice; KO, knockout mice; DHA, docosahexaenoic acid; EPA, eicosapentaenoic acid; AA, Arachidonic acid.\n\nFigure 4: Figure 4. Data are the mean ± SD, n = 16. Comparisons were based on mRNA levels relative to C group (taken as 1). **P < 0.01, ***P < 0.0001. C, control mice; CF, clofibrate-treated mice.\n\nFigure 5: Figure 5. Hepatic mRNA levels of Cpt1a and Ehhadh are shown in (D). Data are the mean ± SD, n = 16 (for A, B, and D) or 4 (for C). *P < 0.05, **P < 0.01, ***P < 0.0001. C, control mice; CF, clofibrate-treated mice; DHA, docosahexaenoic acid; EPA, eicosapentaenoic acid; AA, Arachidonic acid.\n\nFigure 6: Figure 6. (C) shows BDNF protein levels in brain cortex. Data are the mean ± SD, n = 16. (A) and (B). The comparison was based on the mRNA levels relative to the C group (taken as 1). *P < 0.05, ***P < 0.0001. C, control mice; CF, clofibrate-treated mice; BDNF, brain-derived neurotrophic factor."
      }
    ]
  },
  {
    "id": "PMC6763723_multi",
    "image": [
      "images/PMC6763723-f1.png",
      "images/PMC6763723-f2.png",
      "images/PMC6763723-f3.png",
      "images/PMC6763723-f4.png",
      "images/PMC6763723-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Novel Cellular Functions of Very Long Chain-Fatty Acids: Insight From ELOVL4 Mutations\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. VLC-SFA and VLC-PUFA elongation pathways. (A) VLC-SFA biosynthesis pathway. Elongation steps are performed by ELOVL1-7. Although some ELOVL family members catalyze specific steps in VLC-SFA synthesis, others are multifunctional and may catalyze multiple steps. Elongation of C24 substrates also may be performed by ELOVL4 (ELOVL4). (B) VLC-PUFA biosynthesis pathway. Desaturation and elongation steps are performed by ELOVL1-5, Δ5 Desaturase (fatty acid desaturase-1, FADS1), and Δ6 desaturase (fatty acid desaturase-2, FADS2) as indicated. Although some ELOVL family members catalyze specific steps in VLC-PUFA synthesis, others are multifunctional and may catalyze multiple steps. Elongation of C24 substrates also may be performed by ELOVL4 (ELOVL4). (C) VLC-PUFA are incorporated into phosphatidylcholine in the retina. Example shown contains the VLC-PUFA, 34:5n3 (green), and the long chain-PUFA, 22:6n3 (DHA). (D) VLC-SFA are incorporated into ω-O-acylceramides in the skin. Example shown contains the VLC-SFA, 28:0 (green) ω-O-linked with 18:2n3. (E) VLC-SFA are incorporated into sphingolipids in the brain. Example shown shows sphingomyelin containing the VLC-SFA, 30:0 (green) (panels C–E from Hopiavuori et al., 2019, used with permission).\n\nFigure 2: Figure 2. Predicted transmembrane topology for ELOVL4. (A) Predicted five transmembrane-spanning topology for ELOVL4 (Zhang et al., 2001; Molday and Zhang, 2010). (B) Predicted seven transmembrane-spanning topology for ELOVL4 (Ozaki et al., 2015; figures used with permission).\n\nFigure 3: Figure 3. Fatty acid elongation by the ELOVL family of enzymes. Diagram of the four-step fatty acid elongation cycle indicating the mammalian (ALL CAPITALS) and the yeast enzymes involved in each step. The ELOVL family elongasaes catalyze the initial condensation reaction (Kihara, 2012; figure used with permission).\n\nFigure 4: Figure 4. ELOVL4 protein and mRNA distribution in the adult mouse brain. (A) Immunofluorescent labeling for ELOVL4 in the postnatal day 60 mouse brain is widely distributed, but shows cell-specific distribution in different regions of the brain. (B) In situ hybridization (ISH) for Elovl4 mRNA in the mouse brain at P56 shows distribution similar to that of ELOVL4 protein. (Image from: Allen Institute for Brain Science Allen Mouse Brain Atlas for the P56 mouse brain, image number 69059903_134; http://mouse.brain-map. org). CB, cerebellum; BG, basal ganglia; CTX, cerebral cortex; HPF, hippocampal formation; HY, hypothalamus; M, medulla; MB, midbrain; MOB, main olfactory bulb; P, pons; cc, corpus callosum; fo, fornix; VL, lateral ventricle. Scale bars = 1 mm (figure from Sherry et al., 2017). Used with open access under the Creative Commons attribution license CC-BY, version 4.0; http://creativecommons.org/licenses/by/4.0/).\n\nFigure 5: Figure 5. Cell-specific expression of ELOVL4 in isocortex, hippocampus and cerebellum. (A–C) Cerebral Cortex (CTX). (A) Labeling for ELOVL4 is present in all layers of the cerebral cortex (CTX). Cells in the pyramidal layers (II/III and V) are most prominently labeled, but ELOVL4-positive cells also are present in the molecular layer (I), layer 4 (IV) and layer 6 (VI). (B) Labeling for the neuronal marker, NeuN. (C) Overlay of panels A and B shows close correspondence of ELOVL4 (red) and NeuN labeling (green). (D–F) Hippocampal formation (HPF). (D) Labeling for ELOVL4 is present in the cellular layers of the HPF, including the Cornu Ammonis, with field 1 (CA1) showing less prominent labeling than field 3 (CA3). Prominent ELOVL4 labeling also is present in the subiculum (sub) and interneurons in the polymorph layer (arrow). Cells along the inner margin of the dentate gyrus (DG) show moderate ELOVL4 labeling, but most dentate granule cells show little ELOVL4 labeling. (E) Labeling for the neuronal marker, NeuN. (F). Overlay of (D,E) shows close correspondence of ELOVL4 (red) and NeuN (green) labeling. TH, Thalamus. (G–I) Cerebellar cortex. (G) Cross section through a cerebellar folium showing ELOVL4 expression in the cerebellar cortex. Neurons (arrows) in the molecular cell layer (mcl) show strong ELOVL4 labeling, but the Purkinje cells (arrowheads) in the Purkinje cell layer (pcl) show only moderate levels of ELOVL4 labeling. The densely packed cells of the granule cell layer (gcl) show very intense labeling. (H) Labeling for the neuronal marker, NeuN, strongly labels neurons in the gcl, but not Purkinje cells, as appropriate. (I) Overlay of (G,H) shows close correspondence of intense ELOVL4 (red) and NeuN (green) labeling resulting in an orange color in the gcl. wm, white matter of the arbor vitae. Scale bars = 200 μm for (A–C,G–I); 500 μm for (D–F) (figure from Sherry et al., 2017; used with open access under the Creative Commons attribution license CC-BY, version 4.0; http://creativecommons.org/licenses/by/4.0/)."
      }
    ]
  },
  {
    "id": "PMC6763723_multi_2",
    "image": [
      "images/PMC6763723-f6.png",
      "images/PMC6763723-f7.png",
      "images/PMC6763723-f8.png",
      "images/PMC6763723-f9.png",
      "images/PMC6763723-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Novel Cellular Functions of Very Long Chain-Fatty Acids: Insight From ELOVL4 Mutations\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Disease-causing mutations in ELOVL4. STGD3-causing mutations (blue) result in early truncation of ELOVL4 and the loss of the C-terminal ER retention motif or, in the case of the promoter mutations, severely suppress ELOVL4 expression. SCA34-causing mutations (green) result in amino acid substitutions but still produce a full-length protein. ELOVL4 Neuro-ichthyosis-causing mutations (red) cause very early termination of the protein that would truncate substantial portions of transmembrane domains in either the 5-transmembrane or 7-transmembrane models of ELOVL4 topology in addition to deleting the ER retention motif.\n\nFigure 7: Figure 7. Model of membrane fusion between a VLC-SFA-rich synaptic vesicle and presynaptic active zone membrane. In this cartoon, a synaptic vesicle (SV) containing lipids with common fatty acids (phosphatidylcholine or phosphatidylserine molecules with palmitic, 16:0, and stearic acids, 18:0) is used as a model to illustrate the three stages of synaptic vesicular exocytosis, namely, (1) undocked vesicle; (2) docked and hemifused vesicle stage, with deformation tilt of the membranes and stalk formation; and (3) membrane fusion and contents release stage. In (2b), an SV is depicted with lipids containing, in addition, VLC-SFA (typically 28:0 or 30:0 fatty acid chains, see inset). We have shown that the normal presence of these fatty acids in the SV membrane renders it more stable than do the shorter LC fatty acids, thereby fusing and releasing at comparatively lower rates (Hopiavuori et al., 2018) (PS, phosphatidylserine; PC, phosphatidylcholine; SM, sphingomyelin; SL, sphingolipids; see text for more details).\n\nFigure 8: Figure 8. Seizure activity resulting from STGD3 deletion. Left: Spontaneous bursting activity in hippocampal slices from S+Elovl4mut/mut mice with knock-in of the 5 bp STGD3 mutation and skin-specific rescue of wildtype (WT) ELOVL4 function to prevent perinatal lethality, and S+Elovl4wt/wt control mice expressing the WT ELOVL4 gene under baseline conditions. Representative traces of field potentials from postnatal day 19 S+Elovl4wt/wt (upper trace) and S+Elovl4mut/mut mice (lower trace). Each trace represents the first 1 s of a single channel chosen from a 10 min recording taken using a 64 channel multi-electrode array. The S+Elovl4mut/mut slice shows a dramatic increase in spontaneous neuronal activity compared to WT littermates. Right: Stepwise increased stimulations to perforant path synapses in dentate gyrus (DG) revealed a markedly enhanced input/output (I/O) ratio indicating a boost in synaptic strength in the main input pathway from the entorhinal cortex of S+Elovl4mut/mut mice (red) compared to S+Elovl4wt/wt control mice (statistics: two-way RM ANOVA, ∗p < 0.05 from 70 to 100 μA). Reproduced from Hopiavuori et al. (2018) with the permission under the Creative Commons Attribution 4.0 International License (link to the Creative Commons license; http://creativecommons.org/licenses/by/4.0/).\n\nFigure 9: Figure 9. Accelerated synaptic vesicle release in Elovl4 mutant neurons and its rescue by VLC-SFA. Top panel: Faster synaptic release in Elovl4mut/mut hippocampal synapses (red) compared to WT control synapses (black), as detected with FM1-43 dye. Representative traces of average synaptic release activated by four rounds of high K+ depolarization. Bottom panel: Cumulative graph depicts the fraction of total releasable synaptic vesicle pool exocytosed after 15 s depolarization (WT = black line). Vesicle release kinetics was recorded by FM1-43 fluorescence from 900 to 1200 synapses. Note the robust right shift of the cumulative distribution for Elovl4mut/mut synapses (red), which is rescued by supplementation with 28:0 and 30:0 SFAs (green) but not by 24:0 (blue). Inset: Frequency distribution of responses with slowest responding synapses on the left, and the fastest on the right on the curve. Reproduced from Hopiavuori et al. (2018) with permission under the Creative Commons Attribution 4.0 International License (link to the Creative Commons license; http://creativecommons.org/licenses/by/4.0/).\n\nFigure 10: Figure 10. Elovanoid signaling derivatives of VLC-PUFA. Genetic ablation of adiponectin receptor 1 leads to depletion of VLC-PUFAs and its derivatives in retina. (A) Dietary DHA, or that derived from dietary 18:3n3, is supplied by the liver and captured by adiponectin receptor 1 (AdipoR1), followed by elongation in the inner segment of PRC by ELOVL4 to VLC-PUFA and incorporation into phosphatidylcholine molecular species, which also contains DHA. During daily PRC outer segment renewal, these phosphatidylcholine molecular species interact with rhodopsin and, after shedding and phagocytosis, become part of RPE cells. UOS or other disruptors of homeostasis trigger the release of VLC-PUFAs. 32:6n3 and 34:6n3 are depicted generating hydroperoxy forms, and then ELV-N32 or ELV-N34, respectively. (B) The pool size of free 32:6n3 in retinas of AdipoR1 knockout (KO) mice (red) is decreased as compared with that in wild type (WT) (blue). Insert (1) shows ELV-N32 in KO (red) and WT (blue); insert (2) shows mono-hydroxy 32:6n3, the stable derivative of the hydroperoxy precursor of ELV-N32, in WT (blue) and lack of detectable signal in the KO (red). (C) Similarly, the pool size of free 34:6n3 in retinas of AdipoR1 KO mice (red) is decreased as compared with that in WT (blue). Insert (1) shows ELV-N32 in KO (red) and WT (blue); insert (2) shows mono-hydroxy 34:6n3, the stable derivative of the hydroperoxy precursor of ELV-N34, in WT (blue) and lack of detectable signal in the KO (red). (D) RPE cells sustain PRC functional integrity (left); right, the ablation of AdipoR1 switches off DHA availability, and PRC degeneration ensues. Reproduced from Jun et al. (2017) with permission under the Creative Commons Attribution 4.0 International License (link to the Creative Commons license; http://creativecommons.org/licenses/by/4.0/)."
      }
    ]
  },
  {
    "id": "PMC6791227_multi",
    "image": [
      "images/PMC6791227-f1.png",
      "images/PMC6791227-f2.png",
      "images/PMC6791227-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Exome-First Approach in Fetal Akinesia Reveals Chromosome 1p36 Deletion Syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. G-banding analysis of cultured amniocytes at 32 weeks and 6 days of gestation. The fetal karyotype was 46,XY,22pstk+. The arrow indicates 22pstk+.\n\nFigure 2: Figure 2. Postnatal molecular cytogenetic analyses. (a) Whole exome sequencing analysis using the eXome Hidden Markov Model (XHMM). XHMM analysis using WES data detected the copy number loss located within 1p36.33–p36.32, suggesting a 3 Mb deletion (black bar). x axis shows the physical position, and y axis shows the Z score of the principal component analysis that was normalized to read depth. Purple circles connected by red lines represent values of the placenta to WES. Gray dots with gray connected lines indicate the results of normalized read depth. Copy number losses (red dots) without gains (green dots) on chromosome 1p36 were detected in the placenta. (b) Chromosomal microarray (CMA) analysis using Cytoscan 750 k Array. CMA analysis results for the copy number log2 ratio of chromosome 1p region for the placenta (purple), father (pink), and mother (blue). CMA analysis demonstrated a 3 Mb heterozygous deletion within 1p36.33–p36.32 in the placenta. The fetus had arr[hg]1p36.33–p36.32 (849466_3347420)x1. There were no copy number variations in the parents detected by CMA.\n\nFigure 3: Figure 3. Fluorescence in-situ hybridization (FISH) analysis of cultured amniocytes. FISH showed two 1p31.3 region specific signals (blue) and one 1p36.33 region specific signal (green), indicating 1p36 deletion. The arrow indicates 1p36.33 region specific signal. The arrowhead indicates 1p31.3 region specific signal."
      }
    ]
  },
  {
    "id": "PMC6867988_multi",
    "image": [
      "images/PMC6867988-f1.png",
      "images/PMC6867988-f2.png",
      "images/PMC6867988-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The Classification of Autosomal Recessive Cerebellar Ataxias: a Consensus Statement from the Society for Research on the Cerebellum and Ataxias Task Force\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clinical classification of autosomal recessive ataxias. The gene associated with each primary recessive ataxia is classified according to the most frequent clinical syndrome described for this disorder. Note that some disorders have more complex or variable phenotypes and are placed in the overlapping areas between two categories. Genes presented in larger font represent the most prevalent ataxias\n\nFigure 2: Figure 2. Graphical summary of the clinical approach to a patient presenting with ataxia\n\nFigure 3: Figure 3. Pathophysiological classification of autosomal recessive ataxias. A Purkinje cell is depicted along with a granule cell and parallel fibers. Subcellular organelles and structures are represented graphically. Each gene is classified at one or more subcellular localizations according to the different metabolic pathways involved"
      }
    ]
  },
  {
    "id": "PMC6893362_multi",
    "image": [
      "images/PMC6893362-f1.png",
      "images/PMC6893362-f2.png",
      "images/PMC6893362-f3.png",
      "images/PMC6893362-f3-2.png",
      "images/PMC6893362-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Parkin‐mediated ubiquitylation redistributes MITOL/March5 from mitochondria to peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A–CMITOL‐HA formed small dot‐like structures following CCCP treatment. HeLa cells transiently expressing Flag‐Parkin and MITOL‐HA were treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry. MITOL and Tom20 (mitochondrial marker; A) signals co‐localized well without CCCP treatment, whereas the MITOL‐positive small dots were not coincident with Tom20, Sec61β (ER marker; B), or LAMP1 (lysosomal marker; C) after CCCP treatment. Scale bars, 10 μm.DMITOL‐HA co‐localized with catalase (peroxisome marker) following CCCP treatment. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads indicate representative examples of MITOL‐HA co‐localization with catalase.ECorrelation statistics for the localization of MITOL‐HA and Tom20, Sec61β, LAMP1, or catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.FThe line graph shows a line scan of fluorescence through three MITOL‐positive peroxisomes (red bar in D) that clearly indicates co‐localization of MITOL (green line) and catalase (magenta line).GPeroxisomal membrane protein (PMP) 34‐FusionRed also co‐localized with MITOL‐GFP in Parkin‐expressing HeLa cells after 3 h of CCCP treatment. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm.HCorrelation statistics for the localization of MITOL‐GFP and PMP34‐FusionRed. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. MITOL‐HA formed small dot‐like structures following CCCP treatment. HeLa cells transiently expressing Flag‐Parkin and MITOL‐HA were treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry. MITOL and Tom20 (mitochondrial marker; A) signals co‐localized well without CCCP treatment, whereas the MITOL‐positive small dots were not coincident with Tom20, Sec61β (ER marker; B), or LAMP1 (lysosomal marker; C) after CCCP treatment. Scale bars, 10 μm. MITOL‐HA co‐localized with catalase (peroxisome marker) following CCCP treatment. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads indicate representative examples of MITOL‐HA co‐localization with catalase. Correlation statistics for the localization of MITOL‐HA and Tom20, Sec61β, LAMP1, or catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. The line graph shows a line scan of fluorescence through three MITOL‐positive peroxisomes (red bar in D) that clearly indicates co‐localization of MITOL (green line) and catalase (magenta line). Peroxisomal membrane protein (PMP) 34‐FusionRed also co‐localized with MITOL‐GFP in Parkin‐expressing HeLa cells after 3 h of CCCP treatment. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Correlation statistics for the localization of MITOL‐GFP and PMP34‐FusionRed. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.\n\nFigure 2: Figure 2. MITOL‐HA did not move to peroxisomes, but was rather retained on mitochondria even after CCCP treatment in HeLa cells lacking endogenous Parkin. Wild‐type HeLa cells or HeLa cells stably expressing GFP‐Parkin were transfected with MITOL‐HA, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐HA and anti‐Tom20 antibodies. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm.Correlation statistics for the localization of MITOL‐HA and Tom20 in the absence or presence of GFP‐Parkin. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.MITOL was not degraded following mitochondrial depolarization. HeLa cells stably expressing 3Flag‐MITOL were transfected with a GFP‐Parkin plasmid or the pEGFP‐C1 vector, treated with 15 μM CCCP ± 10 μM MG132 for 3 h, and then immunoblotted with anti‐Flag, anti‐ubiquitin, and anti‐tubulin antibodies. Black arrowheads indicate 3Flag‐MITOL in the upper panel and mono‐ubiquitin in the middle panel, respectively.The total cellular amount of MITOL was not dramatically reduced following extended valinomycin treatment. Immunoblotting combined with fractionation analysis showed that mitofusin2 (MFN2) underwent rapid degradation within 3 h of valinomycin treatment, in particular in the 3,000 g pellet (mitochondria‐rich fractions). Cytochrome c oxidase subunit 2 (MTCO2, inner mitochondrial protein) was significantly reduced at 24 h 10 μM valinomycin treatment. In contrast to those two proteins, MITOL degradation was minimal. Note that the chemical apoptosis inhibitor Z‐VAD‐FMK (10 μM) was added to cells along with valinomycin to prevent cell death.Quantification of 3Flag‐MITOL, MFN2, and MTCO2 protein levels in the PNS and 3,000 g pellet fraction following 10 μM valinomycin + Z‐VAD‐FMK treatment at the indicated times. Data represent the mean fold change ± s.e.m. relative to untreated samples in three biological replicates.Pre‐existing MITOL on mitochondria moves to peroxisomes following CCCP treatment. Following doxycycline treatment for 3 h to induce MITOL expression, cells were washed with fresh medium to stop the synthesis of new MITOL. After treatment with or without CCCP for more than 3 h, cells were immunostained using anti‐Flag, anti‐Pex14 (peroxisomal membrane protein), and anti‐Hsp60 antibodies. Higher magnification images of the boxed regions are shown in the bottom panel. Scale bars, 10 μm. MITOL‐HA did not move to peroxisomes, but was rather retained on mitochondria even after CCCP treatment in HeLa cells lacking endogenous Parkin. Wild‐type HeLa cells or HeLa cells stably expressing GFP‐Parkin were transfected with MITOL‐HA, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐HA and anti‐Tom20 antibodies. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Correlation statistics for the localization of MITOL‐HA and Tom20 in the absence or presence of GFP‐Parkin. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. MITOL was not degraded following mitochondrial depolarization. HeLa cells stably expressing 3Flag‐MITOL were transfected with a GFP‐Parkin plasmid or the pEGFP‐C1 vector, treated with 15 μM CCCP ± 10 μM MG132 for 3 h, and then immunoblotted with anti‐Flag, anti‐ubiquitin, and anti‐tubulin antibodies. Black arrowheads indicate 3Flag‐MITOL in the upper panel and mono‐ubiquitin in the middle panel, respectively. The total cellular amount of MITOL was not dramatically reduced following extended valinomycin treatment. Immunoblotting combined with fractionation analysis showed that mitofusin2 (MFN2) underwent rapid degradation within 3 h of valinomycin treatment, in particular in the 3,000 g pellet (mitochondria‐rich fractions). Cytochrome c oxidase subunit 2 (MTCO2, inner mitochondrial protein) was significantly reduced at 24 h 10 μM valinomycin treatment. In contrast to those two proteins, MITOL degradation was minimal. Note that the chemical apoptosis inhibitor Z‐VAD‐FMK (10 μM) was added to cells along with valinomycin to prevent cell death. Quantification of 3Flag‐MITOL, MFN2, and MTCO2 protein levels in the PNS and 3,000 g pellet fraction following 10 μM valinomycin + Z‐VAD‐FMK treatment at the indicated times. Data represent the mean fold change ± s.e.m. relative to untreated samples in three biological replicates. Pre‐existing MITOL on mitochondria moves to peroxisomes following CCCP treatment. Following doxycycline treatment for 3 h to induce MITOL expression, cells were washed with fresh medium to stop the synthesis of new MITOL. After treatment with or without CCCP for more than 3 h, cells were immunostained using anti‐Flag, anti‐Pex14 (peroxisomal membrane protein), and anti‐Hsp60 antibodies. Higher magnification images of the boxed regions are shown in the bottom panel. Scale bars, 10 μm.\n\nFigure 3: Figure 3. The localization of MITOL in ATG5 knockout cells stably expressing Parkin was analyzed by immunocytochemistry using anti‐Flag and anti‐PMP70 antibodies. Following 15 μM CCCP treatment, MITOL clearly overlapped with PMP70 in ATG5 knockout cells, suggesting that inhibition of autophagy (including mitophagy) does not affect the translocation of MITOL to peroxisomes. Scale bars, 10 μm.\n\nFigure 3: Figure 3. Wild‐type or PINK1 knockout (KO) HeLa cells were transfected with GFP‐Parkin wild‐type or the C431S mutant, treated with 15 μM CCCP, and then immunostained with anti‐Flag and anti‐catalase antibodies. Wild‐type Parkin, but not the catalytically inactive Parkin (C431S) mutant, mediated 3Flag‐MITOL translocation to peroxisomes following mitophagy stimulation. In PINK1 KO HeLa cells, the redistribution of MITOL to peroxisomes was not observed even in the presence of wild‐type Parkin when mitochondria were damaged. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads indicate representative examples of MITOL–peroxisome co‐localization observed only in the presence of wild‐type Parkin.The redistribution of MITOL from mitochondria to peroxisomes does not require its own E3 activity. The E3‐inactive MITOL Cys65Ser/Cys68Ser (CS) and H43W mutants were transfected into HeLa cells stably expressing HA‐Parkin, treated with 15 μM CCCP, and then subjected to immunocytochemistry with anti‐Flag and anti‐catalase antibodies. After 3 h of CCCP treatment, both the CS and H43W mutants co‐localized with catalase. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads indicate representative examples of 3Flag‐MITOL co‐localization with catalase.Correlation statistics for the localization of 3Flag‐MITOL and catalase in the presence of GFP‐Parkin wild‐type or an inactive C431S mutant. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. MITOL overlapped with catalase only in the presence of wild‐type Parkin in wild‐type HeLa cells. In PINK1 knockout (KO) HeLa cells, wild‐type Parkin was unable to induce the peroxisomal translocation of MITOL.Correlation statistics for the localization of 3Flag‐MITOL wild‐type or inactive mutants with catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. Wild‐type or PINK1 knockout (KO) HeLa cells were transfected with GFP‐Parkin wild‐type or the C431S mutant, treated with 15 μM CCCP, and then immunostained with anti‐Flag and anti‐catalase antibodies. Wild‐type Parkin, but not the catalytically inactive Parkin (C431S) mutant, mediated 3Flag‐MITOL translocation to peroxisomes following mitophagy stimulation. In PINK1 KO HeLa cells, the redistribution of MITOL to peroxisomes was not observed even in the presence of wild‐type Parkin when mitochondria were damaged. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads indicate representative examples of MITOL–peroxisome co‐localization observed only in the presence of wild‐type Parkin. The redistribution of MITOL from mitochondria to peroxisomes does not require its own E3 activity. The E3‐inactive MITOL Cys65Ser/Cys68Ser (CS) and H43W mutants were transfected into HeLa cells stably expressing HA‐Parkin, treated with 15 μM CCCP, and then subjected to immunocytochemistry with anti‐Flag and anti‐catalase antibodies. After 3 h of CCCP treatment, both the CS and H43W mutants co‐localized with catalase. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads indicate representative examples of 3Flag‐MITOL co‐localization with catalase. Correlation statistics for the localization of 3Flag‐MITOL and catalase in the presence of GFP‐Parkin wild‐type or an inactive C431S mutant. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. MITOL overlapped with catalase only in the presence of wild‐type Parkin in wild‐type HeLa cells. In PINK1 knockout (KO) HeLa cells, wild‐type Parkin was unable to induce the peroxisomal translocation of MITOL. Correlation statistics for the localization of 3Flag‐MITOL wild‐type or inactive mutants with catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.\n\nFigure 4: Figure 4. Schematic topology representation of the mitochondrial membrane proteins analyzed in this study.Peroxisomal translocation of other mitochondrial proteins such as MitoNEET/CISD1, Fis1, Miro1/2, and Tom70 (mitochondrial outer membrane proteins), and Hsp60 (mitochondrial matrix protein) was not observed in CCCP‐treated cells. HeLa cells stably expressing HA‐Parkin were treated with 15 μM CCCP for 3 h, and then immunostained with anti‐MitoNEET/CISD1, anti‐Fis1, anti‐Miro1/2, anti‐Tom70, anti‐Hsp60, and anti‐catalase antibodies. Scale bars, 10 μm.A multi‐spanning outer membrane protein PBR (peripheral benzodiazepine receptor) did not co‐localize with catalase, but did with Tom20 during mitophagy. HeLa cells stably expressing HA‐Parkin were treated with 15 μM CCCP for 3 h, and then immunostained with anti‐Flag, anti‐Tom20, and anti‐catalase antibodies. Scale bars, 10 μm. Schematic topology representation of the mitochondrial membrane proteins analyzed in this study. Peroxisomal translocation of other mitochondrial proteins such as MitoNEET/CISD1, Fis1, Miro1/2, and Tom70 (mitochondrial outer membrane proteins), and Hsp60 (mitochondrial matrix protein) was not observed in CCCP‐treated cells. HeLa cells stably expressing HA‐Parkin were treated with 15 μM CCCP for 3 h, and then immunostained with anti‐MitoNEET/CISD1, anti‐Fis1, anti‐Miro1/2, anti‐Tom70, anti‐Hsp60, and anti‐catalase antibodies. Scale bars, 10 μm. A multi‐spanning outer membrane protein PBR (peripheral benzodiazepine receptor) did not co‐localize with catalase, but did with Tom20 during mitophagy. HeLa cells stably expressing HA‐Parkin were treated with 15 μM CCCP for 3 h, and then immunostained with anti‐Flag, anti‐Tom20, and anti‐catalase antibodies. Scale bars, 10 μm."
      }
    ]
  },
  {
    "id": "PMC6893362_multi_2",
    "image": [
      "images/PMC6893362-f6.png",
      "images/PMC6893362-f5.png",
      "images/PMC6893362-f6-2.png",
      "images/PMC6893362-f7.png",
      "images/PMC6893362-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Parkin‐mediated ubiquitylation redistributes MITOL/March5 from mitochondria to peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A–ELocalization of Drp1, MFN2, Mcl1, MiD49, and MFN1 following CCCP treatment in Parkin‐expressing cells. In (B–D), HeLa cells stably expressing Parkin were transfected with 3Flag‐MFN2, 3HA‐Mcl1, or MiD49‐3HA plasmids. After 3 h of CCCP treatment, the cells were immunostained with anti‐Flag, anti‐HA, anti‐Tom20, and anti‐catalase antibodies. For Drp1 (A) and MFN1 (E), plasmids were not transfected. HeLa cells stably expressing Parkin were treated with 10 μM CCCP for 3 h and then subjected to immunocytochemistry using anti‐Drp1, anti‐MFN1, anti‐Tom20, and anti‐Pex14 antibodies. These previously reported substrates of MITOL do not localize to peroxisomes upon mitochondrial depolarization. Higher magnification images of the boxed regions are shown in the lower panel. Scale bars, 10 μm. Localization of Drp1, MFN2, Mcl1, MiD49, and MFN1 following CCCP treatment in Parkin‐expressing cells. In (B–D), HeLa cells stably expressing Parkin were transfected with 3Flag‐MFN2, 3HA‐Mcl1, or MiD49‐3HA plasmids. After 3 h of CCCP treatment, the cells were immunostained with anti‐Flag, anti‐HA, anti‐Tom20, and anti‐catalase antibodies. For Drp1 (A) and MFN1 (E), plasmids were not transfected. HeLa cells stably expressing Parkin were treated with 10 μM CCCP for 3 h and then subjected to immunocytochemistry using anti‐Drp1, anti‐MFN1, anti‐Tom20, and anti‐Pex14 antibodies. These previously reported substrates of MITOL do not localize to peroxisomes upon mitochondrial depolarization. Higher magnification images of the boxed regions are shown in the lower panel. Scale bars, 10 μm.\n\nFigure 5: Figure 5. siRNA‐based knockdown of endogenous Tom70, Tom20, Tom40, and Sam50. HeLa cells treated with the corresponding siRNAs and immunoblotted with the indicated antibodies. AIF, apoptosis‐inducing factor.HeLa cells were immunostained with anti‐Flag and anti‐catalase antibodies after treatment of each siRNA. Tom20‐ and Tom40‐siRNA treatment inhibited import of Su9‐GFP (the targeting sequence of the FoF1 ATPase subunit 9) into the mitochondria, leading to an accumulation of Su9‐GFP precursor proteins in the cytosol and cell nucleus. 3Flag‐MITOL still localized to mitochondria in Tom20, Tom40, and Sam50 siRNA‐treated cells. In contrast, 3Flag‐MITOL dispersed into the cytosol when Tom70 was knocked down. Scale bars, 10 μm.Statistical analysis of the MITOL subcellular localization following 15 μM CCCP treatment for 3 h in cells treated with control, Tom70, Tom20, Tom40, or Sam50 siRNAs. Su9‐GFP was not imported into the mitochondria, but rather localized to the cytosol and nucleus following Tom20 and Tom40 knockdown. The number of HeLa cells with cytosol‐localized Su9‐GFP or 3Flag‐MITOL in each siRNA experiment was determined. Data represent the mean ± s.e.m. from > 100 cells in three biological replicates. (In case of Tom40, and Sam50 siRNAs, data represent the mean ± s.e.m. from > 60 cells in three biological replicates.) Statistical significance was calculated using a one‐tailed Welch's t‐test.HeLa cells treated with siControl or siTom70 were fractionated into cytosolic and mitochondrial fractions and then immunoblotted with anti‐lactate dehydrogenase (LDH), anti‐Tom20, and anti‐Flag antibodies. LDH was used as a cytosolic marker. Although some MITOL detached from mitochondria during fractionation, sufficient amounts of MITOL were collected in the mitochondria‐enriched fraction in control cells. In contrast, almost all of the MITOL was collected in the cytosolic fraction in siTom70‐treated cells. siRNA‐based knockdown of endogenous Tom70, Tom20, Tom40, and Sam50. HeLa cells treated with the corresponding siRNAs and immunoblotted with the indicated antibodies. AIF, apoptosis‐inducing factor. HeLa cells were immunostained with anti‐Flag and anti‐catalase antibodies after treatment of each siRNA. Tom20‐ and Tom40‐siRNA treatment inhibited import of Su9‐GFP (the targeting sequence of the FoF1 ATPase subunit 9) into the mitochondria, leading to an accumulation of Su9‐GFP precursor proteins in the cytosol and cell nucleus. 3Flag‐MITOL still localized to mitochondria in Tom20, Tom40, and Sam50 siRNA‐treated cells. In contrast, 3Flag‐MITOL dispersed into the cytosol when Tom70 was knocked down. Scale bars, 10 μm. Statistical analysis of the MITOL subcellular localization following 15 μM CCCP treatment for 3 h in cells treated with control, Tom70, Tom20, Tom40, or Sam50 siRNAs. Su9‐GFP was not imported into the mitochondria, but rather localized to the cytosol and nucleus following Tom20 and Tom40 knockdown. The number of HeLa cells with cytosol‐localized Su9‐GFP or 3Flag‐MITOL in each siRNA experiment was determined. Data represent the mean ± s.e.m. from > 100 cells in three biological replicates. (In case of Tom40, and Sam50 siRNAs, data represent the mean ± s.e.m. from > 60 cells in three biological replicates.) Statistical significance was calculated using a one‐tailed Welch's t‐test. HeLa cells treated with siControl or siTom70 were fractionated into cytosolic and mitochondrial fractions and then immunoblotted with anti‐lactate dehydrogenase (LDH), anti‐Tom20, and anti‐Flag antibodies. LDH was used as a cytosolic marker. Although some MITOL detached from mitochondria during fractionation, sufficient amounts of MITOL were collected in the mitochondria‐enriched fraction in control cells. In contrast, almost all of the MITOL was collected in the cytosolic fraction in siTom70‐treated cells.\n\nFigure 6: Figure 6. ACRISPR/Cas9 gene editing was used to generate peroxisome‐null cell lines by knocking out PEX19. In wild‐type HCT116 cells, catalase localized to peroxisomes (dot‐like structures), whereas in PEX19 −/− cells catalase was diffusely localized throughout the cytosol, indicating loss of peroxisomes. Scale bars, 10 μm.B, CWild‐type and PEX19 −/− HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL were treated with 10 μM valinomycin for 3 h, and then subjected to immunocytochemistry with anti‐Flag, anti‐catalase, and anti‐Hsp60 (B), or anti‐Flag and anti‐Tom20 (C) antibodies. In wild‐type HCT116 cells, MITOL translocated to peroxisomes, whereas MITOL remained associated with mitochondria in PEX19 −/− cells. Arrowheads indicate representative examples of 3Flag‐MITOL co‐localization with catalase rather than Hsp60 in wild‐type HCT116 cells.Data information: Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. CRISPR/Cas9 gene editing was used to generate peroxisome‐null cell lines by knocking out PEX19. In wild‐type HCT116 cells, catalase localized to peroxisomes (dot‐like structures), whereas in PEX19 −/− cells catalase was diffusely localized throughout the cytosol, indicating loss of peroxisomes. Scale bars, 10 μm. Wild‐type and PEX19 −/− HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL were treated with 10 μM valinomycin for 3 h, and then subjected to immunocytochemistry with anti‐Flag, anti‐catalase, and anti‐Hsp60 (B), or anti‐Flag and anti‐Tom20 (C) antibodies. In wild‐type HCT116 cells, MITOL translocated to peroxisomes, whereas MITOL remained associated with mitochondria in PEX19 −/− cells. Arrowheads indicate representative examples of 3Flag‐MITOL co‐localization with catalase rather than Hsp60 in wild‐type HCT116 cells.\n\nFigure 7: Figure 7. siRNA‐based knockdown of Pex3, Pex16, and Pex19. HeLa cell lysates treated with the indicated plasmids and siRNAs were immunoblotted with the indicated antibodies.A comparable amount of MITOL was detected in control, PEX3‐, PEX16‐, and PEX19‐knockdown cells. HeLa cell lysates stably expressing HA‐Parkin and 3Flag‐MITOL treated with the corresponding siRNAs were immunoblotted with the indicated antibodies.MITOL translocation from the mitochondria to peroxisomes is highly dependent on Pex3. HeLa cells stably expressing 3Flag‐MITOL and HA‐Parkin were transfected with control, PEX3, PEX16, or PEX19 siRNA, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag and anti‐catalase antibodies. Scale bars, 10 μm.Correlation statistics for the localization of 3Flag‐MITOL and catalase in cells transfected with the indicated siRNAs. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. siRNA‐based knockdown of Pex3, Pex16, and Pex19. HeLa cell lysates treated with the indicated plasmids and siRNAs were immunoblotted with the indicated antibodies. A comparable amount of MITOL was detected in control, PEX3‐, PEX16‐, and PEX19‐knockdown cells. HeLa cell lysates stably expressing HA‐Parkin and 3Flag‐MITOL treated with the corresponding siRNAs were immunoblotted with the indicated antibodies. MITOL translocation from the mitochondria to peroxisomes is highly dependent on Pex3. HeLa cells stably expressing 3Flag‐MITOL and HA‐Parkin were transfected with control, PEX3, PEX16, or PEX19 siRNA, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag and anti‐catalase antibodies. Scale bars, 10 μm. Correlation statistics for the localization of 3Flag‐MITOL and catalase in cells transfected with the indicated siRNAs. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.\n\nFigure 8: Figure 8. MITOL did not merge with Hsp60 in control siRNA‐treated cells, whereas most MITOL co‐localized with Hsp60 in p97/VCP knockdown cells in response to mitophagy stimuli. HeLa cells stably expressing 3Flag‐MITOL and HA‐Parkin were transfected with control or p97/VCP siRNA, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag, anti‐catalase, and anti‐Hsp60 antibodies. Scale bars, 10 μm.HeLa cell lysates treated with control or p97/VCP siRNA were immunoblotted with anti‐p97/VCP and anti‐tubulin antibodies.Overexpression of a p97/VCP ATP hydrolysis‐defective mutant, E305Q/E578Q (p97QQ), blocked MITOL redistribution from mitochondria to peroxisomes, while overexpression of wild‐type p97/VCP had no effect on MITOL redistribution. HeLa cells stably expressing GFP‐Parkin were transfected with MITOL‐HA and Flag‐p97/VCP wild‐type or p97QQ, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐HA and anti‐catalase antibodies. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm.NMS‐873, a specific inhibitor of p97/VCP, prevented MITOL translocation following CCCP treatment. HeLa cells stably expressing HA‐Parkin were transfected with 3Flag‐MITOL, treated with 15 μM CCCP in the presence or absence of 10 μM NMS‐873 for 3 h, and then subjected to immunostaining with anti‐Flag, anti‐catalase, and anti‐HA antibodies. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads in (C) and (D) indicate representative examples of MITOL–peroxisome co‐localization that was only observed in the presence of a functional VCP.Correlation statistics for the localization of 3Flag‐MITOL and catalase in the presence of NMS‐873. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. MITOL did not merge with Hsp60 in control siRNA‐treated cells, whereas most MITOL co‐localized with Hsp60 in p97/VCP knockdown cells in response to mitophagy stimuli. HeLa cells stably expressing 3Flag‐MITOL and HA‐Parkin were transfected with control or p97/VCP siRNA, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag, anti‐catalase, and anti‐Hsp60 antibodies. Scale bars, 10 μm. HeLa cell lysates treated with control or p97/VCP siRNA were immunoblotted with anti‐p97/VCP and anti‐tubulin antibodies. Overexpression of a p97/VCP ATP hydrolysis‐defective mutant, E305Q/E578Q (p97QQ), blocked MITOL redistribution from mitochondria to peroxisomes, while overexpression of wild‐type p97/VCP had no effect on MITOL redistribution. HeLa cells stably expressing GFP‐Parkin were transfected with MITOL‐HA and Flag‐p97/VCP wild‐type or p97QQ, treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐HA and anti‐catalase antibodies. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. NMS‐873, a specific inhibitor of p97/VCP, prevented MITOL translocation following CCCP treatment. HeLa cells stably expressing HA‐Parkin were transfected with 3Flag‐MITOL, treated with 15 μM CCCP in the presence or absence of 10 μM NMS‐873 for 3 h, and then subjected to immunostaining with anti‐Flag, anti‐catalase, and anti‐HA antibodies. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. Arrowheads in (C) and (D) indicate representative examples of MITOL–peroxisome co‐localization that was only observed in the presence of a functional VCP. Correlation statistics for the localization of 3Flag‐MITOL and catalase in the presence of NMS‐873. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test."
      }
    ]
  },
  {
    "id": "PMC6893362_multi_3",
    "image": [
      "images/PMC6893362-f11.png",
      "images/PMC6893362-f9.png",
      "images/PMC6893362-f13.png",
      "images/PMC6893362-f14.png",
      "images/PMC6893362-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Parkin‐mediated ubiquitylation redistributes MITOL/March5 from mitochondria to peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. An increased molecular weight shift of MITOL based on ubiquitylation was observed following addition of the p97/VCP specific inhibitor NMS‐873. After 3 h of 15 μM CCCP treatment with or without 10 μM NMS‐873, cell lysates from HeLa cells stably expressing HA‐Parkin and 3Flag‐MITOL were analyzed by immunoblotting with an anti‐Flag antibody. Red bar indicates ubiquitylation.Mass spectrometric (MS) analysis for identification of MITOL ubiquitylation sites. PEX19 −/− HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL after 3 h of valinomycin treatment were immunoprecipitated with anti‐Flag magnetic beads, and then subjected to LC‐MS/MS analysis. Ubiquitylation of K268, K40, and K54 was revealed by the MS/MS spectra of m/z 724.35694, 562.28265, and 358.84908 ions in tryptic peptides, respectively.The abundances of K268, K40, and K54 peptides with di‐glycine modification in valinomycin‐treated samples were compared with those determined in control (untreated) samples. MITOL K268 underwent significant ubiquitylation in response to mitophagy. Error bars represent the mean ± s.e.m. in three biological replicates. Statistical significance was calculated using a one‐tailed Student's t‐test.Multiple sequence alignment of the MITOL C‐terminal region containing K268 from various organisms. K268 (red font) is well conserved. Gray shading indicates the fourth transmembrane segment. An increased molecular weight shift of MITOL based on ubiquitylation was observed following addition of the p97/VCP specific inhibitor NMS‐873. After 3 h of 15 μM CCCP treatment with or without 10 μM NMS‐873, cell lysates from HeLa cells stably expressing HA‐Parkin and 3Flag‐MITOL were analyzed by immunoblotting with an anti‐Flag antibody. Red bar indicates ubiquitylation. Mass spectrometric (MS) analysis for identification of MITOL ubiquitylation sites. PEX19 −/− HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL after 3 h of valinomycin treatment were immunoprecipitated with anti‐Flag magnetic beads, and then subjected to LC‐MS/MS analysis. Ubiquitylation of K268, K40, and K54 was revealed by the MS/MS spectra of m/z 724.35694, 562.28265, and 358.84908 ions in tryptic peptides, respectively. The abundances of K268, K40, and K54 peptides with di‐glycine modification in valinomycin‐treated samples were compared with those determined in control (untreated) samples. MITOL K268 underwent significant ubiquitylation in response to mitophagy. Error bars represent the mean ± s.e.m. in three biological replicates. Statistical significance was calculated using a one‐tailed Student's t‐test. Multiple sequence alignment of the MITOL C‐terminal region containing K268 from various organisms. K268 (red font) is well conserved. Gray shading indicates the fourth transmembrane segment.\n\nFigure 9: Figure 9. MITOL was ubiquitylated only in the presence of Parkin when the mitochondrial membrane was decreased. After 15 μM CCCP treatment for 3 h, HeLa cells stably expressing HA‐Parkin and 3Flag‐MITOL were immunoprecipitated with anti‐Flag magnetic beads, and then immunoblotted with the indicated antibodies. Red bars indicate ubiquitylation; the black arrowhead indicates 3Flag‐MITOL.The characteristic ubiquitylation ladder was observed for wild‐type MITOL, but was absent in the K268A and K54A/K268A mutants. Black arrowhead indicates 3Flag‐MITOL.The MITOL K268A and K268R mutants were targeted to mitochondria under steady‐state conditions, whereas peroxisomal localization following CCCP treatment was considerably disrupted. HeLa cells stably expressing HA‐Parkin were transfected with 3Flag‐MITOL wild‐type, K268A, or K268R mutants, treated with 15 μM CCCP for 3 h, and then subjected to immunostaining with anti‐Flag and anti‐catalase antibodies. Scale bars, 10 μm.The double K54/K268 mutation did not change the MITOL localization pattern. The subcellular localization of the MITOL K268A or K268R mutants was not drastically changed by inclusion of the K54A or K54R mutations. Scale bars, 10 μm.Correlation statistics for the localization of 3Flag‐MITOL wild‐type, K268A, or K268R mutants with catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.The fold change in ubiquitylation of MITOL K268, K40, and K54 in valinomycin‐treated samples versus untreated samples. After 3 h of valinomycin treatment, PEX19 −/− HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL were immunoprecipitated with anti‐Flag magnetic beads, and then subjected to LC‐MS/MS analysis for label‐free quantification of ubiquitylated peptides. Error bars represent the mean ± s.e.m. in three biological replicates. MITOL was ubiquitylated only in the presence of Parkin when the mitochondrial membrane was decreased. After 15 μM CCCP treatment for 3 h, HeLa cells stably expressing HA‐Parkin and 3Flag‐MITOL were immunoprecipitated with anti‐Flag magnetic beads, and then immunoblotted with the indicated antibodies. Red bars indicate ubiquitylation; the black arrowhead indicates 3Flag‐MITOL. The characteristic ubiquitylation ladder was observed for wild‐type MITOL, but was absent in the K268A and K54A/K268A mutants. Black arrowhead indicates 3Flag‐MITOL. The MITOL K268A and K268R mutants were targeted to mitochondria under steady‐state conditions, whereas peroxisomal localization following CCCP treatment was considerably disrupted. HeLa cells stably expressing HA‐Parkin were transfected with 3Flag‐MITOL wild‐type, K268A, or K268R mutants, treated with 15 μM CCCP for 3 h, and then subjected to immunostaining with anti‐Flag and anti‐catalase antibodies. Scale bars, 10 μm. The double K54/K268 mutation did not change the MITOL localization pattern. The subcellular localization of the MITOL K268A or K268R mutants was not drastically changed by inclusion of the K54A or K54R mutations. Scale bars, 10 μm. Correlation statistics for the localization of 3Flag‐MITOL wild‐type, K268A, or K268R mutants with catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines indicate the medians, the box limits indicate the 25th and 75th percentiles as determined in the R software package, and the whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. The fold change in ubiquitylation of MITOL K268, K40, and K54 in valinomycin‐treated samples versus untreated samples. After 3 h of valinomycin treatment, PEX19 −/− HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL were immunoprecipitated with anti‐Flag magnetic beads, and then subjected to LC‐MS/MS analysis for label‐free quantification of ubiquitylated peptides. Error bars represent the mean ± s.e.m. in three biological replicates.\n\nFigure 13: Figure 13. As compared to K268, ubiquitylation of MITOL K40 and K54 was not critical for translocation from mitochondria to peroxisomes during Parkin‐mediated mitophagy. The K40A and K40R mutations had little inhibitory effect on peroxisomal redistribution of MITOL following CCCP treatment. The K54A and K54R mutations slightly impeded the migration of MITOL to peroxisomes, whereas the effect was weaker than K268A and K268R mutations. HeLa cells stably expressing HA‐Parkin were transfected with 3Flag‐MITOL wild‐type, K40A, K40R, K54A, or K54R mutants, treated with 10 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag, anti‐catalase, and anti‐Hsp60 antibodies. Scale bars, 10 μm.\n\nFigure 14: Figure 14. AMitophagy progression in the presence of wild‐type MITOL or the translocation‐defective K268A MITOL mutant was monitored as a proportion of cells in which mt‐Keima underwent an acidification‐specific fluorescence change. FACS analysis revealed that the mitophagic flux in MITOL −/− HCT116 cells complemented with the MITOL K268A mutant was equivalent to that in MITOL −/− HCT116 cells complemented with MITOL wild‐type following 10 μM antimycin and 4 μM oligomycin for 3 and 6 h.BQuantification of mitophagic flux. Error bars represent the mean ± s.d. in three biological replicates. Statistical significance was calculated using a one‐tailed Welch's t‐test. Mitophagy progression in the presence of wild‐type MITOL or the translocation‐defective K268A MITOL mutant was monitored as a proportion of cells in which mt‐Keima underwent an acidification‐specific fluorescence change. FACS analysis revealed that the mitophagic flux in MITOL −/− HCT116 cells complemented with the MITOL K268A mutant was equivalent to that in MITOL −/− HCT116 cells complemented with MITOL wild‐type following 10 μM antimycin and 4 μM oligomycin for 3 and 6 h. Quantification of mitophagic flux. Error bars represent the mean ± s.d. in three biological replicates. Statistical significance was calculated using a one‐tailed Welch's t‐test.\n\nFigure 10: Figure 10. To generate MITOL‐3Flag knock‐in (KI) HCT116 cell lines, 3xFlag gene cassettes were inserted upstream of the MITOL stop codon using CRISPR/Cas9‐based gene editing. Insertion of the 3Flag‐tag was verified by immunoblotting with an anti‐Flag antibody. Asterisk indicates a cross‐reacting band.The MITOL subcellular localization was observed in MITOL‐3Flag KI HCT116 cells stably expressing HA‐Parkin with anti‐Flag, anti‐catalase, and anti‐Hsp60 antibodies. Endogenous MITOL (detectable with an anti‐Flag antibody) overlapped with Hsp60 under steady‐state conditions, whereas 3 h of valinomycin (10 μM) treatment induced translocation of endogenous MITOL from mitochondria to peroxisomes. Higher magnification images of the boxed regions are shown in the bottom panel. Scale bars, 10 μm.Correlation statistics for the localization of endogenous MITOL‐3Flag with catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.The extraction of endogenous MITOL from depolarized mitochondria is blocked by the p97/VCP inhibitor NMS‐873. Higher magnification images of the boxed regions are shown in the lower panel. Scale bars, 10 μm.Correlation statistics for the localization of endogenous MITOL and PMP70 in the presence of NMS‐873. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.Endogenous MITOL is ubiquitylated following valinomycin treatment. After MITOL‐3Flag KI HCT116 cells stably expressing HA‐Parkin were treated with valinomycin for 3 h, the collected cell lysates were immunoprecipitated with anti‐Flag magnetic beads. The immunoprecipitates were blotted using anti‐Flag and anti‐ubiquitin antibodies. Red bars indicate ubiquitylation; the black arrowhead indicates MITOL‐3Flag. To generate MITOL‐3Flag knock‐in (KI) HCT116 cell lines, 3xFlag gene cassettes were inserted upstream of the MITOL stop codon using CRISPR/Cas9‐based gene editing. Insertion of the 3Flag‐tag was verified by immunoblotting with an anti‐Flag antibody. Asterisk indicates a cross‐reacting band. The MITOL subcellular localization was observed in MITOL‐3Flag KI HCT116 cells stably expressing HA‐Parkin with anti‐Flag, anti‐catalase, and anti‐Hsp60 antibodies. Endogenous MITOL (detectable with an anti‐Flag antibody) overlapped with Hsp60 under steady‐state conditions, whereas 3 h of valinomycin (10 μM) treatment induced translocation of endogenous MITOL from mitochondria to peroxisomes. Higher magnification images of the boxed regions are shown in the bottom panel. Scale bars, 10 μm. Correlation statistics for the localization of endogenous MITOL‐3Flag with catalase. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. The extraction of endogenous MITOL from depolarized mitochondria is blocked by the p97/VCP inhibitor NMS‐873. Higher magnification images of the boxed regions are shown in the lower panel. Scale bars, 10 μm. Correlation statistics for the localization of endogenous MITOL and PMP70 in the presence of NMS‐873. Dots indicate individual Pearson correlation coefficient data points. In the box‐plots, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. Endogenous MITOL is ubiquitylated following valinomycin treatment. After MITOL‐3Flag KI HCT116 cells stably expressing HA‐Parkin were treated with valinomycin for 3 h, the collected cell lysates were immunoprecipitated with anti‐Flag magnetic beads. The immunoprecipitates were blotted using anti‐Flag and anti‐ubiquitin antibodies. Red bars indicate ubiquitylation; the black arrowhead indicates MITOL‐3Flag."
      }
    ]
  },
  {
    "id": "PMC6893362_multi_4",
    "image": [
      "images/PMC6893362-f11-2.png",
      "images/PMC6893362-f12.png",
      "images/PMC6893362-f13-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Parkin‐mediated ubiquitylation redistributes MITOL/March5 from mitochondria to peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. ADistribution of exogenous 3Flag‐MITOL in the mitochondria‐rich or peroxisome‐rich fraction following cellular fractionation. HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL were subjected to fractionation and detected using anti‐Tom20, anti‐PMP70, and anti‐Flag antibodies. Tom20 and PMP70 were used as mitochondrial and peroxisomal markers, respectively. The 3,000 g and 100,000 g pellets represent the mitochondria‐rich and peroxisome‐rich fractions.BThe recovery ratio of 3Flag‐MITOL between the mitochondria‐enriched (3,000 g pellet) and peroxisome‐enriched fraction (100,000 g pellet) following valinomycin treatment for the indicated times. The ratio of peroxisome‐localized 3Flag‐MITOL to mitochondria‐localized 3Flag‐MITOL increased with valinomycin treatment for 3 h. Graphic data represent results of two biological replicates. In scatter plot, dots indicate individual data points. Black dots indicate the ratio of 3Flag‐MITOL collected in the mitochondria‐enriched fractions, and red dots are the ratio of 3Flag‐MITOL collected in the peroxisome‐enriched fractions. Mean values are also shown.C, DDistribution of endogenous MITOL in the mitochondria‐rich or peroxisome‐rich fraction following cellular fractionation. The distribution of endogenous MITOL was examined as in (A) and (B) using MITOL‐3Flag knock‐in HCT116 cells. Treatment of cells with valinomycin for 3 h reduced the amount of endogenous MITOL in the mitochondria‐enriched fraction, but concomitantly increased endogenous MITOL in the peroxisome‐enriched fraction. Graphic data represent results of two biological replicates. In scatter plot, dots indicate individual data points. Black dots indicate the ratio of MITOL‐3Flag collected in mitochondria‐enriched fractions, and red dots are the ratio of MITOL‐3Flag collected in the peroxisome‐enriched fractions. Mean values are also shown. Distribution of exogenous 3Flag‐MITOL in the mitochondria‐rich or peroxisome‐rich fraction following cellular fractionation. HCT116 cells stably expressing HA‐Parkin and 3Flag‐MITOL were subjected to fractionation and detected using anti‐Tom20, anti‐PMP70, and anti‐Flag antibodies. Tom20 and PMP70 were used as mitochondrial and peroxisomal markers, respectively. The 3,000 g and 100,000 g pellets represent the mitochondria‐rich and peroxisome‐rich fractions. The recovery ratio of 3Flag‐MITOL between the mitochondria‐enriched (3,000 g pellet) and peroxisome‐enriched fraction (100,000 g pellet) following valinomycin treatment for the indicated times. The ratio of peroxisome‐localized 3Flag‐MITOL to mitochondria‐localized 3Flag‐MITOL increased with valinomycin treatment for 3 h. Graphic data represent results of two biological replicates. In scatter plot, dots indicate individual data points. Black dots indicate the ratio of 3Flag‐MITOL collected in the mitochondria‐enriched fractions, and red dots are the ratio of 3Flag‐MITOL collected in the peroxisome‐enriched fractions. Mean values are also shown. Distribution of endogenous MITOL in the mitochondria‐rich or peroxisome‐rich fraction following cellular fractionation. The distribution of endogenous MITOL was examined as in (A) and (B) using MITOL‐3Flag knock‐in HCT116 cells. Treatment of cells with valinomycin for 3 h reduced the amount of endogenous MITOL in the mitochondria‐enriched fraction, but concomitantly increased endogenous MITOL in the peroxisome‐enriched fraction. Graphic data represent results of two biological replicates. In scatter plot, dots indicate individual data points. Black dots indicate the ratio of MITOL‐3Flag collected in mitochondria‐enriched fractions, and red dots are the ratio of MITOL‐3Flag collected in the peroxisome‐enriched fractions. Mean values are also shown.\n\nFigure 12: Figure 12. HeLa cells expressing HA‐Parkin and wild‐type 3Flag‐MITOL or 3Flag‐MITOL lacking C‐terminal 8 amino acids (∆C8) were treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag and anti‐PMP70 antibodies. Expanded peroxisomes were observed in MITOL∆C8‐expressing cells. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm.3Flag‐MITOL∆C8 with the E3‐inactive Cys65Ser/Cys68Ser (CS) and H43W mutations were transfected into HeLa cells stably expressing HA‐Parkin, treated with 15 μM CCCP, and then subjected to immunocytochemistry with anti‐Flag and anti‐PMP70 antibodies. After 3 h of CCCP treatment, both the CS and H43W mutants localized on peroxisomes but expansion was not observed. Scale bars, 10 μm.HeLa cells expressing HA‐Parkin and MITOL wild‐type or ∆C8 were treated with 15 μM CCCP for 3 h, and the number of peroxisomes was counted as PMP70‐positive dots per 100 μm2. In the box‐plots, dots indicate individual data points, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. The abundance of peroxisomes in cells expressing MITOL∆C8 was significantly decreased as compared with cells expressing wild‐type MITOL.MITOL∆C8 causes a drastic expansion of peroxisomes following CCCP treatment. HeLa cells expressing HA‐Parkin and wild‐type or ∆C8 MITOL were treated with 15 μM CCCP for 3 h, and the approximate size of peroxisomes was determined as the number of pixels occupied by one peroxisome. The PMP70‐positive pixels per 100 μm2 were divided by the number of peroxisomes in the same area. In the box‐plots, dots indicate individual data points, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. HeLa cells expressing HA‐Parkin and wild‐type 3Flag‐MITOL or 3Flag‐MITOL lacking C‐terminal 8 amino acids (∆C8) were treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag and anti‐PMP70 antibodies. Expanded peroxisomes were observed in MITOL∆C8‐expressing cells. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. 3Flag‐MITOL∆C8 with the E3‐inactive Cys65Ser/Cys68Ser (CS) and H43W mutations were transfected into HeLa cells stably expressing HA‐Parkin, treated with 15 μM CCCP, and then subjected to immunocytochemistry with anti‐Flag and anti‐PMP70 antibodies. After 3 h of CCCP treatment, both the CS and H43W mutants localized on peroxisomes but expansion was not observed. Scale bars, 10 μm. HeLa cells expressing HA‐Parkin and MITOL wild‐type or ∆C8 were treated with 15 μM CCCP for 3 h, and the number of peroxisomes was counted as PMP70‐positive dots per 100 μm2. In the box‐plots, dots indicate individual data points, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test. The abundance of peroxisomes in cells expressing MITOL∆C8 was significantly decreased as compared with cells expressing wild‐type MITOL. MITOL∆C8 causes a drastic expansion of peroxisomes following CCCP treatment. HeLa cells expressing HA‐Parkin and wild‐type or ∆C8 MITOL were treated with 15 μM CCCP for 3 h, and the approximate size of peroxisomes was determined as the number of pixels occupied by one peroxisome. The PMP70‐positive pixels per 100 μm2 were divided by the number of peroxisomes in the same area. In the box‐plots, dots indicate individual data points, the center lines show the medians, box limits indicate the 25th and 75th percentiles as determined by the R software package, and whiskers extend 1.5 times the interquartile range from the 25th and 75th percentiles. Means and the number of samples are shown on the box and the X‐axis, respectively. Statistical significance was calculated using a one‐tailed Welch's t‐test.\n\nFigure 13: Figure 13. A, BHeLa cells expressing HA‐Parkin and MITOL∆C8 (A) or MITOL∆C8 lacking E3 activity (B) were treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag and anti‐ubiquitin antibodies. Expanded peroxisomes were ubiquitylated upon E3 activity of MITOL. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm.CThe schematic model of PINK1/Parkin‐mediated MITOL redistribution. MITOL is targeted to mitochondria with sustained membrane potential via Tom70. In response to mitophagy stimuli, Parkin‐catalyzed ubiquitylation of MITOL causes its extraction from damaged mitochondria in a p97/VCP‐dependent manner, and then, MITOL translocates to peroxisomes via Pex3/Pex16 pathway. As ubiquitylation of MITOL is rarely observed in the absence of NMS‐873, MITOL inserted into the peroxisome membrane is shown here in the non‐ubiquitylated form. HeLa cells expressing HA‐Parkin and MITOL∆C8 (A) or MITOL∆C8 lacking E3 activity (B) were treated with 15 μM CCCP for 3 h, and then subjected to immunocytochemistry with anti‐Flag and anti‐ubiquitin antibodies. Expanded peroxisomes were ubiquitylated upon E3 activity of MITOL. Higher magnification images of the boxed regions are shown in the small panel. Scale bars, 10 μm. The schematic model of PINK1/Parkin‐mediated MITOL redistribution. MITOL is targeted to mitochondria with sustained membrane potential via Tom70. In response to mitophagy stimuli, Parkin‐catalyzed ubiquitylation of MITOL causes its extraction from damaged mitochondria in a p97/VCP‐dependent manner, and then, MITOL translocates to peroxisomes via Pex3/Pex16 pathway. As ubiquitylation of MITOL is rarely observed in the absence of NMS‐873, MITOL inserted into the peroxisome membrane is shown here in the non‐ubiquitylated form."
      }
    ]
  },
  {
    "id": "PMC6901512_multi",
    "image": [
      "images/PMC6901512-f1.png",
      "images/PMC6901512-f2.png",
      "images/PMC6901512-f3.png",
      "images/PMC6901512-f4.png",
      "images/PMC6901512-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mitochondria ubiquitin ligase, MARCH5 resolves hepatitis B virus X protein aggregates in the liver pathogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Analysis of MARCH5 mRNA expression in histologic grades of human hepatocellular carcinomas (HCCs) of TCGA dataset (***p < 0.001; Wilcoxon’s signed-rank test). b Western blot analysis of MARCH5 and HBx protein expression in human HCCs (T) and matched surrounding non-tumor liver tissues (N). Densitometric values of MARCH5 normalized with GAPDH (lower panel). c The survival rates of HCC patients by MARCH5 mRNA expression levels. Analyzed by a Kaplan–Meier curve (**p = 0.0163, Log-rank (Mantel–Cox) test). d The cumulative overall survival days of HCC patients (G2 and G3) with HBV infection or HCV infection. MARCH5 mRNA expression in HCC patients with HBV infection was correlated with cumulative survival (***p < 0.001; Mann–Whitney test).\n\nFigure 2: Figure 2. a After transfection of HBx-Flag for indicated times, subcellular localization of HBx was determined by immunostaining with anti-Flag antibody, followed by FITC-conjugating secondary antibody. Mitochondria was co-stained using MitoTracker -Red. The number of HBx-positive mitochondria aggregated cells were quantified and shown in the right panel (*p < 0.05, **p < 0.01, Two-tailed paired Student’s t-test). b Huh7 cells were transfected with Myc-MARCH5WT and HBx-Mito-Flag. After 36 h post-transfection, cells were stained by immunostaining with anti-Myc antibody and anti-Flag antibody. c After HEK293T cells were transfected with Myc-MARCH5WT, Myc-MARCH5H43W, and HBx-Flag, cell lysates were immunoprecipitated with anti-Flag antibody and immunoblotted with anti-Flag or anti-Myc antibody. d HEK293T cells were transfected with HBx-Flag and lysed cell extracts were immunoprecipitated with anti-MARCH5 antibody. e A schematic diagram showing MARCH5 deletion constructs (upper panel). In the lower panel, Huh7 cells were co-transfected with HBx-Flag and Myc-MARCH5WT or MARCH5 deletion constructs. The cell lysates were immunoprecipitated with anti-Myc antibody and immunoblotted with anti-Flag antibody.\n\nFigure 3: Figure 3. a, c Huh7 cells were transfected with either HBx-Flag or HBx-Mito-Flag along with Myc-MARCH5WT and expression of HBx protein was analyzed by immunoblotting. b The HBx-Flag plasmid was transfected into HEK293T cells or MARCH5 knockout HEK293T cells (MARCH5−/−). Expression levels of HBx protein in these cells were detected by immunoblotting. d After transfection, cells were homogenized and mitochondria fraction and cytosolic fraction were separately obtained. Expression of HBx protein was analyzed by immunoblotting. e Cells were transfected with HA-Ub, HBx-Flag, Myc-MARCH5WT, and MARCH5H43W. The cell lysates were immunoprecipitation with anti-Flag antibody and analyzed by immunoblotted with anti-Ub antibody. f Cells were co-transfected with indicated constructs. The HBx-Flag ubiquitination was monitored by immunoprecipitation with anti-Flag antibody and analyzed by immunoblotting with anti-Ub antibody. g Cells were transfected with indicated constructs and immunoprecipitation was carried out. h Ubiquitination patterns of HBx mutants were analyzed using anti-Ub antibody.\n\nFigure 4: Figure 4. a, b Huh7 cells were transfected with HBx-Flag or HBx-Mito-Flag along with increasing concentrations of Myc-MARCH5 for 36 h. Before harvest, cells were treated with 20 μM of MG132 or 2.5 nM of bafilomycin A1 (Baf A1) for 12 h. To detect HBx aggregates, the cells were directly lysed with sample buffer without β-mercaptoethanol and analyzed on the SDD-AGE (semi-denaturing detergent agarose gel electrophoresis). Alternately, the cell lysates were incubated with 1 mM of DSS as a cross-linker for 30 min and quenched with 10 mM Tris–HCl. Then, the sample buffer without SDS and β-mercaptoethanol was added and analyzed on the SDS–PAGE.\n\nFigure 5: Figure 5. a, b Huh7 cells were transfected with indicated constructs for 36 h. Intracellular ROS levels were determined by incubation of cells with DCF-DA for 20 min at 37 °C, followed by flow cytometry. c Huh7 cells were co-transfected with indicated constructs along with mt-Keima. Fluorescence images were analyzed by confocal microscopy. Scale bar, 100 μm. Graph indicates the Red/green mt-Keima signal. d, e Huh7 cells were co-transfected with COX-2 luciferase reporter or NF-κB luciferase reporter along with indicated constructs. Luciferase activity was determined. Graphs represent fold-induction of the luciferase activity. Error bars represent the mean ± s.e.m. (n = 3)."
      }
    ]
  },
  {
    "id": "PMC6911980_multi",
    "image": [
      "images/PMC6911980-f1.png",
      "images/PMC6911980-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Rhizomelic chondrodysplasia punctata: Role of EEG as a biomarker of impending epilepsy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Changes in the brain MRI in a patient with the severe phenotype of RCDP. Figure A. Lower limb x-ray image shows punctate epiphyseal calcification, done on day 1 of life B. Coronal T2 MRI shows normal brain MRI with the normal cerebellum at the age of 3 months. C. Coronal T2 MRI shows severe cerebellar atrophy at the age of 3 years 8 months. D. FLAIR T2 axial image shows supratentorial white matter signal abnormalities, most prominent in the bilateral parieto-occipital region.\n\nFigure 2: Figure 2. Changes in the EEG pattern in a patient with the severe phenotype of RCDP. Fig. A shows EEG at 8 months: Normal background frequency and amplitude (left and right posterior dominant rhythms are shown with arrows;sensitivity 10 uV/mm). Fig. B shows EEG at 3 years: Independent and dependent (arrows) central-parietal epileptiform discharges, but the persistence of normal EEG background. Fig. C. EEG at 4 years: Very high amplitude, disorganized high amplitude background, loss of posterior dominant rhythm, generalized high amplitude slow spike and polyspike wave discharges(Sensitivity of 30 uV/mm). Fig. D shows EEG changes during a tonic seizure with burst of polyspike wave discharge followed by electrodecrement. Bipolar, anterior-posterior montages(left central, right central, left temporal, right temporal, and then midline chains, 4 channels each)."
      }
    ]
  },
  {
    "id": "PMC6921552_multi",
    "image": [
      "images/PMC6921552-f1.png",
      "images/PMC6921552-f2.png",
      "images/PMC6921552-f3.png",
      "images/PMC6921552-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Broadening the phenotype of the TWNK gene associated Perrault syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Neuropathological investigations. a Predominantly neurogenic alteration can be observed in the muscle tissue (large caliber variation, angular atrophic muscle fibers) H&E staining X250. b In the semithin section, many muscle fibers contained centrally numerous small vacuoles. Semi-thin section X350. c Electron microscopic picture of the muscle specimen. Lipid vacuoles are attached to the mitochondria. x d Enlarged mitochondria with abnormal cristae in the muscle tissue. × 24,000\n\nFigure 2: Figure 2. Electron microscopic pictures of the sural nerve biopsy specimen. a Complex group of degenerated and regenerated myelinated fibers. In one myelinated fiber, adaxonal vacuole is present, in another one, a myelin-like figure can be observed. × 8400. b Vesicular widening of the myelin in the region of a Schmidt-Lanterman cleft. In the Schwann cell and in the axon, slightly enlarged mitochondria (white arrows) are present. The myelin sheaths are slightly decompacted (dotted arrows). × 20.000 C. In a Schwann cell, a pi granula is present. × 16.000\n\nFigure 3: Figure 3. Brain MRI of the patient. a (FLAIR horizontal), b (T2 horizontal) and c (sagittal horizontal) are MRI examinations performed in 2008, while d (FLAIR horizontal), e (T2 horizontal) and f (sagittal) was performed in 2016. The hyperintense signs (white arrows) in the cerebellum are clearly visible on the images and show progression between the two examinations. Cerebellar, medulla oblongata, and cervical spinal cord atrophy can also be observed\n\nFigure 4: Figure 4. a Sanger traces of the identified mutations b pedigree information with segregation information. The mother is heterozygous for c.1196A > G, the father is heterozygous for c.1358A > G, and one female sibling is heterozygous for c.1196A > G, the other healthy sibling does not carry any of the examined mutations"
      }
    ]
  },
  {
    "id": "PMC6926218_multi",
    "image": [
      "images/PMC6926218-f1.png",
      "images/PMC6926218-f2.png",
      "images/PMC6926218-f3.png",
      "images/PMC6926218-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Neonate with classic Zellweger syndrome\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Sagittal Ultrasound of the right (A) and left kidney (B) show normal-sized kidneys with parenchymal hyperechogenicity and loss of corticomedullary differentiation. Small cysts are present in the medulla bilaterally (arrow).\n\nFigure 2: Figure 2. Brain MRI (A) Axial T2 WI image shows bilateral perisylvian polymicrogyria (white arrow) as well as caudothalamic germinolytic cysts. (B) Axial T2WI image show bilateral frontal pachygyria, delay myelination noted.\n\nFigure 3: Figure 3. Brian MRI Sagittal T1WI image shows hypoplastic corpus callosum.\n\nFigure 4: Figure 4. (A,B): AP view of the knees show scimitar-like patella bilatrally."
      }
    ]
  },
  {
    "id": "PMC6956636_multi",
    "image": [
      "images/PMC6956636-f1.png",
      "images/PMC6956636-f2.png",
      "images/PMC6956636-f3.png",
      "images/PMC6956636-f4.png",
      "images/PMC6956636-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Infantile Alexander Disease with Late Onset Infantile Spasms and Hypsarrhythmia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. FLAIR transverse brain MRI (13 months) showed internal hydrocephalus and spots of impaired mye-lination.\n\nFigure 2: Figure 2. FLAIR transverse brain MRI (13 months) revealed ventriculomegaly with disturbed myelination: diffuse hyperintensity of white matter in the frontal lobe, within the left lentiform nucleus and in the left-sided posterior part of the internal capsule.\n\nFigure 3: Figure 3. SET2 weighted transverse brain MRI (13 months) with areas of diffuse hyperintensity of white matter in the frontal lobe, within the left lentiform nucleus and in the left-sided part of the internal capsule.\n\nFigure 4: Figure 4. DICOMDIR (18 months) showed internal hydrocephalus and improper myelination compared with the previous brain MRI performed at the age of 13 months.\n\nFigure 5: Figure 5. FLAIR transverse brain MRI (18 months) revealed internal hydrocephalus, the size of the lateral ventricles was comparable with the previous brain MRI result at the age of 13 months."
      }
    ]
  },
  {
    "id": "PMC6985062_multi",
    "image": [
      "images/PMC6985062-f1.png",
      "images/PMC6985062-f2.png",
      "images/PMC6985062-f3.png",
      "images/PMC6985062-f4.png",
      "images/PMC6985062-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Biomarker Identification, Safety, and Efficacy of High-Dose Antioxidants for Adrenomyeloneuropathy: a Phase II Pilot Study\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Trial profile. Patients initially received a lower oral dose A daily for 2 months (M2). After that, a 2-month washout period was introduced during which the biomarkers of protein oxidative damage were tested in plasma (M4). In patients showing normalization of biomarkers (patient 8), the treatment was restarted for 12 months at the same dose (M10, M16). In patients showing no normalization of oxidative damage biomarkers, the dosage was increased to dose B for 3 months (M7). After this treatment period, the biomarkers were tested again during a new washout period of 2 months (M9). If normalization of the levels was attained with dose B, the treatment was restarted for 12 more months with the higher dose (M15, M21). In the eventuality that protein oxidative damage biomarkers were not reduced, the patient would have been considered a nonresponder, and the treatment would have been discontinued at that point. This eventually did not apply to any of the patients. Blue boxes, patients taking dose A; pink boxes, patients taking dose B\n\nFigure 2: Figure 2. Oxidative lesion markers and treatment effect in subjects. (a) Significant pretreatment increase in the oxidation markers CML, CEL, MDAL in the plasma, and 8-oxo-dG in the urine is observed in subjects compared with controls. Whiskers indicate 1.5 times the interquartile range; the bottom and top of the boxes indicate the first and third quartiles, respectively; the center lines of the boxes indicate the second quartile. (b) A significant decrease was observed in the plasma concentrations of the oxidation markers CML, CEL, and MDAL after 2 months with dose A (M2) and, more strikingly, after 3 months with dose B (M7) compared with pretreatment levels at the initial time point (M0). A significant decrease in AASA in plasma and urine 8-oxo-dG levels was only observed after 3 months with dose B. P values are colored red if they are less than 0.05. AASA, CML, CEL, and MDAL are expressed as μmol/mol lysine; 8-oxo-dG is expressed as ng/mg creatine\n\nFigure 3: Figure 3. Effects of the antioxidant treatment on inflammatory markers. (a) A significant decrease was observed in the pro-inflammatory markers 12S-HETE, 15S-HETE, TXB2, TNF, IL-8, IFNA2, IL-36A, and CCR3 after 3 months with dose B compared with pretreatment levels. (b) A significant increase was detected in the levels of the anti-inflammatory markers adiponectin and IL-10 after 3 months with dose B compared with pretreatment levels at the initial time point (time 0). The same treatment led to a significant decrease in IL-4 levels. (c) Significantly higher levels of neopterin in cerebrospinal fluid and MCP1 in plasma were observed in AMN patients before treatment, and neopterin levels exhibited a significant decrease after 3 months of treatment. Whiskers indicate 1.5 times the interquartile range; the bottom and top of the boxes indicate first and third quartiles, respectively; the center lines of the boxes indicate the second quartile. P values are colored red if they are less than 0.05. The 12S-HETE, 15S-HETE, and TXB2 in plasma and neopterin in cerebrospinal fluid are expressed as μmol/l; TNF, IL-8, and MCP1 in plasma are expressed as pg/ml; adiponectin in plasma is expressed as μg/ml; IFNA2, IL-36A, CCR3, IL-4, and IL-10 are expressed as the relative gene expression in PBMCs\n\nFigure 4: Figure 4. Effects of treatment on the 6-minute walk test (6MWT) and on motor evoked potentials. (a) The correlation between the 6MWT and EDSS before treatment at the initial time point. (b) The correlation between the 6MWT and EDSS at the end of treatment. In (a) and (b), the colors represent the 3 different phenotypes: mild in gray, moderate in yellow, and severe in blue. Subjects with an improvement are represented by darker colors. The correlation was measured using Pearson’s product moment correlation coefficient test. (c) Significant improvements were observed in the distance walked in the last visit compared with the pretreatment distances. Eight subjects improved in the distance walked, 1 showed no change and 1 worsened. (d) The percentage of improvement of subjects in the 6MWT is indicated. Only subjects with amelioration of their scores are listed. n = number of cases of each phenotype. (e) A significant decrease was observed in central motor conduction time (CMCT) in both legs in the last visit in comparison with baseline. R = right; L = left. P values are colored in red if they are less than 0.05. CMCT is the difference between the shortest peripheral motor and the shortest corticomotor latencies\n\nFigure 5: Figure 5. Stratification of patients by integrating biomarkers with clinical variables. PCA was used to distribute patients with AMN according to their clinical phenotype severity (in (a)) and according to their pretreatment biomarker values (b, c). Loading plots: the axes for components 1 and 2 indicate the most varying direction of the data, and the arrows show the direction of the variables. Mild phenotypes are shown in gray, moderate phenotypes in yellow, and severe phenotypes in blue. Darker colors depict patients who improved clinically in the 6MWT after treatment. In (a), the clinical variables EDSS and 6MWT are shown in relation to age. In (b), the plasma levels of inflammatory molecules in relation to age are shown. The most severe phenotypes show higher levels of MCP1, TNF, and IL-8, except for patient 7. In (c), the expression of molecules and mediators of inflammation in PBMCs are shown. Patients 3 and 11, with milder phenotypes, showed higher levels of protective IL-10"
      }
    ]
  },
  {
    "id": "PMC6995399_multi",
    "image": [
      "images/PMC6995399-f1.png",
      "images/PMC6995399-f2.png",
      "images/PMC6995399-f3.png",
      "images/PMC6995399-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"High level of RNF187 contributes to the progression and drug resistance of osteosarcoma\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The RNF187 expression in os. A and B. qRT- PCR analysis of the RNF187 expression in OS tissues and matched nontumorous tissues, Data are showed as the mean ± SD, n=3. C and D. Representative H&E and RNF187 expression in OS tissues and matched nontumorous tissues (Bar=200μm).\n\nFigure 2: Figure 2. High level of RNF187 promote OS progression. A. Western blot and qRT- PCR analysis of the RNF187 expression in OS and hFOB1.19 cell lines; B. RNF187 expression was effectively interfered in MG-63 cells by specific RNF187-shRNA vectors; C. RNF187 expression was up-regulated in HOS cells by transfecting the RNF187 cDNA vectors; D. wound‐healing assays were used to evaluate the migration of OS cells with different RNF187 expression; E. Cell proliferation in OS cells with enhanced or reduced RNF187 expression was assessed by a CCK-8 assay. F. Transwell assays were used to measure the effects of RNF187 up- and down‐regulation on the invasion of OS cells; G. Changes in Colony formation activity of OS cells with RNF187 up- and down‐regulation.\n\nFigure 3: Figure 3. High level of RNF187 induce drug resistance and metastasis in vivo. A and B. The cell viability was investigated at the cells treated by paclitaxel and docetaxel. **P<0.01. C. The cell viability was investigated at the cells treated by paclitaxel and docetaxel in 5th day. **P<0.01. D. Western blot was used to detect the ERK1/2 and AKT signaling- and apoptosis related molecules. E. The volume of the tumors derived from OS cell lines with different RNF187 expression was calculated in vivo for 6 weeks; Serial sections from mouse lung showed the metastasis ability of cancer cells expressing different RNF187 (Scale bar: 50 μm).\n\nFigure 4: Figure 4. The RNF187 overexpression in OS prognosis. A. The representative pictures of RNF187 expression in OS tissues; B. Survival analysis of 51 OS patients with respect to RNF187 expression."
      }
    ]
  },
  {
    "id": "PMC6997366_multi",
    "image": [
      "images/PMC6997366-f1.png",
      "images/PMC6997366-f2.png",
      "images/PMC6997366-f3.png",
      "images/PMC6997366-f4.png",
      "images/PMC6997366-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A20 targets PFKL and glycolysis to inhibit the progression of hepatocellular carcinoma\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a A20 suppresses proliferation in Huh7 and LM3 cells. Cell proliferation was determined by cell counting. The two-tailed Student’s t-test was used. b A20 decreases HCC tumor growth in vivo. Huh7 cells stably expressing A20 and empty vector counterpart cells were subcutaneously injected into the bilateral flanks of nude mice. At 4 weeks after injection, tumors from 10 mice were extracted and photographed (left panel). Tumor diameters were measured at the indicated time points, and tumor volumes were calculated (right panel). Significant differences were evaluated by t-test. c A20 suppresses the migration of Huh7 and LM3 cells. Huh7 and LM3 cells were transfected with pcDNA3-A20 or pMKO-shA20 plasmids, and cell migration was analyzed by Transwell experiments. d Quantitative analysis of cell migration was performed by ImageJ. The numbers of migrated cells (mean ± S.D.) from three independent experiments. e, f A20 suppresses cell glucose uptake and lactate production. pcDNA3-A20 or pMKO-shA20 plasmids was transfected in Huh7 and LM3 cells, respectively, and cellular glucose uptake and lactate production were detected via glucose uptake assay and lactate colorimetric assay, respectively. Error bars represent ± S.D. for triplicate experiments. g A20 inhibits cell glycolysis. The real-time assessment of the extracellular acidification rate (ECAR) in cultured cells was examined by Seahorse XFe96 analyzer. h Relative glycolytic capacity was normalized to the cell number (means ± S.D., n = 3). (The two-tailed Student’s t-test was used. The symbol * shows statistically significant differences with *p < 0.05, **p < 0.01, and ***p < 0.001).\n\nFigure 2: Figure 2. a LC-MS/MS identified an interaction between PFKL and A20. b, c PFKL binds with A20 directly. The interaction between endogenous A20 and PFKL was determined by co-IP and western blotting (b). Exogenous VC155-A20 and VN173-PFKL plasmids were transfected into Huh7 cells. Representative confocal pictures of BiFC signals (green) in Huh7 cells are shown (c). d GST-PFKL can readily pull-down A20. BL21 E. Coli were transformed with pGEX-6P-1-GST-PFKL plasmid and induced by isopropyl-b-D-thiogalactoside. Protein was purified by GST antibody-conjugated columns and incubated with Huh7 cell lysates and then repurified through immunoprecipitation and subjected to western blotting. e, f LPS enhances the interaction between A20 and PFKL. Huh7 cells were cultured with or without LPS for 4 h as indicated and then processed for double immunofluorescence with antibodies against PFKL (green) and A20 (red). Merged images of both channels are shown on the right. Bar: 10 mm (e). LPS promotes endogenous PFKL binding with A20 in Huh7 cells. Huh7 cells were pretreated with MG132 for 6 h, then with or without LPS for 4 h as indicated, followed by proximity ligation (Duolink®) assay. Confocal images of the PLA reaction between A20 and PFKL in Huh7 cells. The PLA signal is in red, and DAPI is in blue. Representative data from 3 independent biological experiments (f).\n\nFigure 3: Figure 3. a A20 decreases the PFKL protein level. Huh7 and LM3 cells were transfected with pcDNA3-A20 or pMKO-shA20 plasmids. The protein levels of PFKL were determined by standard western blotting (left panel). The relative PFKL protein compared with the β-actin level was quantified (right panel). b A20 reduces PFKL protein level in a dose-dependent manner. Huh7 cells were transfected with the PFKL vector together with varying amounts of A20 or empty control (Con) vectors, and the protein levels of PFKL were determined by standard western blotting (left panel). The relative PFKL protein compared with the β-actin level and relative A20 protein compared with the β-actin level was quantified (right panel). c LPS treatment increases the endogenous A20 protein level and decreases the PFKL protein level. Huh7 cells were treated with 9 and 18 μg/mL LPS for 4 h. Untreated cells were used as controls. The expression level of A20 protein was determined by western blotting. d–f A20 decreases PFKL expression at the post-transcriptional level. PFKL mRNA was determined by qPCR and normalized against β-actin. Error bars represent ± S.D. of triplicate experiments. The two-tailed Student’s t-test was used. NS denotes no significance (d). Scatterplots revealed that A20 and PFKL were not correlated at the mRNA level. Clinical data of non-cancerous liver samples and hepatocellular carcinoma samples were based on GSE364 (e). Data from the GEPIA website showed that A20 has no correlation with PFKL at the mRNA level (r = 0.16) (f). (The two-tailed Student’s t-test was used. The symbol * shows statistically significant differences with *p < 0.05, **p < 0.01, and ***p < 0.001).\n\nFigure 4: Figure 4. a MG132 treatment led to the accumulation of PFKL protein levels. Huh7 and LM3 cells were treated with MG132. Cell lysates were directly subjected to western blotting. b MG132 rescues PFKL protein reduction induced by A20 overexpression. Huh7 and LM3 cells were transfected with pcDNA3-A20 plasmid, followed by MG132 treatment. The protein expression level of PFKL and A20 was determined by western blotting. c A20 overexpression shortens the half-life of PFKL. Huh7 cells were transfected with pcDNA3-A20 or vector plasmids. A CHX chase experiment was performed and PFKL protein was determined by western blotting (left panel). The right panel showcases the relative protein amounts of different groups. Error bars represent ± S.D. of triplicate experiments. The two-tailed Student’s t-test was used. *p < 0.05, **p < 0.01, and ***p < 0.001. d A20 promotes PFKL degradation through ubiquitination. Huh7 cells were transfected with the indicated plasmids. After MG132 treatment, the ubiquitination level of purified flag-PFKL protein was determined. e A20 knockdown decreases the ubiquitination level of endogenous PFKL. Huh7 cells were transfected with the indicated plasmids. After MG132 treatment for 6 h, cells were lysed for co-IP assay. Endogenous PFKL was immunoprecipitated by anti- PFKL antibody and probed for total ubiquitin.\n\nFigure 5: Figure 5. a, b A20 inhibits HCC cell proliferation through PFKL. Huh7 and LM3 cells were transfected with the indicated plasmids respectively. Proliferative ability was determined by cell counting assay at the indicated times. Data represent the means ± S.D. of three independent experiments. c A20 inhibits HCC cell colony formation through PFKL. The indicated plasmids were co-transfected into Huh7 cells. Proliferative ability was determined by colony formation experiment at 10 days in culture. Error bars represent ± S.D. for triplicate experiments. d A20 inhibits HCC cell migration through PFKL. The indicated plasmids were co-transfected into Huh7 cells. Cell migration capacity was analyzed by Transwell experiments. The numbers of migrated cells (mean ± S.D.) from three independent experiments. e, f A20 inhibits HCC cell glucose consumption and lactate excretion by downregulating PFKL. The indicated plasmids were co-transfected into Huh7 cells. Cell glucose consumption and lactate excretion were detected by glucose uptake assay and lactate colorimetric assay, respectively. Error bars represent ± S.D. of triplicate experiments. g A20 inhibits HCC cell glycolysis through PFKL. ECAR was examined using a Seahorse XFe96 analyzer. (The two-tailed Student’s t-test was used. The symbol * shows statistically significant differences with *p < 0.05, **p < 0.01 and ***p < 0.001)."
      }
    ]
  },
  {
    "id": "PMC6997366_multi_2",
    "image": [
      "images/PMC6997366-f6.png",
      "images/PMC6997366-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"A20 targets PFKL and glycolysis to inhibit the progression of hepatocellular carcinoma\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a A20 expression is inversely with PFKL. Human HCC samples were paired as tumor tissue (designated as T) and adjacent non-tumor tissue (designated as NT). Samples were lysed and directly subjected to western blotting. 10 pairs of samples showcasing an inverse correlation are shown. b Immunohistochemical staining of A20 and PFKL proteins in tumor and adjacent non-tumor tissues. A20 expression was negatively correlated with the PFKL level in human HCC specimens (magnification, left panel, ×100; right panel, ×400). c A20 and PFKL mRNA levels are inversely correlated in non-metastatic tissues and metastatic tissues. Scatterplot data are from clinical data sets from GSE364. d Kaplan–Meier overall survival curves of HCC patients in the Protein Atlas website showing that high expression of PFKL significantly correlates with poor overall survival.\n\nFigure 7: Figure 7. A20 upregulation promotes PFKL degradation through UPS. Malignant transformation of HCC results in decreased expression of A20 and subsequently reduced PFKL degradation. Accumulation of PFKL facilitates rapid cell proliferation and migration, therefore promoting HCC growth."
      }
    ]
  },
  {
    "id": "PMC6999709_multi",
    "image": [
      "images/PMC6999709-f1.png",
      "images/PMC6999709-f2.png",
      "images/PMC6999709-f3.png",
      "images/PMC6999709-f4.png",
      "images/PMC6999709-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"march5 Governs the Convergence and Extension Movement for Organization of the Telencephalon and Diencephalon in Zebrafish Embryos\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. WISH analysis of march5 at 1 cell through 24 hpf. (A) march5 was expressed in the blastodisc at 1-cell stage, indicating it is maternally expressed. (B) After MBT (512-cell), march5 was expressed in deep cell layer (DEL) and enveloping layer (EVL) except I-YSL (yolk syncytial layer). (C) march5 was expressed in both ventral & dorsal region at shield stage. (D–F) The transcripts were abundant in the central nervous system at 10 hpf through 18 hpf. (F) At 18 somite, march5 transcripts were distributed in the precursor region of brain along the AP axis. (G and H) march5 expression patterns at 24 hpf zebrafish embryo stage. Lateral (G) and anterior view (H) of the embryos labeled with march5 antisense probe at 24 hpf. march5 was expressed in the forebrain through the notochord including the telencephalon, diencephalon, tegmentum, optic tectum, cerebellum and rhombomere. All embryos were collected synchronously from WT zebrafish for WISH analysis at the corresponding stages. MHB, midbrain hindbrain boundary; ot, optic tectum; c, cerebellum; rh, rhombomere; te, tegmentum; hb, hindbrain; m, midbrain; d, diencephalon; t, telencephalon. (A–H) Scale bars = 250 μm.\n\nFigure 2: Figure 2. (A) WT zebrafish embryo, (B) vehicle control injected with the same volume of phenol red dye in distilled water as the volume of the mRNAs injected, and (C) march5 mRNA injected embryo. Microinjection of march5 mRNA (50 pg) into embryos at 1-cell stage for overexpression of march5. (D) WT, (E) 5-mismatch MO, and (F) march5 MO that 0.8 ng of march5 morpholino was injected into embryos at 1-cell stage for knockdown of march5. (G–J) At 24 hpf, embryos injected with march5 MO and coinjected with march5-MO and march5 mRNA. (G–I) march5 morphants are categorized as Class 1 through 3. (J) Rescue with march5 mRNA after injection of march5-MO. (K) The proportion of normal appearing embryos (C1) is increased after recue with march5 mRNA. (A–J) Scale bars = 250 μm.\n\nFigure 3: Figure 3. (A–F) WISH analysis of march5 in dorso-ventral axis development using dorsal markers, gsc and chd at 4.7 hpf. WT embryos (A and D), embryos injected with 5-mismatch as control (B and E), and march5 MO (C and F). march5 morphants showed narrower and reduced expression pattern for gsc (C) and the level of chd transcripts was significantly reduced in the dorsal region (D–F). (G–I) Embryos were examined for the expression of ventral marker, bmp2b at 4.7 hpf. Transcripts of bmp2b in WT (G) and 5-mis MO control (H). Injection of march5-MO caused notable expanded bmp2b expression domains, circumference around the germ ring region at 4.7 hpf (I). (A–I) Scale bars = 200 μm.\n\nFigure 4: Figure 4. (A–D) WISH analysis using ntl as a molecular marker for the convergence and extension (C&E) indicates that loss of march5 function disrupted the processes in C&E governing anterior-posterior patterning. (A) WT embryo. Microinjection of march5 mRNA (50 pg per embryo) into wild-type embryos thickened the C&E (B). march5 5-mismatch control embryos had the similar expression patterns in C&E (C) to that of WT (A). In contrast, knock-down of march5 (0.8 ng morpholino per embryo) splited the body axis (arrowheads) in march5 morphants at 8 hpf (D). (E–H) WISH analysis with sox17 as a molecular marker for the DFCs. sox17 transcripts were present in the DFC of WT (E) and control embryos injected with 5-mismatch (G). Overexpression of march5 (march5 mRNA 50 pg per embryo) extended the area expressing sox17 (F) while knock-down of march5 (0.8 ng of march5 morpholino per embryo) remarkably reduced the level of sox17 transcripts in the DFC (asterisk) of the morphants (H). (A–H) Scale bars = 200 μm.\n\nFigure 5: Figure 5. (A–C) Two color WISH analysis with krox20- and fgf8-specific probes detected changes in their transcripts in the MHB (asterisks) and the hindbrain, the rhombomeres (r) 3 and 5 at 18 hpf. (A) WT embryo, (B) 5-mismatch MO control, and (C) march5 MO (0.8 ng of march5 morpholino per embryo). (D–I) WISH analysis of march5 MO (0.8 ng of march5 morpholino per embryo) using rx3 and emx1 as probes. (D) rx3 transcripts in the presumptive eye field and hypothalamus of WT embryos at 10 hpf. (E) Embryos injected with 5-mismatch showed similar patterns to those of WT embryos. (F) march5 MO shows remarkable reduction of rx3 transcripts in the presumptive eye field and hypothalamus, which abut the telencephalic primordium at 10 hpf. Transcripts of emx3 in WT (G), 5-mismatch control (H), and march5 MO (I) at 24 hpf. emx3 transcripts were present in the telencephalon and ventral diencephalon in WT and 5-mismatch control whereas the ventral diencephalon expression was lost in the corresponding areas of march5 MO. vd, ventral diencephalon; t, telencephalon. (A–I) Scale bars = 100 μm."
      }
    ]
  },
  {
    "id": "PMC7013971_multi",
    "image": [
      "images/PMC7013971-f1.png",
      "images/PMC7013971-f2.png",
      "images/PMC7013971-f3.png",
      "images/PMC7013971-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Pexophagy: A Model for Selective Autophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic of the mammalian peroxisome matrix protein import cycle. PEX5 binds PTS1-containing proteins in the cytosol and recruits them to the peroxisome membrane through binding with PEX13-PEX14. Following the deposition of PTS1-containing proteins into the peroxisome lumen, PEX5 is ubiquitinated by the RING-like E3 ubiquitin ligases PEX2, PEX10, PEX12. Ubiquitinated PEX5 is removed from the membrane by the AAA-type ATPase complex, PEX1-PEX6-PEX26. In the cytosol, PEX5 is either deubiquitinated to enable another round of import or polyubiquitinated and proteasomally degraded.\n\nFigure 2: Figure 2. Schematic of mammalian selective autophagy. (A) Stages of autophagosome biogenesis and degradation. The ULK1 complex drives autophagy initiation to form the isolation membrane from membrane precursors. Nucleation of the isolation membrane by the VPS34 complex forms a cup-shaped membrane termed the phagophore. The phagophore elongates by the ubiquitin-like conjugation systems, ATG12-5-16 and LC3-II-phosphatidylethanolamine (PE), to form the autophagosome. The autophagosome sequesters cargoes within and undergoes fusion with a lysosome to form an autolysosome, where degradation occurs. (B) Selective autophagy cargoes are often marked for degradation by the addition of ubiquitin on their outer surface by E3 ubiquitin ligases. Ubiquitin designation signals can be dissipated from cargoes by deubiquitinases and regulators. Designated cargoes are targeted to the autophagosome through binding with autophagy receptors that interact with LC3-II on the autophagosome. Cargoes sequestered inside autophagosomes through binding with autophagy receptors are degraded in an autolysosome.\n\nFigure 3: Figure 3. Schematic of pexophagy mechanisms of designation, targeting and sequestration in yeast and mammalian systems. (A) S. cerevisiae autophagy receptor Atg36p and P. pastoris autophagy receptor Atg30p are phosphorylated by Hrr25p and an unknown kinase to designate peroxisomes for autophagy. Phosphorylated Atg36p and Atg30p interact with scaffolding proteins Atg11p, Atg17p and Atg1p that target them to autophagosomes. Interactions between phosphorylated Atg36p, Atg30p and Atg8p further sequester designated peroxisomes within autophagosomes. Pex11βp-mediated fission further aids peroxisome sequestration within the autophagosome. (B) Peroxisome membrane proteins are ubiquitinated by the E3 ubiquitin ligase, PEX2, to designate peroxisomes for pexophagy. Ubiquitinated peroxisome membrane proteins are removed from peroxisomes by the AAA-type ATPase PEX1-PEX6-PEX26 and the deubiquitinase USP30 to prevent pexophagy. Increasing expression of PEX3 on peroxisome membranes may also designate them for pexophagy. Ubiquitinated peroxisomes are targeted to autophagosomes through interactions with the autophagy receptors NBR1 and p62, which facilitate sequestration within autophagosomes through binding with LC3-II. Peroxisomes are also targeted and sequestered within autophagosomes when LC3-II out-competes PEX5 for binding to PEX14.\n\nFigure 4: Figure 4. Regulation of mammalian pexophagy. Schematic of ubiquitin-independent and ubiquitin-dependent pexophagy resulting from intracellular and extracellular cues. Amino acid starvation relieves mTORC1 inhibition of the peroxisomal E3 ubiquitin ligase PEX2, allowing PEX2 to ubiquitinate peroxisomal proteins PMP70 and PEX5 and facilitating NBR1 and p62-mediated pexophagy. LC3-II-PEX14 interactions promote pexophagy in an amino acid starvation-dependent mechanism. Increased reactive oxygen species (ROS) levels result in ATM–PEX5 interactions at the peroxisome that promote PEX5 phosphorylation by ATM and ubiquitination by PEX2, to facilitate p62-mediated pexophagy. Hypoxia relieves VHL-mediated inhibition of HIF-2a, resulting in PEX5 ubiquitination by an unknown E3 ubiquitin ligase and NBR1-mediated pexophagy. The peroxisomal AAA-type ATPase complex PEX1-PEX6-PEX26 opposes PEX5-ubiquitination and pexophagy."
      }
    ]
  },
  {
    "id": "PMC7042889_multi",
    "image": [
      "images/PMC7042889-f1.png",
      "images/PMC7042889-f2.png",
      "images/PMC7042889-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Evaluation of X-Linked Adrenoleukodystrophy Newborn Screening in North Carolina\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A first-tier high-performance liquid chromatography tandem mass spectrometry (HPLC-MS/MS) assay in negative ion mode was used for the initial screening of specimens. All specimens that screened positive were sent for sequencing of the adenosine triphosphate–binding cassette subfamily D member 1 (ABCD1) gene, and the infant was referred to follow-up. Multiple specimens from the same infant with borderline results that were also classified as abnormal were sent for sequencing and referred to follow-up. C24 indicates 1-tetracosanoyl-sn-glycero-3-phosphocholine; C26, 1-hexacosanoyl-2-hydroxy-sn-glycero-3-phosphocholine; and LPC, lysophosphatidylcholine\n\nFigure 2: Figure 2. The flowchart shows the protocol for confirmatory testing and short-term follow-up of screen-positive specimens through diagnosis. ABCD1 indicates the adenosine triphosphate–binding cassette subfamily D member 1 gene; DBS, dried blood specimen; NCSLPH, North Carolina State Laboratory of Public Health; UNC, University of North Carolina; VLCFA, very long-chain fatty acid; VUS, variant of unknown significance; and X-ALD, X-linked adrenoleukodystrophy.\n\nFigure 3: Figure 3. Screen-positive cases are as follows: X-linked adrenoleukodystrophy (X-ALD) hemizygotes, false-positive (False pos), X-ALD heterozygous female, and other disorders. The cyan vertical line is set at 0.15 μmol/L, and the navy horizontal line is set at 0.175 μmol/L to capture all the samples with increased concentrations of C26:0-LPC and C24:0-LPC, respectively. The tan vertical line at 0.08 μmol/L represents the borderline cutoff value for C26:0-LPC. The patient numbers in parentheses correspond to those given in Table 2. AGS indicates Aicardi-Goutières syndrome; F, female; and M, male."
      }
    ]
  },
  {
    "id": "PMC7051990_multi",
    "image": [
      "images/PMC7051990-f1.png",
      "images/PMC7051990-f2.png",
      "images/PMC7051990-f3.png",
      "images/PMC7051990-f4.png",
      "images/PMC7051990-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Overexpression of △12, △15-Desaturases for Enhanced Lipids Synthesis in Yarrowia lipolytica\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A schematic illustrating the pathways rewired in Y. lipolytica’s metabolism to drastically increase lipogenesis capacity. Acetyl-CoA carboxylase gene (ACC1): ACC1 catalyzes the first committed step toward lipid biosynthesis, converting cytosolic acetyl-CoA into malonyl-CoA, which is the primary precursor for fatty acid synthesis. Diacylglycerol acyltransferases I gene (DGA1): DGA promotes triacylglycerol (TAG) biosynthesis and transport TAG into the lipid droplet. The multifunctional enzyme gene (MFE1): MFE1 catalyzes both the second and third steps of fatty acid β-oxidation. Peroxisome biogenesis factor 10 (PEX10), a transcription factor necessary for correct peroxisomal biogenesis and morphology. SCD, 12D, and 15D: The fatty acid desaturases catalyze the introduction of double bonds into △9, △12, and △15 fatty-acid hydrocarbon chains to produce unsaturated fatty acids.\n\nFigure 2: Figure 2. Lipid contents and fatty acid profiles of the strains with PEX10 deletion and DGA1 overexpression. (A) The percentage of lipid and fatty acid dry cell weight (Lipid% DCW) was shown for strains PO1f, YL-1, YL-2 cultivated in the media of C:N = 50. (B) Fatty acid profiles of lipid extract from the strains PO1f, YL-1, YL-2 were shown after 6 day shake flask fermentation. Error bars represent standard deviations (n = 3). The asterisks indicate a significant difference compared with the control (**p < 0.01).\n\nFigure 3: Figure 3. Lipid contents and fatty acid profiles of the strains with the expression of 12D, SCD, and 15D. (A) The percentage of lipid and fatty acid dry cell weight (Lipid% DCW) was shown for strains YL-2, YL-3(SCD+), YL-4(12D+), and YL-5(15D+) cultivated in the media of C:N = 50. (B) Fatty acid profiles of lipid extract from the strains YL-2, YL-3(SCD+), YL-4(12D+), and YL-5(15D+) were shown after 6 day shake flask fermentation. Error bars represent standard deviations (n = 3). The asterisks indicate a significant difference compared with the control (**p < 0.01).\n\nFigure 4: Figure 4. Lipid contents of the strains with the expression of 12D-SCD, 15D-SCD, and 12D-15D. Error bars represent standard deviations (n = 3). The asterisks indicate a significant difference compared with the control (**p < 0.01).\n\nFigure 5: Figure 5. Combinatorial analysis of the PO1f, YL-8(12D+-15D+), YL-9, and YL-10 strains. (A) The percentage of lipid and fatty acid dry cell weight (Lipid% DCW) was shown for strains PO1f, YL-8(12D+-15D+), YL-9, YL-10 cultivated in the media of C:N = 50. (B) Relative quantification of RNA transcripts using real-time PCR. ACTIN was used as the reference gene. Error bars represent standard deviations (n = 3). The data are normalized by the transcription level of genes in PO1f, except for △15D, which is normalized by the transcriptional level in YL-9. Red box: the transcriptional levels of △15D in YL-9 and YL-10 were calculated using the 2–△ct calculation (△ct = CT, Target − CT, Actin). (C) Imaging analyses of the PO1f strain at 48 h of the shake flask fermentation period. (D) Imaging analyses of the YL-10 strain at 48 h of the shake flask fermentation period."
      }
    ]
  },
  {
    "id": "PMC7054992_multi",
    "image": [
      "images/PMC7054992-f1.png",
      "images/PMC7054992-f2.png",
      "images/PMC7054992-f3.png",
      "images/PMC7054992-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisome prognostications: Exploring the birth, life, and death of an organelle\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PPVs. (A) An electron micrograph of PPVs isolated from Y. lipolytica. Scale bar, 200 nm. (B) A schematic of preperoxisomal vesicles revealing the different morphologies observed within and between different PPVs. The different diameters of the membranes are proposed to reflect the asymmetric distribution of different classes of peroxisomal membrane proteins.\n\nFigure 2: Figure 2. A spatiotemporal model of peroxisome biogenesis and Pex3 function. Peroxisome proliferation occurs by two mechanisms: division of existing peroxisomes through fission and de novo formation from the ER. Peroxisomes are formed de novo from the ER through budding and then fusion of two classes of PPV (although there may be more). This mechanism separates RING finger and docking components of the import complex into different vesicles, which are not import competent until after fusion and assembly of a complete and functional import complex. Once mature, these peroxisomes can multiply by growth and incorporate proteins and membranes from the ER. These two arms of the biogenic cascade are mediated by Pex3, which has different functions depending on its location. (1) Pex3 facilitates PMP insertion into membranes, either with assistance of a membrane translocon, or, for a subset of membrane proteins, direct insertion into the membrane. (2) Pex3 chaperones PMPs, protecting them from quality control systems such as ER-associated protein degradation (ERAD), and assisting in their lateral sorting through the ER to sites of PPV formation. (3) Pex3 and Pex19 define sites of PPV budding and recruit the scission machinery, ESCRT-III, to release them from the ER. (4) Additional functions of Pex3, such as peroxisomal tethering to the ER, are mediated by its binding proteins, such as Inp1.\n\nFigure 3: Figure 3. A model for Pex3 and Pex19 topology and chaperone function. Pex3 is a type-III transmembrane protein. It interacts with peroxisomal membrane proteins through binding sites located along the side of its cytosolic helical bundle. This interaction is initiated by Pex19, which first binds the PMP in the cytosol and then brings it into the proximity of Pex3.\n\nFigure 4: Figure 4. A nested feedforward network motif in peroxisome biogenesis. Network motifs describe the distinctive features of the relationship of cellular components that enable predictions of their behavior when stimulated or repressed. Here, the production of peroxisomes occurs not only by growth and division but also de novo biogenesis. Because the de novo biogenesis pathway feeds into the growth and division pathway, leading to the further proliferation of peroxisomes, this arrangement resembles a nested coherent feedforward network motif. See text for further details. (A) The nested feed-forward network motif regulating peroxisome biogenesis. (B) The biogenesis pathway of peroxisomes and their life cycle, spatially arranged to illustrate the topology of the nested feed-forward network motif."
      }
    ]
  },
  {
    "id": "PMC7057175_multi",
    "image": [
      "images/PMC7057175-f1.png",
      "images/PMC7057175-f2.png",
      "images/PMC7057175-f3.png",
      "images/PMC7057175-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The diversity of ACBD proteins – From lipid binding to protein modulators and organelle tethers\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Evolution of Acyl-CoA binding domain containing proteins (ACBDs) among metazoans. The scheme summarizes data from a phylogenetic reconstruction including 449 sequences from animals, fungi and plants (for details see Fig. S1). After alignment by the ClustalW 2.0 algorithm included in the Seaview software package and manual correction of misaligned sequences, phylogenetic reconstructions were performed with PhyML3.0 using the aLRT algorithm for branch support, BioNJ for tree topology optimization, 4 rate categories for RHAS (Rate Heterogeneity Among Sites) modelling and including NNI and SPR tree searching operations. Furthermore, we used Marcoil1.0 online prediction tool [181] to screen the sequences for coiled-coil motifs and TMHMM2.0 and TMPred for TMD prediction [182,183]. Colours highlight four major categories of ACBDs – the C-terminally membrane-anchored ACBD4/5 (green), the enoyl-CoA isomerase containing ACBD2 (blue), the small soluble ACBD1 (red) and the extended forms with protein interaction domains ACBD3/6 and extended plant forms (purple; ACBP class II–IV). Taxonomic categories shown name the minimum organism group in which a distinct protein subfamily was detected. E.g. while ACBD2 was only found in vertebrate and invertebrate animals, ACBD4/5 occur in both animals and fungi, more specifically in basidiomycota and several early branching fungal divisions of incertae sedis (*symbolized with Mucoromycota in the figure). By contrast, the ankyrin repeat-containing ACBD6/ACBP II is distributed among all metazoans indicating its early evolution from the ACBD1 form. Evolution of Acyl-CoA binding domain containing proteins (ACBDs) among metazoans. The scheme summarizes data from a phylogenetic reconstruction including 449 sequences from animals, fungi and plants (for details see Fig. S1). After alignment by the ClustalW 2.0 algorithm included in the Seaview software package and manual correction of misaligned sequences, phylogenetic reconstructions were performed with PhyML3.0 using the aLRT algorithm for branch support, BioNJ for tree topology optimization, 4 rate categories for RHAS (Rate Heterogeneity Among Sites) modelling and including NNI and SPR tree searching operations. Furthermore, we used Marcoil1.0 online prediction tool [181] to screen the sequences for coiled-coil motifs and TMHMM2.0 and TMPred for TMD prediction [182,183]. Colours highlight four major categories of ACBDs – the C-terminally membrane-anchored ACBD4/5 (green), the enoyl-CoA isomerase containing ACBD2 (blue), the small soluble ACBD1 (red) and the extended forms with protein interaction domains ACBD3/6 and extended plant forms (purple; ACBP class II–IV). Taxonomic categories shown name the minimum organism group in which a distinct protein subfamily was detected. E.g. while ACBD2 was only found in vertebrate and invertebrate animals, ACBD4/5 occur in both animals and fungi, more specifically in basidiomycota and several early branching fungal divisions of incertae sedis (*symbolized with Mucoromycota in the figure). By contrast, the ankyrin repeat-containing ACBD6/ACBP II is distributed among all metazoans indicating its early evolution from the ACBD1 form.\n\nFigure 2: Figure 2. 3D predictions of selected acyl-CoA binding proteins/domains. The predictions were accomplished with Phyre2 using entire cDNA sequences from ACBD1 of Homo sapiens (F) and homologous small ACBDs from the β-proteobacterium Aquabacterium parvum beta (A), an hitherto undefined ACBD sequence (TFG05618) of Lokiarchaeota origin (B), the choanoflagellate Monosiga brevicollis (C), the Mucoromycota fungus Rhizopus oryzae (D), the moss Sphagnum fallax (E); for comparison the ACB domain of human ACBD5 was added subjected to 3D prediction (G). Hydrophobic regions in the protein surface structure are highlighted in red and residues conserved among all species are shown. (H) Tertiary structure reconstructions from (A)–(F) are additionally shown as sequence overlay in ribbon cartoon format to illustrate the significant structural homology in the distantly related species (depicted in different colours). Conversion of the PDB files into graphical illustrations was performed with PyMOL 2.3.2.\n\nFigure 3: Figure 3. Domain structures of animal, fungal and plant acyl-CoA binding proteins. The schemes represent ACBDs from Homo sapiens (Mammalia, Animalia), Ustilago maydis (Basidiomycota, Fungi) and Oryza sativa (Angiospermae, Planta); sequence and domain lengths as well as position are proportional to the original protein structure. For some ACBDs, several isoforms have been reported or predicted. In such cases, only the currently best characterized isoform is presented. Note the structural similarity between the mammalian, fungal and plant ankyrin repeat-containing ACBDs, which suggests an early evolution already found in the LECA. ECH, enoyl-CoA hydratase domain; FFAT, two phenylalanines in an acidic tract motif.\n\nFigure 4: Figure 4. Schematic overview of the localization of ACBD proteins. ACBD, acyl-CoA binding domain containing protein (ACBD1–8); ER, endoplasmic reticulum; LPLAT, acyl-CoA:lysophospholipid acyltransferase; NMT2, N-myristoyltransferase 2; PO, peroxisome; TSPO, translocator protein for cholesterol; VAPB, vesicle-associated membrane protein (VAMP)–associated protein B. For details see 3, 4, 5, 6, 7 as well as Table 1, Table 2."
      }
    ]
  },
  {
    "id": "PMC7075811_multi",
    "image": [
      "images/PMC7075811-f1.png",
      "images/PMC7075811-f2.png",
      "images/PMC7075811-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Dysfunction in Neurological Diseases and Brain Aging\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Summary of specialized roles of peroxisomes in some organs, including the brain. Created using BioRender.\n\nFigure 2: Figure 2. Summary of pexophagy. (A) In macropexophagy, a form of macroautophagy selective for peroxisomes, a single membrane known as a phagophore engulfs a peroxisome for degradation. The phagophore matures into an autophagosome, which then fuses with a lysosome. Their fusion creates an autophagolysosome that degrades the target. (B) In mammalian systems, pexophagy occurs when Pex2 ubiquitinates Pex5. As a result, autophagy adaptor proteins NBR1 or SQSTM1 (p62) bind to ubiquitinated Pex5, and then eventually bind to LC3 on the phagophore. Due to this process, pexophagy occurs. Created using BioRender.\n\nFigure 3: Figure 3. Summary of peroxisomal dysfunction in age-related diseases in the CNS, and other diseases that affect the CNS. Created using BioRender."
      }
    ]
  },
  {
    "id": "PMC7086354_multi",
    "image": [
      "images/PMC7086354-f1.png",
      "images/PMC7086354-f2.png",
      "images/PMC7086354-f3.png",
      "images/PMC7086354-f4.png",
      "images/PMC7086354-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"F-box proteins and cancer: an update from functional and regulatory mechanism to therapeutic clinical prospects\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A SCF complex. This complex comprises of scaffold CUL1, SKP1, RBX1/2 and F-box receptor. The substrate is phosphorylated by specific kinase enzyme and recognized by the substrate recognition domain. Ubi is transferred from E2 to E3 ligase/F-box proteins in coordination with RBX1/2 for proteosomal degradation. B Different forms of ubiquitination. After the substrate is presented to F-box protein, different types of ubiquitination occur depending on the number and types of Ubi/Ubis presented to substrates, namely mono-ubiquitination (i.e., single ubiquitin is added to substrate), linear poly Ubi-K63/K48/K11 (many Ubis are added one after another along a line format at lysine K63/K48/K11 locus of Ubis) and multi-poly-Ubi-K63 (Ubis are added in multilayers at lysine K63/K48/K11 locus). Some other Ubi-types are yet undetermined, such as K6, K27, K29, K33, etc. Ubi-K48/K11 types are proteolytic whereas Ubi-K63 and mono-Ubi are non-proteolytic in nature. The substrate is mainly processed at the 26S proteasome complex for ubiquitination guided proteasomal degradation.\n\nFigure 2: Figure 2. Substrates of SKP2 and FBXL2 in various cancer relevant cellular functions and pathways. K63-linkage poly-ubiquitinations are annotated on the arrows, the others are K48-linkage ubiquitinations.\n\nFigure 3: Figure 3. Substrates of FBXL5 in iron homeostasis and various cancer relevant cellular functions and pathways.\n\nFigure 4: Figure 4. Substrates of FBXW family proteins β-TrCP and FBXW7 in various cancer relevant cellular functions and pathways.\n\nFigure 5: Figure 5. Substrates of FBXO family proteins FBXO1, FBXO3 and FBXO4 in various cancer relevant cellular functions and pathways."
      }
    ]
  },
  {
    "id": "PMC7106852_multi",
    "image": [
      "images/PMC7106852-f1.png",
      "images/PMC7106852-f2.png",
      "images/PMC7106852-f3.png",
      "images/PMC7106852-f4.png",
      "images/PMC7106852-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Slc25a17 Gene Trapped Mice: PMP34 Plays a Role in the Peroxisomal Degradation of Phytanic and Pristanic Acid\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Expression of PMP34 in murine embryonic and adult life. (A) Northern analysis of RNA isolated from liver of age matched female (F) and male (M) mice of the indicated genotypes. Migration of ribosomal markers indicated at the left. (B–E) PMP34 expression in Slc25a17+/– embryos at different prenatal stages or in adult mice as revealed by promoter-driven β-galactosidase reporter expression: whole mount staining at E7.5 (B) and E12.5 (C); stained cryosections (10 μm) counterstained with Nuclear Fast Red from liver (D) and kidney (E) (Scale bar 10 μm; stainings of WT samples were negative). (F) β-galactosidase activity in tissues derived from 1 month old +/– male (black bars) or adult –/male (gray bars). Values are represented as mean ± SD of separate measurements on two mice/genotype, except for liver (n = 5 for –/–, n = 3 for +/–). Galactosidase activities in tissues of WT mice were less then 0.05 mU/mg protein (not shown). Hard. Gl., Harderian gland; prep. Gl., preputial gland; CBR, cerebrum; CBL, cerebellum; duodenum, duodenal mucosa; BAT, brown adipose tissue. Panel G, PMP34 deficiency at the protein level. Total liver homogenates of adult wild type (WT) or PMP34-deficient (KO) mice, all containing equal amounts of protein, were processed for SDS-PAGE, Western blotting, and sequential immunoblot analysis with antisera specific for PMP34 and β-actin. The migration points of relevant molecular mass markers (expressed in kDa) are shown on the left. The arrows mark specific immunoreactive bands.\n\nFigure 2: Figure 2. α- and β-oxidation in PMP34 deficient cells. Primary MEF (A), immortalized MEF (B,C) or liver slices (D) from wild type (WT) and PMP34 knockout (KO) embryos or mice were analyzed for α- and β-oxidation using 14C-labeled substrates. Data for primary MEF (A), derived from a single WT or KO E14.5 embryo (C57BL/6 background), are based on single incubations at 310-430 μg protein/T25 falcon, followed by analysis of labeled oxidation products (white bars: CO2; gray bars, acid soluble material or formate in case of 3-methylbranched fatty acids), normalized to protein content of the monolayer. Incorporation of fatty acids in glycerolipids and total uptake was comparable between the genotypes (not shown). Similar findings were obtained when incubations were done at other cell densities. Data for immortalized fibroblasts (B,C), derived from 2 different embryos per genotype, are based on duplicate incubations at 110-180 μg protein/T25 falcon, and expressed as mean ± SD. Oxidation (B), normalized to protein, represent the sum of CO2 and acid soluble material or to CO2 plus formate in case of 3-methyl-branched fatty acids. Total uptake by fibroblasts, calculated as oxidation plus esterification, the latter representing the label recovered in cholesterylesters, triacylglycerols and phospholipids (C), was not different between WT and KO cells. Data for liver slices (D) are based on duplicate incubations with slices derived from 3 male animals per genotype and represent the sum of CO2 and acid soluble material or CO2 plus formate in case of 3-methyl-branched fatty acids, expressed as mean ± SD (normalized to phospholipids, PL). For no substrate, differences in CO2 or acid soluble material production were statistically significant except for THCA (*P < 0.05). Esterification rates for fatty acids were comparable (not shown). Dicarboxylic acids, 2-hydroxy long chain fatty acids, and bile acids are hardly or not incorporated into triacylglycerols and phospholipids, hence esterification of these substrates was not analyzed. C16, [1-14C]-hexadecanoic acid; 2MC16, 2-methyl-[1-14C]-hexadecanoic acid; 3MC16, 3-methyl-[1-14C]-hexadecanoic acid; C24, [1-14C]-tetracosanoic acid; 2OHC18, 2-hydroxy-[1-14C]-octadecanoic acid; C24:6, [2-14C]-6,9,12,15,18,21-tetracosahexaenoic acid; THCA, [26-14C]-3,7,12-trihydroxycholestanoic acid; diC14, [1,14-14C]-tetradecanedioic acid.\n\nFigure 3: Figure 3. Phenotype of phytol challenged PMP34 knockout mice. (A–C) Influence of phytol diet on male or female PMP34 knock out (KO) mice versus age matched wild type (WT) mice on body weight, expressed as % of body weight (BW) at the start of the diet (A), liver size, expressed in g/100 g BW (B), and fat mass, expressed in g/g total tissue mass (TTM) as determined by DEXA at the start and end of the diet (C). Data are represented as mean ± SD (n = 4-8 (A,B) or 3-6 (C) per gender and per genotype. The effect of phytol was statistically analyzed per gender (Oneway ANOVA **P < 0.01, *P < 0.05 KO versus WT). Heterozygous mice responded in a similar way to phytol diet as WT animals and liver size and fat mass of KO and WT did not differ on a control diet (data not shown). (D,E) Mottled appearance of liver of knockout mice on a phytol diet, as seen upon dissection of a male mouse (D) or after bleeding and removal of the liver (E; scale bar 1 cm). Similar mottling is evident in female KO mice (not shown). (F–I) H&E stained liver sections of WT (F) and KO male mice (G–I) on phytol enriched diet showing enlarged nuclei (open arrowhead), apoptotic bodies (full arrowhead), inflammation zones (arrow) and microvesicular steatosis (dashed arrow) in the phytol-fed KO mice. (F,G): portal triads; (H,I): intermediary zone of the hepatic lobule. Scale bar 50 μm.\n\nFigure 4: Figure 4. Hepatic steatosis in phytol challenged PMP34 knockout mice. Liver sections of male control (WT) and knockout (KO) mice fed standard or phytol enriched diet were stained with Oil red O (ORO) (top row; scale bar 50 μm) or immunostained for macrophage marker F4/80 plus DAPI (second row; scale bar 200 μm; inset scale bar 25 μm), showing in the liver of the KO mice fed phytol accumulation of neutral lipids or enlarged macrophages in the process of phagocytosing cell debris (asterisks). Bottom, left: representative TLC of lipid extracts of liver of male age-matched WT and KO mice fed standard or phytol diet, visualized by iodine staining (solvent hexane/diethylether/acetic acid 70/30/1, v/v; portion of plate shown; direction of solvent indicated by arrow and its front by F). Standards, migration indicated, were cholesterol (C), triolein (triacylglycerides, TAG), cholesteryloleate (cholesterylester, CE); X indicates presence of new TAG species. When using hexane/diethylether/acetic acid (80/20/1, v/v) as solvent, spot X is splitting up in separate bands (right panel).\n\nFigure 5: Figure 5. Lipid accumulation, vacuolization and dual hepatocyte population in liver of phytol challenged PMP34 knockout mice. Left panel: Electron microscopic image of a liver section from an adult male phytol fed PMP34 knockout mouse, stained for catalase and contrast stained with uranyl acetate and lead citrate. Lipid accumulation (L) and vacuolization (V) are clearly visible in the hepatocyte lacking catalase positive peroxisomes, adjacent to a hepatocyte containing DAB-reactive peroxisomes (PO). Right panel: Light microscopic image of a semithin liver section from an adult male phytol fed PMP34 knockout mouse. A dual population of hepatocytes can be observed: aberrant hepatocytes, lacking DAB-reactive peroxisomes and containing cytoplasmic and nuclear catalase (closed arrowhead) are discernible adjacent to normal hepatocytes containing DAB-reactive peroxisomes (open arrowhead)."
      }
    ]
  },
  {
    "id": "PMC7106852_multi_2",
    "image": [
      "images/PMC7106852-f6.png",
      "images/PMC7106852-f7.png",
      "images/PMC7106852-f8.png",
      "images/PMC7106852-f9.png",
      "images/PMC7106852-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Slc25a17 Gene Trapped Mice: PMP34 Plays a Role in the Peroxisomal Degradation of Phytanic and Pristanic Acid\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Hepatic changes in phytol treated PMP34 knockout mice. Livers of adult male (M) or female (F) wild type (+/+) or knockout mice (–/–) given a 0.5% phytol enriched diet for 3 weeks were analyzed for protein and lipid content, fatty acid composition, and peroxisomal β-oxidation enzymes. Small amounts of branched fatty acids were present in all +/+ females, but only in one +/+ male animal detected (hence larger SD), whereas severe but variable accumulation was seen in all –/– animals. Arachidonic acid (C20:4) was expressed relative to the amount of palmitic acid (C16:0) per liver. ACOX1 values are several fold higher than in animals receiving a normal diet (see Supplementary Figure S3). Values are mean ± SD for 4-6 animals per gender and per genotype, treated in four different feeding studies. Values in heterozygous mice were similar to those in wild type animals (data not shown). Statistical differences are calculated per gender (Oneway ANOVA ***P < 0.005, **P < 0.01, *P < 0.05 KO versus WT). TAG, triacylglycerides; PL, phospholipid; 3MC13, 4,8,12-trimethyltridecanoic acid; mU, nmol/min.\n\nFigure 7: Figure 7. Total hepatic fatty acid profiles of phytol challenged PMP34 knockout mice. GC-MS profiles of tert-butyldimethylsilyl esters prepared from total lipid extracts from livers of age-matched male wild type (A) and knockout (B) mice fed phytol diet. A portion of the chromatogram (15-35 min) is shown. Major peaks are labeled for the wild type sample (A), and extra peaks appearing in the knockout sample are indicated in panel B. Using a temperature program better suited for separation of medium chain fatty acids, 2,6,10-trimethylundecanoic acid is also seen in the KO profiles (not shown) (IS, internal standard; tricosanoic acid, C23:0).\n\nFigure 8: Figure 8. Hepatic acyl-CoA profiles of phytol challenged PMP34 knockout mice. Panels (A,B) show representative RP-chromatograms of etheno-acyl-CoAs (and other adenine-containing compounds), prepared from liver extracts of female (A) or male (B) wild type and PMP34 deficient mice on a normal or phytol-enriched diet, spiked with internal standard (500 pmol 3-methyldodecanoyl-CoA, IS). Arrows indicate the elution, based on spiking and co-elution, of phytanoyl-CoA (Ph), pristanoyl-CoA (Pr), and 4,8,12-trimethyltridecanoyl-CoA (3MC13). New peaks appearing in the phytol-treated female +/+ animals, and further increased in all –/– mice, are marked with a red asterisk. Some phytol-derived intermediates, marked with a black asterisk, elute close to straight acyl-CoAs, impeding baseline separation. The elution of different standards as etheno-derivatives, is shown in panel C (taken from Mezzar et al., 2017): mix 1 (red) contains CoA, acetyl-, propionyl-, hexanoyl-, decanoyl-, palmitoyl- and lignoceroyl-CoA; mix 2 (green) acetyl-, octanoyl-, tetradecanoyl-, palmitoyl- and eicosanoyl-CoA; mix 3 (blue), IS and pristanoyl-CoA; mix 4 (black) phytanoyl-CoA. Panel (D) shows the quantification of known and some unknown, labeled as A–C in panel (A), phytol-derived acyl-CoAs (values based on 2 separate mice per gender and per genotype; mean ± SD).\n\nFigure 9: Figure 9. Biliary bile acid profiles of PMP34 KO mice. Panels (A–E) show MS-scans [350-650 m/z; negative mode; smoothed (0.2; 1; GA)] of bile obtained from wild type or PMP34 KO mice fed a normal or a phytol enriched diet or treated with cholesterylamine (C-amine) (gender and concentration of biliary bile acids of the individual animals is indicated in parentheses). Murine bile contains mainly tauro-conjugates, the major ones being tauromuricholic acids (TMCA, a,p-isomers) and taurocholic acid (TCA), both same m/z 514 (signal topped in all panels), followed by taurochenodeoxycholic acid (TCDCA, m/z 498) and a taurotetrahydroxycholanic acid (T(OH)4, m/z 530) (IS, 23-nor-3a,12a-dihydroxy-5p-cholanoic acid, m/z 377). The ion with m/z 596 represents a Na-acetate adduct of m/z 514; non-conjugated bile acids (cholic acid/muricholic acid, CA/MCA, m/z 407; deoxycholic acid, DCA, m/z 393) are hardly visible. In contrast, an abnormal profile is clearly revealed when analyzing bile of a mouse lacking MFP2 (panel F) with accumulation of C27 bile acid intermediates, such as A24-cholestenoic acid (A24-THCA, m/z 447) and its tauroconjugate (TA24THCA, m/z 554), and 24-hydroxycholestanoic acid (24OH-THCA, m/z 465), or a mouse lacking liver peroxisomes (panel G) with abnormal levels of trihydroxycholestanoic acid (THCA, m/z 449) and its tauroconjugate (TTHCA, m/z 556). Nor-CA/MCA (m/z 393), reported in deconjugated bile of SCPx-deficient mice, or their tauroconjugates (m/z 500), were not seen.\n\nFigure 10: Figure 10. Link between PMP34 and peroxisomal phytol degradation. Schematically shown are the different steps involved in phytol breakdown and their (presumed) subcellular sites. Cofactors involved in intraperoxisomal reactions are highlighted in blue; enzymatic steps are drawn with solid black arrows; transport processes are shown with dotted lines, black for known or accepted ones, ochre-brown for non-characterized or putative ones, orange for (hypothesized) PMP34 related ones. The areas depicting reactions related to α- and β-oxidation are tinted darker. Compounds (or their hydrolysis product) depicted in red accumulate in phytol treated PMP34 knockout mice. Likely, different phytol derivatives can enter peroxisomes (phytol, 2-phytenal, 2-phytenic acid, phytanic acid, 2-phytenoyl-CoA, phytanoyl-CoA, phytanic acid), the CoA-esters presumably via ABCD3, but whether or not hydrolysis occurs during this transport is not specified. Activation of phytanic acid by ACSVL1 requires intraperoxisomal ATP/CoA (and export of generated AMP, perhaps via PMP34), but phytanic acid could also be activated at the cytosolic side of the peroxisomal membrane by ACSL4/1. In the α-oxidation process, ATP stimulates PHYH but is not required for its activity. Before pristanic acid, produced by α-oxidation, can enter the β-oxidation spiral, it needs to be activated to its CoA-ester, a CoA/ATP-dependent step which could be carried out in the peroxisomal lumen by ACSVL1 (AMP export not depicted) or in the cytosol by ACSL4/1, followed by transport via ABCD3. Subsequently, pristanoyl-CoA is degraded by three β-oxidation cycles (individual reactions are not shown) whereby the produced 4,8-dimethylnonanoyl-CoA (4,8-DM-C9-CoA) is presumed to be exported either as carnitine ester or acid, both reactions producing CoA. Similarly, the other β-oxidation products acetyl- and propionyl-CoA can be converted to carnitine esters (by CRAT) or hydrolyzed (by ACOT8/12) and result in CoA formation (not shown). CoA is not formed when 4,8-dimethylnonanoyl-CoA is cleaved by nudix hydrolases (NUDT), instead adenosine-3′,5′-diphosphate (PAP) and 4,8-dimethylnonanoyl-phosphopantetheine (4,8-DM-C9-PP) are generated. These NUDT enzymes can also act on CoA, producing phosphopantetheine (PP) and PAP. These products (MW 358, respectively 423 Da), being negatively charged, might not leak out via PMP22, but could rely on PMP34. Given the presence of shortened branched acyl-CoAs, activation of phytanic/pristanic acid is not a major issue if PMP34 is absent. Inadequate import of CoA (orange arrow), required for the SCPx reactions of the β-oxidation spiral, can explain the build-up of the upstream intermediates. Inability to export CoA, formed by the above mentioned ACOT/CROT/CRAT reactions, could reverse these reactions and slow down β-oxidation. If the CROT/ACOT8 reactions are to sluggish to handle an exces of 4,8-dimethyl-C9-CoA, PMP34-mediated export of this CoA-ester would offer another explanation for the observed metabolic phenotype. Inability to remove PAP could impact phytol degradation as well, if this compound is inhibitory to some oxidation enzymes. DM-, dimethyl-; TM-, trimethyl-; ER, endoplasmic reticulum."
      }
    ]
  },
  {
    "id": "PMC7116601_multi",
    "image": [
      "images/PMC7116601-f1.png",
      "images/PMC7116601-f2.png",
      "images/PMC7116601-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogens, platelet-activating factor and beyond – Ether lipids in signaling and neurodegeneration\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The crucial steps of ether lipid biosynthesis take place in peroxisomes, which are in close interaction with other organelles via various recently identified contact sites (reviewed in (Schrader et al., 2020)). Accordingly, multiple factors may influence the synthesis and levels of ether lipids in such a complex environment: The production of fatty alcohols from fatty acyl-CoA for generation of the ether bond has been proposed as rate-limiting step for ether lipid biosynthesis (Honsho et al., 2013). Accordingly, substrate availability and activity of FAR1 are essential regulators of the whole pathway (1). Owing to the localization of the enzymes carrying out the initial steps, ether lipid biosynthesis critically depends on peroxisome biogenesis and proliferation (2), processes which themselves are subject to regulation by multiple factors. Polymorphisms and mutations in biosynthetic enzymes can have a dramatic impact on ether lipid levels (3). Based on current knowledge, contact sites may be crucial for the exchange of ether lipid precursors between organelles (4). For example, tethering to the ER was shown to be required for maintenance of plasmalogen levels (Hua et al., 2017) and is influenced by cellular oxidative stress and other factors. After exiting the peroxisome by an unknown mechanism (indicated by a question mark), further enzymatic modification of the ether lipid precursor is accomplished at the ER or in the cytosol, thus producing the wide range of different ether lipid species. These are continuously exposed to remodeling (e.g. by phospholipases) or catabolic steps (5). Apart from endogenous biosynthesis, ether lipids can, to a lesser extent, also be derived from dietary sources (6). AADHAPR, acyl/alkyl-DHAP reductase; ADHAPS, alkyl-DHAP synthase; DHAP, dihydroxyacetone phosphate; DHAPAT, DHAP acyltransferase; FAR, fatty acyl-CoA reductase.\n\nFigure 2: Figure 2. A prototypic plasmalogen (A), lysoplasmalogen (B), N-acyl ethanolamine plasmalogen (pNAPE; C), platelet-activating factor (PAF; D), lyso-PAF (E), alkyl- glycerol (F), alkenyl-lysophosphatidic acid (alkenyl- LPA; G), alkyl-LPA (H), noladin ether (I), ether- linked diglyceride (J), plasmanyl phospholipid (K), seminolipid (L) and fecapentaene (M) are shown with alkyl groups (ether-bonded) colored red, al-kenyl groups (vinyl ether-bonded) orange and acyl groups (ester-bonded) blue. Head groups in (A), (B) and (J) are predominantly ethanolamine or choline. R1 represents alkyl residues originating from primary alcohols synthesized by FAR (mainly C16:0, C18:1 or C18:0 but also other, less common species have been reported). R2 and R3 designate a wider range of saturated and unsaturated fatty acyl chains. In plasmalogens (A), R2 is usually a PUFA residue; in the case of noladin ether (H), R2 indicates the ether- bonded arachidonyl moiety. R4 constitutes C2H5 (fecapentaene-12) or C4H9 (fecapentaene-14).\n\nFigure 3: Figure 3. (A) Plasmalogens are essential membrane constituents that modulate membrane properties. Their lack can disturb the dynamics of membrane-associated signaling processes, as demonstrated for the impaired membrane recruitment and functioning of AKT/PKB. Other pathways may be affected similarly. (B) Ether-linked diglycerides have been proposed to compete with diacylglycerol (DAG) for binding of PKC but exert a weaker (or no) activation, thus dampening downstream responses. (C) Secreted ether-linked species like alkyl-LPA, alkenyl-LPA and PAF bind G protein-coupled receptors on the cell surface; receptor binding triggers a cascade involving activation and dissociation of G proteins followed by induction of downstream pathways including, but not limited to, MAP kinase pathways. Note that LPA and PAF receptors are not necessarily expressed by the same cell type, as shown here for simplicity. (D) Ether lipids serve as ligands for nuclear receptors like PPARα or PPARγ. Upon ligand binding in the nucleus, or in the cytoplasm triggering nuclear translocation, the PPARs bind to response elements in the DNA. As heterodimers with the retinoid X receptor (RXR), PPARs associate with coactivators (not shown), thus inducing the expression of target genes. Several ether lipid ligands have been suggested, including chlorinated plasmalogens and noladin ether for PPARα as well as alkyl-LPA and plasmanyl phospholipids for PPARγ. For image clarity, the signaling pathways are drawn highly simplified and several intermediate steps are omitted for easier understanding. MAPKK, MAP kinase kinase; MAPKKK, MAP kinase kinase kinase."
      }
    ]
  },
  {
    "id": "PMC7180290_multi",
    "image": [
      "images/PMC7180290-f1.png",
      "images/PMC7180290-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Failure of intrathecal allogeneic mesenchymal stem cells to halt progressive demyelination in two boys with cerebral adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Flow cytometry of third‐party mesenchymal stem cells (MSCs). Shown are representative histograms for MSC‐related cell surface markers on the infused cell product prior to administration. Gating was set to exclude debris and doublets prior to specific marker discrimination. Red histograms indicate the specific antibody compared with the isotype control in blue. The bottom three histograms show markers typically absent on MSCs. CD19 was also tested and was not expressed by MSCs (data not shown)\n\nFigure 2: Figure 2. Magnetic resonance images (MRIs) before and after mesenchymal stem cells (MSCs). A, Patient D.H. MRI was 2 months following the third intrathecal (IT) MSC dose. B, Patient A.S. MRI was 1 month after the dose of IT MSCs"
      }
    ]
  },
  {
    "id": "PMC7186177_multi",
    "image": [
      "images/PMC7186177-f1.png",
      "images/PMC7186177-f2.png",
      "images/PMC7186177-f3.png",
      "images/PMC7186177-f4.png",
      "images/PMC7186177-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Deletion of fatty acid transport protein 2 (FATP2) in the mouse liver changes the metabolic landscape by increasing the expression of PPARα-regulated genes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Roles of FATP2 in fatty acid transport and very-long-chain fatty acid activation. A, FATP2 functions at the plasma membrane in concert with a long-chain acyl-CoA synthetase (ACSL) to couple fatty acid transport and activation of long-chain fatty acids (LCFA; e.g. palmitate (PA) and oleate (OA)), resulting in LCFA-CoA, which enters downstream lipid metabolic pathways (e.g. fatty acid oxidation, fatty acid storage (triglycerides (TAG)), and lipid synthesis). B, FATP2 also functions as a very long chain acyl-CoA synthetase (Acsvl2) in the endoplasmic reticulum, where it activates VLCFAs (arachidonic acid (AA), docosahexaenoic acid (DHA), and eicosapentaenoic acid (EPA)). The resulting VLCFA-CoA enters downstream lipid metabolic pathways required for membrane integrity (shown as yellow acyl chains) and precursors for bioactive lipid synthesis.\n\nFigure 2: Figure 2. Fatp2−/− mice gain less weight and have attenuated fatty acid absorption compared with the control mice (fed a standard chow diet). A, weight gain of mice groups over the course of 6 weeks (beginning at 5 weeks of age until sacrifice at 11 weeks of age). Shown are control males (black) and females (gray) and Fatp2−/− males (red) and females (blue); weight (g) ± S.D. (error bars) (n = 7); *, p ≤ 0.05 using Student's t test. B, quantification using box plots of weight gain over 6 weeks. Shown are control males (black) and females (gray) and Fatp2−/− males (red) and females (blue); weight gain (g) ± S.D. (n = 7); *, p ≤ 0.05 using Student's t test. C, deletion of FATP2 attenuates fatty acid absorption. Male mice (control (gray) and Fatp2−/− (black)) were treated with 500 mg/kg [13C]oleate and then circulating blood levels of [13C]oleate measured after 2 and 6 h. Data are relative to 12C18:1 levels ± S.D. (n = 4); **, p ≤ 0.01 using Student's t test.\n\nFigure 3: Figure 3. WT and Fatp2−/− liver transcriptomes are distinguishable. A, PCA plots of gene counts from the liver transcriptomes from control (red) and Fatp2−/− (green) male (left) and female (right) mice using unsupervised clustering (n = 4). B, volcano plots of genes from Fatp2−/− male (left) and female (right) liver tissue generated using a log2 -fold change and corrected p values of the genes in the male and female RNA-Seq data. The genes in red meet both the p value cut-off (p ≤ 0.05) and log2 -fold change cut-off (≥1.5); genes in blue meet the p value cut-off but not log2 -fold change; and those in gray do not meet either the p value or the log2 -fold change threshold. (n = 4). C, up-regulated DEGs in the liver from male (yellow) and female (blue) Fatp2−/− mice with 52 in common. D, down-regulated DEGs in the liver from male (yellow) and female (blue) Fatp2−/− mice with seven in common.\n\nFigure 4: Figure 4. DEGs in fatty acid transport, trafficking and oxidation, lipid droplet biogenesis, and peroxisome biogenesis correlate with increased size of lipid droplets in the Fatp2−/− liver. A, increased expression of genes (red) encoding proteins involved in fatty acid transport, trafficking, β-oxidation (mitochondrial (left) and peroxisomal (right)), and peroxisome biogenesis pathways. B, DEGs enriched in the pathways leading to triglyceride and lipid droplet biogenesis. For A and B, DEGs increased in expression are colored in red; for genes noted with superscript m or f, expression changed only in male or female mice, respectively; genes noted in black were detected but were unchanged between the control and Fatp2−/− mice. C, control (left) and Fatp2−/− (right) liver sections stained with Oil Red O; images are representative of n = 4 mice. D, quantification of Oil Red O staining (left, indicative of lipid droplets) as noted in Fig. 4C using ImageJ software; data are ± S.D. (error bars) (n = 4). Quantification of neutral lipids (right) as fatty acid methyl esters from control (gray) and Fatp2−/− (black) liver (μg of FA/mg of tissue ± S.D. (n = 4); *, p ≤ 0.05 from Student's t test.\n\nFigure 5: Figure 5. Fatty acid synthesis pathways enriched in DEGs of the Fatp2−/− liver. A, DEGs in de novo fatty acid biosynthesis and fatty acid elongation. B, DEGs in essential fatty acid (C18:2 and C18:3) metabolism. For A and B, DEGs increased in expression are colored in red; for genes noted with superscript m, expression changed only in male mice; the genes noted in black were detected but were unchanged between the control and Fatp2−/− mice."
      }
    ]
  },
  {
    "id": "PMC7186177_multi_2",
    "image": [
      "images/PMC7186177-f6.png",
      "images/PMC7186177-f7.png",
      "images/PMC7186177-f8.png",
      "images/PMC7186177-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Deletion of fatty acid transport protein 2 (FATP2) in the mouse liver changes the metabolic landscape by increasing the expression of PPARα-regulated genes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Retinol metabolic pathway is enriched in DEGs of the Fatp2−/− liver. DEGs increased or decreased in expression are colored in red and green, respectively; for genes noted with superscript f, expression changed only in female mice.\n\nFigure 7: Figure 7. Arachidonic acid metabolic pathway is enriched in DEGs of the Fatp2−/− liver. DEGs increased or decreased in expression are colored in red and green, respectively; for genes noted with superscript m, expression changed only in male mice; the genes noted in black were detected but were unchanged between the control and Fatp2−/− mice. The acyl chains colored in yellow indicate arachidonic acid (AA) in the membrane that is released by Pla2. Metabolites measured are italicized, showing those with increased (red), decreased (green), or unchanged (black) levels.\n\nFigure 8: Figure 8. Genes regulated through PPARα are increased in Fatp2−/− mice. All PPARα-regulated genes detected in the transcriptomic data set are noted and clustered into pathways related to fatty acid trafficking, fatty acid oxidation, fatty acid biosynthesis, retinol and arachidonic acid metabolism, and peroxisome proteins. Genes noted in red have increased expression in the Fatp2−/− mice; those in black were detected but were unchanged when compared with the isogenic controls. Superscript m or f indicates that the expression of the noted gene was increased only in male or female liver, respectively.\n\nFigure 9: Figure 9. The Fatp2−/− mouse liver has altered total fatty acid and eicosanoid levels. A, total fatty acids (mean ± S.D. (error bars), μg/mg) in male control (gray) and Fatp2−/− (black) liver; n = 4; *, p ≤ 0.05 using Student's t test. B, total eicosanoid levels in male control (gray) and Fatp2−/− (black) livers relative to the internal standard, d6-20-HETE ± S.D. (n = 5); *, p ≤ 0.05 from Student's t test."
      }
    ]
  },
  {
    "id": "PMC7210666_multi",
    "image": [
      "images/PMC7210666-f1.png",
      "images/PMC7210666-f2.png",
      "images/PMC7210666-f3.png",
      "images/PMC7210666-f4.png",
      "images/PMC7210666-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Dental anomalies as a possible clue of 1p36 deletion syndrome due to germline mosaicism: a case report\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Patient 1. Dysmorphic features: midfacial hypoplasia, bilateral epicanthic fold, upslanting palpebral fissures, palpebral ptosis, nasal bone hypoplasia, dental occlusion of Class III\n\nFigure 2: Figure 2. Patient 1. a Dental anomalies. Note the atypical shape of the permanent upper incisors (peg- shaped and notched; white arrows) and the areas of enamel demineralization (white and yellow-brown spots diffused and the lack of enamel –pitting-) on the vestibular surface of the inferior central incisor (white arrow). b Orthopantomography X-Ray (OPT-XR). The dental agenesis of the two upper canines was identified (canine position is indicated with stars) together with the dystopic eruptive direction (distoangulation) of the still included upper second premolar (red arrow). The germs of the wisdom teeth were not visible\n\nFigure 3: Figure 3. Patient 2. Dysmorphic features: bilateral epicanthus, low-set ears, severe midfacial hypoplasia, flat occiput\n\nFigure 4: Figure 4. Patient 2. a Dental anomalies. Note the diffused demineralization (white and brown spots; white arrows). b Orthopantomography X-Ray (OPT-XR). Dental agenesis of the two upper canines was identified (canine position is indicated with stars). The suspected shape anomaly of the upper incisors is indicated with red arrows\n\nFigure 5: Figure 5. Oligonucleotides array profile of our patients shows 1p36.32 deletion of 2,3 Mb. OMIM genes disease-causing inside the critical region 1p36.32, according UCSC: PEX10, PRDM16, CEP104"
      }
    ]
  },
  {
    "id": "PMC7217479_multi",
    "image": [
      "images/PMC7217479-f1.png",
      "images/PMC7217479-f2.png",
      "images/PMC7217479-f3.png",
      "images/PMC7217479-f4.png",
      "images/PMC7217479-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ehrlichia chaffeensis TRP120-mediated ubiquitination and proteasomal degradation of tumor suppressor FBW7 increases oncoprotein stability and promotes infection\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A. Confocal immunofluorescent microscopy demonstrating colocalization of FBW7 (red) and E. chaffeensis TRP120 (green) in THP-1 cell nuclei at 24 h post-infection (hpi). Nucleus was stained with DAPI (blue). Confocal immunofluorescent microscopy was performed to further demonstrate FBW7 (red) did not colocalize with E. chaffeensis Dsb (green), suggesting specificity of TRP120-FBW7 nuclear colocalization. Colocalization intensity was determined by Product of the Differences from the Mean (PDM) calculation and shown in the heatmap-like image. The brightest points of colocalization in the PDM image were quantified with Mander’s overlap coefficients (MOC), which ranges between 0 (no colocalization) to 1 (strong colocalization). A table showing MOC values of the highlighted regions of interest shown in the E. chaffeensis-infected cells (top). In addition, a pie chart was generated from MOC values of multiple regions showing colocalization of TRP120 and FBW7 in the nucleus, where five images (n = 5) containing a total of 33 regions (n = 33) were analyzed, where 58% have very strong colocalization and 33% have strong colocalization. B. Co-immunoprecipitation was performed to demonstrate direct interaction between TRP120 and FBW7. THP-1 cells were infected with cell-free E. chaffeensis and then harvested at 24, 48, and 72 hpi. Anti-TRP120 and anti-FBW7 antibodies were first combined with whole cell lysates for coupling to form antigen-antibody complex. A/G coated magnetic beads were added to the antigen-antibody complex to allow binding and pull down of either TRP120 or FBW7. Western immunoblots were probed with anti-FBW7 or anti-TRP120 (n = 3). C. Schematic representation of truncated FBW7 mutant constructs (His-tagged) generated for ectopic expression experiments. D. HeLa cells were co-transfected with FL-FBW7 or FBW7 truncated constructs, and TRP120 to examine colocalization by immunofluorescent microscopy. Colocalization was not observed between TRP120 (green) and FBW7-N (red), but strong colocalization between TRP120 and both FBOX and WD40 domains of FBW7 was detected and colocalization strength shown by Mander’s coefficients of 0.935 and 0.971, respectively. This figure was representative of three experiments (n = 3) with technical replicates (n = 2).\n\nFigure 2: Figure 2. A. Confocal immunofluorescent microscopy was performed to observe colocalization of TRP120 (green) with FBW7 (red) and the temporal changes in FBW7 levels during E. chaffeensis infection. DAPI was used for nuclear staining (blue). In uninfected cells, FBW7 was primarily observed in the nucleus but was also detectable in the cytoplasm. Day 1 post-infection (pi), FBW7 was detected only in the nucleus and colocalization with TRP120 was observed. By day 2 pi, FBW7 levels decreased ~50% and ~70%, respectively compared to uninfected controls. TRP120 levels decreased in nucleus and increased TRP120 was associated with the morulae 48 and 72 hpi. Confocal immunofluorescent microscopy confirming E. chaffeensis infection at day 1 pi (presented in the right panel separated by line) with cytoplasmic E. chaffeensis Dsb (red) detection, also demonstrated nuclear expression of TRP120 (green). For each time point, 3 fields of 30 cells were analyzed (n = 30). B. FBW7 and TRP120 fluorescent intensities from the confocal immunofluorescent microscopy (A) were calculated using image J and graphically demonstrated significant nuclear reduction in FBW7 intensity (normalized to total fluorescent intensity) at D2 (p<0.05) and D3 pi (p<0.05) with presence of nuclear TRP120. A reduction of nuclear TRP120 was also observed at D2 (p<0.05) and D3 pi (p<0.005) compared to D1 pi, while there was a significant increase of TRP120 in the morulae (p<0.0005 for both time points). C. Western immunoblots of whole cell lysates harvested from THP-1 cells infected with cell-free E. chaffeensis for 24, 48 and 72 h with uninfected (ctrl) cells harvested at the same time points identified. Significant decrease of FBW7 level was detected by 72 hpi compared to ctrl (p<0.05). n = 4. D. Quantitative RT-PCR analysis of FBW7 expression was performed using cDNA from infected THP-1 cells at 24, 48 and 72 hpi shows a significant increase in FBW7 expression during infection at 48 and 72 hpi compared to uninfected control (p<0.005). GAPDH was used as endogenous control. The analysis was performed from data collected from 3 experiments and technical replicates.\n\nFigure 3: Figure 3. A. Western immunoblots demonstrating stabilization and upregulation of FBW7 downstream targets: Notch1 intracellular domain (NICD), cMYC, phospho-Jun (p-Jun) and MCL1. Western immunoblots of NICD, cMYC, p-Jun, total c-Jun and MCL1 levels 24, 48 and 72 hpi. GAPDH was used as loading control, and TRP120 to confirm E. chaffeensis infection (n = 3). Significant temporal increases in NICD, cMYC, p-Jun and MCL1 levels were observed during E. chaffeensis infection. Densitometry of Western immunoblots (A) was performed to determine levels of each protein using Image J comparing each infected time point to uninfected. Phospho-Jun was additionally normalized to the levels of total c-Jun, then normalized again to the levels of GAPDH (* p<0.05, ** p<0.005, and *** p<0.0005). B. Western immunoblots of uninfected HeLa cells transfected with catalytic-inactive TRP120 (TRP120-C520S) to demonstrate protein levels of NICD, phospho-Jun, MCL1 and cMYC. Densitometry values were measured in ImageJ and plotted (right) to determine the levels of oncoprotein in uninfected cells transfected with TRP120-C520S to be statistically insignificant (ns) compared to control cells (n = 3). C. Western immunoblots demonstrating significant increase of protein levels of NICD, p-Jun, MCL1 and cMYC in both uninfected and infected THP-1 cells with FBW7-KD, compared to uninfected, scrambled siRNA controls (n = 3). Densitometry values were measured in ImageJ and plotted (right), and statistical analysis was calculated for oncoprotein levels in siFBW7 treated cells compared to control (* p<0.05, ** p<0.005, and *** p<0.0005).\n\nFigure 4: Figure 4. A. Immunoprecipitation of K48-Ub FBW7 from uninfected and E. chaffeensis-infected THP-1 cells demonstrating increased levels of FBW7 K48-Ub. Lysates were treated with NEM (N-ethylmaleimide, equal mass amount to whole cell lysates used) and bortezomib (10ng/ml, 10 h) to prevent deubiquitination and proteasome degradation. Anti-K48-Ub antibody was used to pull down all K48-Ub conjugated proteins. Basal levels of K48-Ub FBW7 at ~200 kDA are observed indicating FBW7 undergoes K48-Ub as a mechanism of protein regulation and turnover. Densitometry values of K48-Ub-FBW7 bands were denoted on top of each band for every time point, and a p<0.05 significance comparing 48 hpi to uninfected control (0 hpi) was calculated from three experiments (n = 3). B. Western immunoblots demonstrating the effect of bortezomib (bort, 26S proteasome inhibitor) on FBW7 during infection. Whole cell lysates were obtained from both bort-treated (10ng/ml, 10 h) and untreated groups infected with cell-free E. chaffeensis and uninfected controls at 24, 48 and 72 hpi. Uninfected cells were harvested at the same time points (24, 48 and 72 hpi) with only a single time point (ctrl) shown in the figure as significant differences were not observed among uninfected cells. FBW7 levels remained unchanged during infection in the bort-treated group; however, there was a temporal reduction of FBW7 levels in untreated group, demonstrating FBW7 proteasomal degradation during infection. C. Densitometry of Western immunoblots (B) performed using image J. Statistical analysis was done by comparing data from infected cells to control cells at respective time points (n = 3). A p<0.05 significance was determined for FBW7 level at 72 hpi in the untreated group compared to uninfected control in the same group.\n\nFigure 5: Figure 5. A. Levels of FBW7 decrease in HeLa cells ectopically expressing TRP120-GFP at 0, 24, and 48 hours post transfection (hpt). Densitometry values of FBW7 for each time point were denoted above respective bands (ctrl: 1.4 ±0.03; 24 hpt: 1.3±0.08; 48 hpt: 0.5±0.09), with Significantly (p<0.05) decreased levels of FBW7 were detected at 48 hpt with TRP120 compared to control (n = 3). B. HeLa cells were transfected with TRP120 WT and HECT E3 ligase catalytic mutants (TRP120-FL-C520S and TRP120-TR-C-C520S). Increased degradation of endogenous FBW7 was detected in TRP120-WT compared TRP120-C520S mutants lacking Ub ligase function. Densitometry values of FBW7 for each sample group were labeled above respective bands (TRP120-FL-WT: 0.1±0.02; TRP120-FL-C520S: 0.3±0.04; TRP120-TR-C-WT: 0.1±0.004; TRP120-TR-C-C520S: 0.3±0.03), with p<0.05 significance for both TRP120 transfection groups (TRP120-FL and TRP120-TR-C) comparing levels of FBW7 in cells transfected with catalytic-inactive TRP120 mutant (C520S) to wildtype TRP120 (WT) (n = 3). C. In vitro ubiquitination of native FBW7 by E. chaffeensis rTRP120 using anti-FBW7 and anti-K48 antibodies for detection. Increased FBW-Ub was detected at ~200 kDa in the presence of rTRP120 compared to controls without TRP120. K48 Ub was also detected on FBW7-Ub in the presence of rTRP120 indicating TRP120 directly ubiquitinates FBW7 with K48-Ub chains. Densitometry values of both FBW7-Ub (FBW7+TRP120: 4.1±0.17; FBW7-TRP120: 1.0±0.02) and K48-Ub (FBW7+TRP120: 4.6±0.06; FBW7-TRP120: 1.0±0.01) were denoted above each bands, with p<0.05 significance comparing levels of either FBW7-Ub or K48-Ub in the presence of rTRP120 to the absence of rTRP120 as E3 ligase (n = 4)."
      }
    ]
  },
  {
    "id": "PMC7217479_multi_2",
    "image": [
      "images/PMC7217479-f6.png",
      "images/PMC7217479-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Ehrlichia chaffeensis TRP120-mediated ubiquitination and proteasomal degradation of tumor suppressor FBW7 increases oncoprotein stability and promotes infection\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A. iRNA knockdown of FBW7 in E. chaffeensis-infected THP-1 cells at 24 and 48 hpi. Scrambled siRNA was used as RNAi control. Western immunoblot (right) demonstrated ~90% knockdown (KD) of FBW7, densitometry values were labeled above each band. Cells were harvested for qPCR to assess changes in E. chaffeensis infection. For all the data points from both uninfected and infected KD cells, the data was first normalized to cells transfected scrambled siRNA (infected and uninfected, respectively). Then, the infected group was normalized to uninfected group to determine the fold change. A significant increase (3-fold) in E. chaffeensis load was detected in FBW7-KD cells (p≤0.05). B. Overexpression of FBW7 was achieved by transfecting HeLa cells with pcDNA3.1+/C-(K) DYK-FBW7 (denoted as pcDNA-FBW7 in the figure), and negatively impacted E. chaffeensis infection (p≤0.005) in infected HeLa cells. Quantitative PCR analysis was performed similarly to panel A. Western Immunoblot (right) confirmed ectopic overexpression of FBW7 and quantitated with densitometry values as denoted above each band. For both panels A and B, the data shown is representative of 3 experiments (n = 3) with technical replicates (n = 3).\n\nFigure 7: Figure 7. (1) Infectious dense-cored E. chaffeensis expressing TRP120 on the surface enter host monocytes through receptor-mediated phagocytosis and replicates in a cytoplasmic vacuoles that do not fuse with lysosomes; (2) TRP120 is secreted via type-1 secretion system into host cell within 3 h of entry and translocates into the host nucleus; (3) TRP120 binds to phosphorylated FBW7 homodimer in trans conformation and ubiquitinates with K48-Ub chains; (4) FBW7-K48-Ub is then degraded by the 26S proteasome, presumably in the nucleus; (5) TRP120-mediated degradation of FBW7 leads to stabilization and accumulation of downstream oncoprotein targets including NICD, c-Jun, MCL1 and cMYC; (6) Pro-survival oncoproteins activate downstream gene transcription to delay host cell apoptosis to promote E. chaffeensis infection."
      }
    ]
  },
  {
    "id": "PMC7261758_multi",
    "image": [
      "images/PMC7261758-f1.png",
      "images/PMC7261758-f2.png",
      "images/PMC7261758-f3.png",
      "images/PMC7261758-f4.png",
      "images/PMC7261758-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Vorinostat in the acute neuroinflammatory form of X‐linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. ABCD2 gene expression remains at low levels compared to ABCD1 after differentiation using GM‐CSF or M‐CSF in human monocyte‐derived macrophages. Monocytes were isolated from leukocyte concentrates derived from healthy donors by plasmapheresis and were differentiated toward macrophages with 50 ng/mL GM‐CSF or M‐CSF for 7 days. Absolute mRNA levels were determined by RT‐qPCR using standard concentration curves of plasmids containing (A) ABCD2 and (B) ABCD1 and for normalization RACK1 cDNA. Each data point represents a replicate (well) from three healthy donors (controls 1–3). For statistical analysis one‐way ANOVA and Sidak’s multiple comparison test were used. ****P < 0.0001, ns = not significant.\n\nFigure 2: Figure 2. Comparison of activating histone modifications indicates a cell type‐specific repressed state of the ABCD2 promoter in monocytes and macrophages. ChIP‐Seq data of activating histone modifications retrieved from the International Human Epigenome Consortium (IHEC) were compared in human monocytes (dark grey), macrophages (orange) and T cells (red) to analyse the mechanism of differential ABCD2 expression, which is high in T cells but barely detectable in monocytes/macrophages. (A) An active promoter is characterized by high trimethylation of histone 3 lysine 4 (H3K4me3) and acetylation (ac) of H3K27. In addition, active expression of a gene is associated with high H3K36me3 marks at intragenic regions. The vice versa pattern could indicate a cell type‐specific, repressed state as indicated in the scheme. (B) Nucleosome‐free regions of DNA are easily accessible for transcription factors and the RNA‐polymerase II and, thus, depending on flanking histone modifications can be linked with an active or poised promoter. Accordingly, the analysis of ChIP‐Seq data reveals the associated characteristic peak‐valley‐peak pattern of H3K4me3 and H3K27ac at a promoter linked to active gene expression. However, a peak spanning the promoter region is associated with a repressed state, while low levels of these modifications typically indicate an inactivated state. (C, D) In the upper panel, a 30‐kb region (GRCh37; Chr 12: 40,000,000–40,031,000) surrounding the ABCD2 promoter is depicted. Within the promoter region (marked with vertical lines) data from the consortia Roadmap (C) and DEEP (D) show a typical peak‐valley‐peak pattern for H3K4me3 and H3K27ac in T cells (red) indicating an active promoter. In monocytes (dark grey) and macrophages (orange), these modifications span a broader region around the promoter. The bottom panels show elevated H3K36me3 marks at intragenic regions of ABCD2 in T cells, indicating active expression, but barely detectable signals in monocytes/macrophages in datasets from both consortia (C, D). n = number of tracks per cell type.\n\nFigure 3: Figure 3. Vorinostat treatment efficiently induces ABCD2 expression, improves β‐oxidation and accumulation of the VLCFA C26:0 in healthy controls and X‐ALD macrophages. (A) Macrophages (M‐CSF) from three healthy donors (Control 4, 5, and 6) were differentiated with 50 ng/mL M‐CSF for 7 days, then treated with 1, 3, and 5 µmol/L Vorinostat for 24 h and absolute ABCD2 mRNA levels were determined and normalized to HPRT1. (B) Macrophages from three healthy donors were differentiated as described in (A) and further activated by 100 ng/mL IL‐4 to obtain activated anti‐inflammatory macrophages. In the presence of IL‐4, macrophages were treated with 2.5 µmol/L Vorinostat (n = 3) or 5 µmol/L Vorinostat (n = 1) for 48 h prior to measuring C26:0 degradation levels via β‐oxidation. The obtained β‐oxidation rates for C26:0 (pmol/min/mg protein) of the added cells are depicted as fold increase versus the mean of DMSO‐treated controls (n = 3). (C) A dose–response curve for the β‐oxidation of C26:0 was generated with 1, 2.5, and 5 µmol/L Vorinostat in macrophages (as described in (B)) from two X‐ALD patients (AMN 1 and AMN 2). The measured activities are shown as % of the DMSO‐treated healthy control (Control 10) value. (D) Macrophages (M‐CSF) from X‐ALD patients (n = 3) were stimulated with 2.5 µmol/L Vorinostat for 5 days and the levels of C26:0‐LPC (pmol/ mg protein) were measured and compared to DMSO‐treated (n = 3) or untreated healthy control (n = 3) macrophages respectively. The statistical tests, one‐way ANOVA and Dunnett’s multiple comparison, were used to analyse induction of ABCD2 in macrophages from controls (n = 3). ****P < 0.0001.\n\nFigure 4: Figure 4. Vorinostat interferes with the differentiation of monocytes to macrophages in vitro and shows differential anti‐inflammatory effects in LPS‐activated X‐ALD macrophages. (A and B) The ability of human blood‐derived monocytes to differentiate toward macrophages when applying M‐CSF in the presence of 2.5 µmol/L Vorinostat was analysed in control macrophages using two replicates from two different donors. For the differentiation analysis, we determined (A) the mean cell size after 7 days and (B) the adherence to the cell culture plate after 3, 5, and 7 days of cultivation. (C–E) To assess whether Vorinostat can efficiently reduce the elevated pro‐inflammatory gene expression of IL12B and TNF in X‐ALD, macrophages (M‐CSF) from healthy donors and X‐ALD patients were stimulated with 100 ng/mL LPS for 24 h. In the presence of LPS, macrophages (Ctrl, n = 4 or n = 6; AMN, n = 7) were treated with 2.5 µmol/L Vorinostat or its solvent DMSO before the mRNA levels of ABCD2 (C), and the pro‐inflammatory cytokines IL12B (D) and TNF (E) were determined by RT‐qPCR and normalized to HPRT1. In addition, supernatants of stimulated macrophages were harvested and IL12p40 secretion was measured by ELISA (D). The efficacy of ABCD2 induction in control and X‐ALD macrophages was analysed by one‐way ANOVA and Sidak’s multiple comparisons test. (D and E) For comparison purposes, the levels of LPS‐treated controls were set to 100% for each experiment and the Vorinostat‐induced changes of pro‐inflammatory gene expression in X‐ALD were subjected to statistical analysis applying the nonparametric Friedman test and Dunn’s multiple comparison test. The error bars in panel (A) represent SD. *P < 0.05, **P < 0.01, ****P < 0.0001, ns = not significant.\n\nFigure 5: Figure 5. Vorinostat treatment withdrawal was required due to the severity of induced thrombocytopenia in two of three treated CALD patients who showed advanced lesions on brain MRIs. (A–C) The brain MRIs (T1‐ or T2‐weighted as indicated) obtained from three patients with advanced CALD with assigned Loes scores of 20, 20, and 18 are shown before they received 100–400 mg/day Vorinostat. (D–F) Vorinostat dose (dashed line) and platelet (thrombocyte) counts (solid line) are depicted for each patient during the treatment period. The arrow indicates the treatment stop for CALD patient 2 and 3."
      }
    ]
  },
  {
    "id": "PMC7261758_multi_2",
    "image": [
      "images/PMC7261758-f6.png",
      "images/PMC7261758-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Vorinostat in the acute neuroinflammatory form of X‐linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Medication with Vorinostat reversed intrathecal immunoglobulin synthesis and the disturbed BCSFB/BBB permeability but did not stop disease progression in a patient with advanced CALD. (A) As shown in the scheme, blood serum and lumbar puncture‐derived CSF were collected from patient CALD1 at the start of treatment with Vorinostat (day 0) and after 80 days of treatment and processed for analysis of albumin (Alb) and Ig levels. (B) The values of the VLCFA C26:0, measured by GC–MS, in the plasma from patient CALD1 are depicted before and during Vorinostat treatment and were normalized to the fatty acid C22:0 or are shown as mg per L plasma. The grey area indicates the normal range during physiological conditions. (C‐D) The ratios (CSF/serum level) of IgG, IgA, and IgM are plotted against the CSF/serum ratio of albumin (red dot, patient CALD1) on logarithmic scales in the Reiber Scheme, (C) before (−) and (D) after (+) Vorinostat treatment. The vertical line indicates the age‐dependent threshold for Alb permeability under physiological conditions on the x‐axis. The dashed lines indicate the percentage of intrathecal synthesis for each Ig class on the y‐axis. (E) An additional brain MRI (#2, T2‐weighted) was obtained 197 days after starting Vorinostat medication and the assigned Loes score of 26 indicated progression of the inflammatory demyelination.\n\nFigure 7: Figure 7. Perivascular B cell accumulation in CALD brain lesions. The light microscopy views depict immunohistochemical staining (brown) of (A) CD20+ B cells and (B) IgG+ plasma B cells (arrows) accumulating in the perivascular space in areas of active demyelinating lesions in postmortem brain tissue of a CALD patient. Perivascular CD20+ B cells were quantified in four untreated CALD cases (n = 4) and compared to controls lacking any signs of brain inflammation (n = 10). An occasional (very rare) parenchymal cell is shown in the magnified view (top right panel). For statistical analysis, the nonparametric Mann–Whitney test was performed. ***P < 0.001."
      }
    ]
  },
  {
    "id": "PMC7274077_multi",
    "image": [
      "images/PMC7274077-f1.png",
      "images/PMC7274077-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"BK Channel Dysfunction in Diabetic Coronary Artery: Role of the E3 Ubiquitin Ligases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A schematic figure of the ubiquitin proteasome system. Initially, a single free ubiquitin was activated by E1 in an ATP-dependent manner and then the activated monoubiquitin molecule is transferred to a cysteine residue of the E2 enzyme, which is subsequently recruited into the E3 ligases. Working with a specific E3, E2 transferred one or more ubiquitin moieties sequentially to form ubiquitin chains to the substrate protein. Finally, the proteasome system can target the ubiquitinated substrate protein for degradation.\n\nFigure 2: Figure 2. Proposed signaling pathways underlying the BK channel downregulation through E3 ubiquitin ligases in coronary smooth muscle cells. In diabetes, increased PKC stimulation overproduced ROS, which inhibits the PI3k/Akt pathway. Decreased Akt phosphorylation suppresses FOXO-3a and then upregulates FBXO expression. Nrf2 is downregulated in diabetic coronary smooth muscle cells. Decreased Nrf2 upregulates NF-κB and MuRF1. FBXO and MuRF1 are muscle-specific E3 ubiquitin ligases, which enhance the ubiquitination and the degradation of the BK β1-subunit. The coronary vasoconstriction in diabetes is increased due to the impaired BK channel expression and function. PKC, protein kinase C; ROS, reactive oxygen species; PI3k, phosphatidylinositide 3-kinases; FOXO-3a, the forkhead box O family transcription factor-3a; FBXO, F-box protein; Nrf2, nuclear factor E2-related factor 2; NF-κB, nuclear factor kappa B; MuRF1, muscle RING finger protein 1."
      }
    ]
  },
  {
    "id": "PMC7290671_multi",
    "image": [
      "images/PMC7290671-f1.png",
      "images/PMC7290671-f2.png",
      "images/PMC7290671-f3.png",
      "images/PMC7290671-f4.png",
      "images/PMC7290671-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Impairment of Proteasome and Autophagy Underlying the Pathogenesis of Leukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Spatial and temporal distribution of ubiquitin aggregates in the brain of twitcher mice. Distribution of ubiquitin aggregates in different regions of the twitcher (Twi) brain at ages 21 to 42 days. The twitcher brain and wild-type (WT) brain were immuno-stained with anti-ubiquitin (in green) and anti-PLP (in red), respectively, and nuclei were counterstained with DAPI (in blue). Scale bars: 200 μm.\n\nFigure 2: Figure 2. Progressive accumulation of p62 aggregates in the brain of twitcher mice. Distribution of p62 aggregates in different regions of the twitcher (Twi) brain at ages 21 to 42 days. The twitcher brain and wild-type (WT) brain were immuno-stained with anti-p62 (in green) and anti-PLP (in red), respectively, and nuclei were counterstained with DAPI (in blue). Scale bars: 200 μm.\n\nFigure 3: Figure 3. Accumulation of ubiquitin/p62 aggregates in oligodendrocytes and neurons. Sections of twitcher brain were double labeled with anti-ubiquitin/anti-p62 and anti-NeuN (neuron)/anti-PLP (oligodendrocytes)/anti-calbindin (Purkinje cells)/anti-GFAP (astrocyte)/anti-Iba1 (microglia)/anti-LAMP1 (lysosome), respectively, and nuclei were counter-stained with DAPI (blue). Scale bars: 10 μm.\n\nFigure 4: Figure 4. Increased autophagic flux in twitcher brain. a Western blot analysis of the total LC3-II, p62, and ubiquitin content in brain stems from wild-type (WT) and twitcher (Twi) mice at ages 21 days, 28 days, 35 days, and 42 days. Soluble fraction was analyzed and β-actin (actin) was used for the loading control. b, c, d Quantification of soluble LC3-II (b), p62 (c), and ubiquitin (d). Values are expressed as mean ± S.D. (n = 3). Statistical significance ***p < 0.001.\n\nFigure 5: Figure 5. Defective autophagy and ubiquitin-proteasome system in twitcher brains. a: Western blot analysis of the total LC3-II, p62, and ubiquitin content in brain stems from wild-type (WT) and twitcher (Twi) mice at ages 21 days, 28 days, 35 days, and 42 days. Insoluble fraction was analyzed and histon-H3 (H3) was used for the loading control. b, c, d Quantification of insoluble LC3-II (b), p62, (c) and ubiquitin (d). Interaction between insoluble p62 and ubiquitin was verified by immunoprecipitation analysis (e). Values are expressed as mean ± S.D. (n = 3). Statistical significance, **p < 0.01, ***p< 0.001."
      }
    ]
  },
  {
    "id": "PMC7290671_multi_2",
    "image": [
      "images/PMC7290671-f6.png",
      "images/PMC7290671-f7.png",
      "images/PMC7290671-f8.png",
      "images/PMC7290671-f9.png",
      "images/PMC7290671-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Impairment of Proteasome and Autophagy Underlying the Pathogenesis of Leukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Progressive astrocytosis and demyelination in twitcher brain. (a) Western blot analysis of the total MBP and GFAP content in brain stems from wild-type (WT) and twitcher (Twi) mice at ages 21 days, 28 days, 35 days, and 42 days of age. b, c Quantification of MBP (b) and GFAP (c). β-actin (actin) was used for the loading control. Values are expressed as mean ± S.D. (n = 3). Statistical significance, **p< 0.01, ***p < 0.001.\n\nFigure 7: Figure 7. Dose- and time-dependent cytotoxicity of psychosine upon MO3.13 cells. (a) Western blot analysis of total LC3-II and p62 in MO313 cells treated with different concentration of psychosine (psy) for 24 h. β-actin (actin) was used for the loading control. (b,c,d) Quantification of total LC3-II (b) and p62 (c) and cell viability (d). e Western blot analysis of total LC3-II and p62 in MO313 cells treated with 20 µM psychosine for 72 h. (f,g,h) Quantification of total LC3-II (f) and p62 (g) and cell viability (h). Values are expressed as mean ± S.D. (Western blot, n = 3; Viability, n = 6). Statistical significance *p < 0.05, **p < 0.01, ***p < 0.001. MO313 cells without treatment are labeled as a control group (C).\n\nFigure 8: Figure 8. Autophagy inhibition increases accumulation of insoluble p62 and ubiquitin. (a) Western blot analysis of the total LC3-II, p62, and ubiquitin in MO3.13 cells treated without (control: C)/with psychosine (Psy) for 72 h concomitant with/without chloroquine (CQ) for the last 24 h. Soluble and insoluble fractions were analyzed. β-actin (actin) and histon-H3 (H3) were used for the loading control in soluble and insoluble fractions, respectively. (b–d) Quantification of soluble LC3-II (b), p62 (c), and ubiquitin (d). (e–g) Quantification of insoluble LC3-II (e), p62 (f), and ubiquitin (g). Values are expressed as mean ± S.D. (n = 3). Statistical significance * p < 0.05, **p < 0.01, *** p < 0.001 in comparison to control (C). C/CQ vs. Psy, or Psy/CQ, # p < 0.05, ## p< 0.01,###p < 0.001. Psy vs. Psy/CQ, ++p< 0.01, +++p< 0.001.\n\nFigure 9: Figure 9. Accumulation of autolysosomes and p62 aggregates by impaired autophagic flux. (a) Autolysosome was determined by the colocalization of the Cyto-ID fluorescence and LysoTracker Red (LTR) in MO3.13 cells treated with/without psychosine (Psy) concomitant with/without chloroquine (CQ) and counter-stained with Hoechst. (b) Quantification of autolysosome puncta in cells. (c) Cytoplasmic deposition of p62 and ubiquitin by chloroquine. Cells were double labeled with anti-p62 and anti-ubiquitin and counterstained with DAPI. Values are expressed as mean ± S.D. (n = 3). Statistical significance *** p< 0.001 in comparison to control (C). C/CQ vs. Psy, or Psy/CQ, ###p < 0.001. Psy vs. Psy/CQ, +++p < 0.001.\n\nFigure 10: Figure 10. Inhibition of autophagy and proteasome exacerbates accumulation of p62 and ubiquitin. (a) Western blot analysis of the total LC3-II, p62, and ubiquitin in MO3.13 cells treated without (control: C)/with psychosine (Psy) for 72 h concomitant with/without MG132 (MG) with/without chloroquine (CQ) for the last 24 h. Soluble and insoluble fractions were analyzed. β-actin (actin) and histon-H3 (H3) were used for the loading control in soluble and insoluble fractions, respectively. (b–d) Quantification of soluble LC3-II (b), p62 (c)and ubiquitin (d). (e–g) Quantification of insoluble LC3-II (e), p62 (f) and ubiquitin (g). (h) Interaction between insoluble p62 and ubiquitin was verified by immunoprecipitation analysis (h).Values were expressed as mean ± S.D. (n = 3). Statistical significance *p< 0.05, ***p < 0.001 in comparison to control (C) or C/MG. C/MG/CQ vs. Psy, or Psy/MG, or Psy/MG/CQ, #p< 0.05, ###p < 0.001. Psy vs. Psy/MG, or Psy/MG/CQ, +p < 0.05, ++p < 0.01, +++p< 0.001. Psy/MG vs. Psy/MG/CQ, ^^^p < 0.001. No statistical significance between C and C/MG."
      }
    ]
  },
  {
    "id": "PMC7290671_multi_3",
    "image": [
      "images/PMC7290671-f11.png",
      "images/PMC7290671-f12.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Impairment of Proteasome and Autophagy Underlying the Pathogenesis of Leukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Impaired autophagic flux and proteasomes enhance aggressive accumulation of autolysosomes and aggregation of p62 and ubiquitin. (a) Autolysosome was determined by the colocalization of the Cyto-ID fluorescence and LysoTracker Red (LTR) in MO3.13 cells treated with/without psychosine (Psy) concomitant with/without MG132 (MG) with/without chloroquine (CQ), and counter-stained with Hoechst. (b) Quantification of autolysosome puncta in cells. (c) Increased p62- and ubiquitin-aggregation. Cells were double labeled with anti-p62 and anti-ubiquitin, and counterstained with DAPI. Values are expressed as mean ± S.D. (n = 3). Statistical significance ***p< 0.001 in comparison to control (C) or C/MG. C/MG/CQ vs. Psy, or Psy/MG, or Psy/MG/CQ, #p < 0.05, ###p < 0.001. Psy vs. Psy/MG, or Psy/MG/CQ, +++p < 0.001. Psy/MG vs. Psy/MG/CQ,^^^p < 0.001. No statistical significance between C and C/MG.\n\nFigure 12: Figure 12. Inhibition of both proteasome and autophagy promotes cell death. MO3.13 cells treated without/with psychosine (Psy) for 72 hs concomitant with MG132 (MG) and chloroquine (CQ) in the last 24 h. (a–c) Levels of ROS (a), basal respiration (b), and cell viability (c) were quantified. Values areexpressed as mean ± S.D. (ROS, n = 3; Respiration, n = 5; Viability, n = 6). Statistical significance *p < 0.05, ***p < 0.001 in comparison to control (C). C/MG/CQ vs. Psy, or Psy/MG/CQ, # p < 0.05, ### p < 0.001. Psy vs. Psy/MG/CQ, +++ p < 0.001."
      }
    ]
  },
  {
    "id": "PMC7306489_multi",
    "image": [
      "images/PMC7306489-f1.png",
      "images/PMC7306489-f2.png",
      "images/PMC7306489-f4.png",
      "images/PMC7306489-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mild form of Zellweger Spectrum Disorders (ZSD) due to variants in PEX1: Detailed clinical investigation in a 9-years-old female\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Fundus imaging (a) and OCT scans (b) of the reported case.\n\nFigure 2: Figure 2. Pure tone audiometry (air and bone conduction) in the right ear (in red) and in the left ear (in blue) in the frequency range between 250 Hz - 8 KHz. Down-sloping audiogram with severe bilateral sensorineural hearing loss is more evident in the higher frequencies.\n\nFigure 4: Figure 4. Main dental findings of the reported case. a) High-arched palate and visible enamel hypoplasia of the first permanent upper molars; further chromatic and structural enamel alterations of the first permanent lower molars b) Orthopantomography reveal the presence of all the permanent teeth expected, lack of taurodontism, nor agenesis. The cusps of the permanent canines and premolars, particularly of the mandible, seem thinner and, presumably hypoplastic.\n\nFigure 5: Figure 5. Dermatological findings of the reported case. a) Leukonychia partialis of all fingernails sparing the distal margin of the nail plates, better magnified by onychoscopy in the right caption b) Clinically detectable banding of hair, confirmed by trichoscopy and light microscopy, showing abnormal cavities in the cortex of the hair shaft typical of pili annulati."
      }
    ]
  },
  {
    "id": "PMC7312067_multi",
    "image": [
      "images/PMC7312067-f1.png",
      "images/PMC7312067-f2.png",
      "images/PMC7312067-f3.png",
      "images/PMC7312067-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Overview of Mitochondrial E3 Ubiquitin Ligase MITOL/MARCH5 from Molecular Mechanisms to Diseases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) MITOL regulates both RIG-I-like receptor (RLR) pathway and Toll-like receptor (TLR) pathway; (B) Relativity between MITOL and cell death signaling in cancer cells.\n\nFigure 2: Figure 2. Relativity between MITOL and aging. Since MITOL gradually decrease following aging, upregulation of MITOL by a Chinese herb might be able to effect anti-aging.\n\nFigure 3: Figure 3. Regulation of mitochondrial fission and fusion factors by MITOL. (A) MITOL might have some specificity for its target; e.g., especially Drp1, such as relating to modifications, structural changes, and interactions with or without Drp1 receptors; (B) Alteration of substrate specificity for mitochondrial fusion factors in response to stress.\n\nFigure 4: Figure 4. (A) Membrane contact site (MCS) formation by MITOL-MFN2 axis. MITOL ubiquitinates mitochondrial MFN2. The ubiquitinated MFN2 enhances its GTPase activity, triggering trans-oligomerization between mitochondrial MFN2 and ER-localized MFN2 for tethering both organelles; mitochondria and the ER; (B) UPR regulation by MITOL-IRE1α axis. MITOL ubiquitinates IRE1α at ER-mitochondria contact site in unstressed and low-stressed conditions regarding the ER. The ubiquitination of IRE1α does not perturbate the oligomerization itself in response to ER stress, however, leading to short-term stabilization and smaller oligomerization. In contract, the ubiquitination by MITOL is reduced under severe or chronic ER stress, resulting in continuous oligomerization of IRE1α and apoptotic switching of IRE1α signaling."
      }
    ]
  },
  {
    "id": "PMC7318087_multi",
    "image": [
      "images/PMC7318087-f1.png",
      "images/PMC7318087-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Expanding the clinical and phenotypic heterogeneity associated with biallelic variants in ACO2\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Pedigrees of families 1–4 showing inheritance of disease‐associated variants in ACO2. Standard pedigree symbols are used; squares, male; circles, female; slush through symbols, deceased individuals. Shading indicates affected status. An arrow indicates the proband in family 1. (B) Images of P1 and P2 (brothers), and P4. Images of P1 were taken at 9 years of age and at 12 years of age for P2. Images of P4 at the age of 8 months showing severe hypotonia. (C) Typical MRI findings in patients with ACO2‐related disorders. Serial images of patients 1–5 (P1–P5) are shown top to bottom. Representative sagittal, two axial, and coronal images are shown for each patient. Noncontrast MRI of the brain of P1 was performed at 2 years and 3 months of age. MRI of the head was normal with normal myelination for age with bilateral terminal zones in the periatrial white matter. The pons and superior cerebellar vermis are slightly small for age. Brain MRI for P2 was performed at 6 years of age. Midbrain, pons, and middle cerebellar peduncles were noted to be small in size. MRI of the cerebellar hemispheres was normal, although the superior cerebellar vermis was felt to be mildly atrophic. In P3, brain MRI at 16 years of age showed mild cerebellar atrophy but was otherwise normal. In P4, brain MRI at 5 months and 11 days showed dilatation of the ventricles and prominent subarachnoid spaces, thinning of the corpus callosum, hypoplastic cerebellar vermis, and hypoplastic pons. Brain MRI in P5 was performed before 4 years of age and showed global hypomyelination and other nonspecific findings.\n\nFigure 2: Figure 2. (A) Schematic diagram of the ACO2 protein showing the mitochondrial aconitate hydratase catalytic and swivel domains. Patient variants are overlaid on the diagram and are color‐coded based on their effect on the encoded protein (Based on NCBI Reference Sequences: NM_001098.2, NP_001089.1). Variants identified in patients described in this cohort are shaded orange. Protein diagrams were generated using ProteinPaint (https://proteinpaint.stjude.org/). (B) MTR‐Viewer results for ACO2. The line graph displays the Missense Tolerance Ratio (MTR) distribution (measure of regional intolerance to missense variation) for ACO2 with regions in red indicating observed variation significantly deviates from neutrality (http://biosig.unimelb.edu.au/mtr‐viewer/). Missense mutations identified in the patient cohort are overlaid and shown as orange circles. (C) Visual representation of the change in vibrational entropy energy between wild‐type (WT) and missense mutations (MUT) generated using DynaMut (http://biosig.unimelb.edu.au/dynamut/). Amino acids colored according to the vibrational entropy change upon mutation with blue indicating a rigidification of the protein structure and red indicating a gain in overall flexibility. A zoomed‐in visualization of the predicted interatomic interactions for WT and MUT residues are shown as sticks and colored in light green along with surrounding residues which are involved in any type of interactions. A table summary of the predicted ΔΔG and ΔΔS predictions are shown below the models for each missense variant in ACO2 (ΔΔG: negative values are destabilizing and positive values are stabilizing)."
      }
    ]
  },
  {
    "id": "PMC7377706_multi",
    "image": [
      "images/PMC7377706-f1.png",
      "images/PMC7377706-f2.png",
      "images/PMC7377706-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Maintaining social contacts: The physiological relevance of organelle interactions\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic overview of mitochondrion-organelle interactions and their physiological relevance. DGAT2, Diacylglycerol O-acyltransferase 2; DMT1, Divalent Metal Transporter 1; ER, Endoplasmic Reticulum; GRP75, Glucose-Regulated Protein 75; IPR3, 1,4,5–triphosphate receptor; LD, Lipid Droplet; LYS, Lysosome; MAVS, Mitochondrial Antiviral-signalling protein; MIGA2, Mitoguardin 2 protein; MITO, Mitochondrion; NLRP3, Nucleotide-binding oligomerization domain-like receptor protein 3; PLIN5, Perilipin-5 protein; PTPIP51, Protein Tyrosine Phosphatase Interacting Protein 51; STARD3, Star-related lipid transfer protein 3; VAPB, Vesicle-Associated Membrane Protein (VAMP)-associated Protein B; VDAC, Voltage-Dependent Anion-selective Channel; VPS13A, Vacuole Protein Sorting-associated protein 13 isoform A.\n\nFigure 2: Figure 2. Schematic overview of peroxisome-organelle interactions and their physiological relevance. ABCD1/3, ATP Binding Cassette subfamily D member 1/3; ACBD4/5, Acyl-CoA Binding Domain containing protein 4/5; ATF6α, Activating Transcription Factor 6α; ER, Endoplasmic Reticulum; Inp1, Inheritance of peroxisomes protein 1; LD, Lipid Droplet; LYS, Lysosome; Mdm34, Mitochondrial distribution and morphology protein 34; MITO, Mitochondrion; M1 spastin, isoform M1 of the microtubule-severing protein spastin; Pex, Peroxin; PI(4,5)P2, Phosphatidylinositol-4,5-biphosphate; PO, Peroxisome; Syt7, Synaptogamin-7; VAPB, Vesicle-Associated Membrane Protein (VAMP)-associated Protein B.\n\nFigure 3: Figure 3. Schematic overview of Golgi-ER and plasma membrane-organelle interactions and their physiological relevance. CERT, Ceramide Transport Protein; FAPP1, Phosphatadyl-four-phosphate-adaptor protein 1; ER, Endoplasmic Reticulum; GOLGI, Golgi Apparatus; Mdm36, Mitochondrial distribution and morphology protein 36; MECA, Mitochondria-ER cortex anchor; MITO, Mitochondrion; Num1, Nuclear migration protein 1; Orai1, Calcium release-activated calcium channel protein 1; Orp9/10/11, Oxysterol-binding protein related protein 9/10/11; Osbp1, Oxysterol-binding protein 1; Osh2/3/6/7, Oxysterol-binding protein homology 2/3/6/7; PI(4)P, Phosphatidylinositol-4-phosphate; Sac1, suppressor of actin 1; Scs2, suppressor of chromosome segregation protein 1 (CSE1) 2; STIM1, Stromal Interaction Molecule 1; VAP, Vesicle-Associated Membrane Protein (VAMP)-associated Protein."
      }
    ]
  },
  {
    "id": "PMC7384229_multi",
    "image": [
      "images/PMC7384229-f1.png",
      "images/PMC7384229-f2.png",
      "images/PMC7384229-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Proteolysis targeting chimeras (PROTACs) are emerging therapeutics for hematologic malignancies\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic representation depicting different strategies of protein suppression. a PROTAC recruits an E3 ligase to a POI followed by polyubiquitination of the POI by an E2 conjugating enzyme. The polyubiquitinated POI is recognized and degraded by the proteasome. Once the POI is degraded, the PROTAC molecule can be recycled to induce the next round of POI degradation, thus working in a sub-stoichiometric manner. b A small molecule inhibitor (SMI) typically binds at the active site of a POI to inhibit the enzymatic functions of the POI. c A monoclonal antibody (mAb) binds to a cell surface receptor to block the signal transduction stimulated by a ligand, a growth factor or a cytokine. d siRNA binds to its targeted mRNA transcript in a complementary manner to induce mRNA cleavage and consequently translational suppression. e An antibody-PROTAC conjugate (Ab-PROTAC) is designed by linking a PROTAC to a mAb. Once an Ab-PROTAC binds to its cell surface receptor, it is internalized into the cytosol through endosomes. In the cytosol, an active PROTAC releases from Ab-PROTAC through lysosomal pathway which induces the degradation of POI\n\nFigure 2: Figure 2. Design and mechanism of homo-PROTACs and light-controllable PROTACs. a Design and mechanism of homo-PROTACs. A homo-PROTAC is consisted of two E3 ligase ligand molecules connected via a linker. Homo-PROTAC recruits an E3 ligase molecule to another E3 ligase molecule followed by bidirectional polyubiquitination of E3 ligase molecules and subsequent degradation of the E3 ligase by the proteasome. b Design and mechanism of light-controllable PROTACs. In a light-controllable PROTAC, a photo-removable group is attached to the POI ligand or E3 ligand or linker. Upon light irradiation, the photo-removable group is detached from the light-controllable PROTAC converting it to an active PROTAC for the proteasomal degradation of POI\n\nFigure 3: Figure 3. Heatmap of single-cell expression of 57 E3 ligases in hematopoietic tissues. The levels of single-cell expression of 57 E3 ligases in different types of hematopoietic cells from the peripheral blood, bone marrow, and spleen in human adults were abstracted from the Human Cell Landscape (HCL) data. In the heatmap, each row represents a cell type, and each column represents an E3 ligase. The color legend shown on the right was determined by averaging the expression values of all cells within a specific cell type. These E3 ligases were clustered by the hierarchical clustering algorithm, and the resulting dendrogram was shown at the bottom. The 57 E3 ligases presented in the figure were chosen according to the criteria: E3 ligases with an average expression value > 0.5 in at least one cell type. Single cell RNA-sequencing (scRNA-seq) data were from the website: https://figshare.com/articles/HCL_DGE_Data/7235471."
      }
    ]
  },
  {
    "id": "PMC7435639_multi",
    "image": [
      "images/PMC7435639-f1.png",
      "images/PMC7435639-f2.png",
      "images/PMC7435639-f3.png",
      "images/PMC7435639-f4.png",
      "images/PMC7435639-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Isoquercitrin Delays Denervated Soleus Muscle Atrophy by Inhibiting Oxidative Stress and Inflammation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Isoquercitrin reduces soleus muscle mass loss caused by denervation (n = 6). (A) The ratio of muscles wet weight in each group. (B) Representative images of laminin-stained muscles cross-sections in each group. Green indicates laminin staining. Scale bar: 50 μm. (C) The histogram shown the cross-sectional area (CSA) of muscles in each group. Ctrl, control group; Den, denervation group; ISO-L, denervated target muscle plus low-dose isoquercitrin (10 mg/kg/d); ISO-M, denervated target muscle plus middle-dose isoquercitrin (20 mg/kg/d); ISO-H, denervated target muscle plus high-dose isoquercitrin (40 mg/kg/d). **p < 0.01 and ****p < 0.0001 vs. Ctrl; #p < 0.05, ##p < 0.01, ###p < 0.001, and ####p < 0.0001 vs. Den; &&p < 0.01 vs. ISO-L.\n\nFigure 2: Figure 2. Isoquercitrin inhibits proteolysis via the ubiquitin-proteasome pathway (n = 6). (A) Western blot of MyHC, MAFbx, and MuRF1. (B–D) Quantification of the expression of MyHC, MAFbx, and MuRF1. Ctrl, control group; Den, denervation group; ISO, denervated target muscle plus middle-dose isoquercitrin (20 mg/kg/d) group. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001 vs. Ctrl; ##p < 0.01vs. Den. MyHC, myosin heavy chain; MuRF1, muscle RING finger 1; MAFbx, muscle atrophy F-box.\n\nFigure 3: Figure 3. Isoquercitrin reduces mitochondrial autophagy in denervated soleus muscles. (A) Ultrastructure of muscle fibers observed using transmission electron microscopy (n = 3). The white arrow indicates mitochondria between muscle fibers. The black arrow indicates an autophage or an autophagic vesicle. (B) Western blot and quantification of the autophagy-related proteins ATG7, BNIP3, PINK1, and LC3B (n = 6). Ctrl, control group; Den, denervation group; ISO, denervated target muscle plus isoquercitrin (20 mg/kg/d) group. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001 vs. Ctrl; #p < 0.05 and ##p < 0.01 vs. Den.\n\nFigure 4: Figure 4. Isoquercitrin delays the slow-to-fast fiber type conversion caused by denervation. (A) Immunofluorescence staining of fast myosin skeletal heavy chain in soleus muscle. (B) Quantification of the positive proption of fast muscle fibers (n = 3). (C) Western blot of PGC-1α, Tn I-FS, and Tn I-SS related to the slow-to-fast fiber type conversion. (D) Quantification of PGC-1α, Tn I-FS, and Tn I-SS. Ctrl, control group; Den, denervation group; ISO, denervated target muscle plus isoquercitrin (20 mg/kg/d) group. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001 vs. Ctrl; #p < 0.05 and ##p < 0.01 vs. Den. PGC-1α, peroxisome proliferator-activated receptor γ coactivator 1α; TnI-FS, fast skeletal muscle troponin I; TnI-SS, slow skeletal muscle troponin I.\n\nFigure 5: Figure 5. Isoquercitrin inhibits the inflammatory response in denervated soleus muscles (n = 6). (A) Quantitative polymerase chain reaction detection of changes in the expression of the inflammatory factors interleukin (IL)-1β, IL-6, and tumor necrosis factor (TNF)-α. (B) Enzyme-linked immunosorbent assay (ELISA) detection of the expression of IL-1β, IL-6, and TNF-α; (C) Western blot analysis of JAK/STAT3 activation. Ctrl, control group; Den, denervation group; ISO, denervated target muscle plus isoquercitrin (20 mg/kg/d) group. **p < 0.01, ***p < 0.001, and ****p < 0.0001 vs. Ctrl; #p < 0.05, ##p < 0.01, and ###p < 0.001 vs. Den."
      }
    ]
  },
  {
    "id": "PMC7435639_multi_2",
    "image": [
      "images/PMC7435639-f6.png",
      "images/PMC7435639-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Isoquercitrin Delays Denervated Soleus Muscle Atrophy by Inhibiting Oxidative Stress and Inflammation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Isoquercitrin inhibits oxidative stress in denervated soleus muscles (n = 6). (A) Fluorescence diagram of reactive oxygen species (ROS) level and quantification of relative fluorescence intensity of each group in the dihydroethidium (DHE) probe detection experiment. (B) Quantitative polymerase chain reaction detection of the relative expression of antioxidant-related genes and ROS production-related genes. (C) Western blot of ROS-related and antioxidant-related proteins and quantification of the relative expressions. ROS, reactive oxygen species; Ctrl, control group; Den, denervation group; ISO, denervated target muscle plus isoquercitrin (20 mg/kg/d) group. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001 vs. Ctrl; #p < 0.05, ##p < 0.01, ###p < 0.001, and ####p < 0.0001 vs. Den.\n\nFigure 7: Figure 7. A schematic diagram illustrating the proposed mechanism by which peripheral nerve injury induces soleus muscle atrophy. Denervation-induced skeletal muscle atrophy is associated with oxidative stress and inflammation. The inhibition of oxidative stress and inflammation through Isoquercitrin alleviated denervation-induced skeletal muscle atrophy by reducing proteolysis, inhibiting mitophagy, and reversing the slow-to-fast fiber type conversion following denervation."
      }
    ]
  },
  {
    "id": "PMC7438929_multi",
    "image": [
      "images/PMC7438929-f1.png",
      "images/PMC7438929-f2.png",
      "images/PMC7438929-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Comparison of the Diagnostic Performance of C26:0-Lysophosphatidylcholine and Very Long-Chain Fatty Acids Analysis for Peroxisomal Disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Correlation plot showing the correlation between C26:0-LPC levels analyzed in DBS and plasma samples from controls (green circles, n = 43), ALD males (blue circles, n = 21), ALD females (purple circles, n = 17) and ZSD patients (red circles, n = 33) that were generated from the same blood sample. The upper limit of the reference range (0.072 μmol/L) is indicated by the dashed lines.\n\nFigure 2: Figure 2. Scatterplots of C26:0 (plasma) (A), C26:0/C22:0 ratio (plasma) (B) and C26:0-LPC [DBS (squares) and plasma (circles)] (C) from controls (green, n = 67), ALD males (blue, n = 26), ALD females (purple, n = 19) and ZSD patients (red, n = 35). The upper limit of the reference range for C26:0 (1.32 μmol/L), the C26:0/C22:0 ratio (0.02) and C26:0-LPC in DBS (0.072 μmol/L) is indicated by the dashed lines.\n\nFigure 3: Figure 3. Correlation plot showing the correlation between C26:0 concentration and the C26:0/C22:0 ratio (A), C26:0-LPC and C26:0 levels (B) and C26:0-LPC level and the C26:0/C22:0 ratio (C) in controls (green, n = 67), ALD males (blue, n = 26), ALD females (purple, n = 19) and ZSD patients (red, n = 35). C26:0-lysoPC results from DBS are indicated by squares and plasma by circles. The upper limit of the reference range for C26:0 (1.32 μmol/L), the C26:0/C22:0 ratio (0.02) and C26:0-LPC (0.072 μmol/L) is indicated by the dashed lines."
      }
    ]
  },
  {
    "id": "PMC7451421_multi",
    "image": [
      "images/PMC7451421-f1.png",
      "images/PMC7451421-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Four patients with D-bifunctional protein (DBP) deficiency: Expanding the phenotypic spectrum of a highly variable disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Brain MRI of the patients. A. An axial T2 Flair sequence of patient #1 at 6 days of age demonstrating mild bilateral peri-sylvian polymicrogyria (arrow). B. Patient #2 - MRI performed at 5 years. Significant cerebellar atrophy and mild cerebral atrophy are noted on the sagittal T1 view (B-1) and abnormal signal in the dentate and cerebral WM are demonstrated in the coronal T2 view (B-2) (arrows). C. Patients #3–4. C1) An axial T2 sequence of patient #3 at 8 months of age - delayed white matter maturation, enlarged ventricles, and extra-axial fluid; C-2) An axial T2 sequence of patient #4 at 18 months of age demonstrating abnormal periventricular white matter signal (arrow); C-3) A sagittal T1 sequence of patient #4 at 18 months of age showing thin corpus callosum (arrow), mild cerebellar atrophy, and extra-axial fluid.\n\nFigure 2: Figure 2. D-Bifunctional Protein structure and mutations. SCP-2 L. C-terminal sterol carrier protein 2-like domain."
      }
    ]
  },
  {
    "id": "PMC7477296_multi",
    "image": [
      "images/PMC7477296-f1.png",
      "images/PMC7477296-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Rosy Beginnings: Studying Peroxisomes in Drosophila\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Knockdown of Pex3 in the Drosophila eye phenocopies the Rosy phenotype. (A) Wild type Drosophila eye pigment is a bright red-orange color. (B) Reduction of Pex3 activity specifically in the eye by a combination of eyeless(ey) GAL4 and a UAS inducible transgene expressing a dsRNA targeting Pex3 mRNA causes the characteristic dark red pigmentation associated with ry mutations. Bar = 300 μm.\n\nFigure 2: Figure 2. A model for the likely role of the Drosophila homologs of peroxisome biogenesis factors, based on a recent one for mammalian peroxisome proteins by Fujiki et al. (2020). Homologs of Pex proteins (Table 1) required for recruitment and insertion of peroxisome membrane proteins (Table 2), as well as Pex3, Pex16, and Pex19 are all conserved in Drosophila. The peroxisome fission machinery also appears conserved as there are three Drosophila Pex11 proteins (Pex11, CG13827, and CG3374). Fis1 is the homolog of Fission, mitochondrial 1 (FIS1), Tango11 is homologous to Mitochondrial fission factor (MFF) and Drp1 is the homolog of Dynamin 1 like (DNM1L), all of which are required for peroxisome fission in mammals. Drosophila peroxisomal matrix protein import in flies appears dependent on PTS1, mediated by Pex5 binding to PTS1 (Table 3), although some matrix proteins do not have a PTS1 motif (Table 4). The docking complex proteins Pex13 and Pex14 are conserved in Drosophila, as is the RING-E3-ligase complex of Pex2, Pex10, and Pex12. It is therefore likely that Pex5-bound cargos are imported, then Pex5 is recycled to the cytosol by Pex1 and Pex6 in a manner similar to mammals. A Pex7 homolog exists in Drosophila, but its role in peroxisome function is unclear."
      }
    ]
  },
  {
    "id": "PMC7478639_multi",
    "image": [
      "images/PMC7478639-f1.png",
      "images/PMC7478639-f2.png",
      "images/PMC7478639-f3.png",
      "images/PMC7478639-f4.png",
      "images/PMC7478639-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A combination of 7-ketocholesterol, lysosphingomyelin and bile acid-408 to diagnose Niemann-Pick disease type C using LC-MS/MS\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. One point is one sample. The error bar is mean value with standard deviation (SD). Red: 7-KC amount above 50 ng/mL among other patients or negative controls.\n\nFigure 2: Figure 2. One point is one sample. The error bar is mean value with standard deviation (SD). Red: lysoSM amount over 10 ng/mL among other patients; blue: lysoSM amount below the threshold in NPC patients.\n\nFigure 3: Figure 3. One point is one sample. The error bar is mean value with standard deviation (SD). Red: bile acid-408 amount over 2.4 ng/punch among negative controls; blue: bile acid-408 amount below the threshold in NPC patients.\n\nFigure 4: Figure 4. a: the correlation between 7-KC and lysoSM; b: the correlation between lysoSM and bile acid-408; c: the correlation between 7-KC and bile acid-408.\n\nFigure 5: Figure 5. One point is one sample. Left: NPC patients (n = 16); middle: high risk suspicious (n = 12); right: negative controls (n = 38) with X-ALD patients in blue (n = 5). Two NPC patients (red) had only one abnormal biomarker."
      }
    ]
  },
  {
    "id": "PMC7486221_multi",
    "image": [
      "images/PMC7486221-f1.png",
      "images/PMC7486221-f2.png",
      "images/PMC7486221-f3.png",
      "images/PMC7486221-f4.png",
      "images/PMC7486221-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Defects in Mitochondrial Biogenesis Drive Mitochondrial Alterations in PARKIN-Deficient Human Dopamine Neurons\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Differentiation and Characterization of iCont and PARKIN KO hESCs to Dopamine Neurons (A) Immunofluorescence staining of DA neuron differentiated cultures at 60 days from iCont and PARKIN KO lines. Neuron-specific class IIIβ-tubulin (TUJ1) is indicated in green and tyrosine hydroxylase (TH) is indicated in red. DAPI (blue) staining represents the nucleus. Scale bar, 50 μm. (B–D) Percentage of (B) TH, (C) TUJ1, and (D) TH/TUJ1 immunofluorescence staining. n = 5 independent experiments. (E) Representative immunoblots of TH and TUJ1 normalized to actin 60 days post differentiation to DA neurons. (F–H) Quantification of immunoblots of (F) TH, (G) TUJ1, and (H) TH/TUJ1. n = 3 independent experiments. (I) Immunofluorescence staining of Ki67 (red) and PI staining (red), nuclei are stained with DAPI (blue) 60 days post differentiation to DA neurons. Scale bar, 50 μm. (J and K) Quantification of immunofluorescence staining of (J) PI and (K) Ki67staining. n = 5 independent experiments. (L) Immunofluorescence staining of Annexin V (red) TH (green), nuclei are stained with DAPI (blue) 60 days post differentiation to DA neurons. Scale bar, 50 μm. (M) Quantification of immunofluorescence staining of Annexin V. n = 5 independent experiments. Error bar represents mean ± SEM. p values were determined using one-way ANOVA followed by Bonferroni's multiple comparisons test. Asterisks indicate the level of statistical significance: ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. See also Figures S1 and S2.\n\nFigure 2: Figure 2. Characterization of Mitochondrial Function Defects in PARKIN KO Neurons (A) Mitochondrial oxygen consumption rate (OCR) using the Seahorse platform in iCont and PARKIN KO neuronal cultures 55 days post differentiation. The blue line represents iCont, green and red represents PARKIN KO-1and KO-2 respectively. (B) Quantification of basal respiration, reserve capacity, and maximal respiration in iCont and PARKIN KO neuronal cultures in the presence of oligomycin, CCCP, and rotenone, respectively. n = 3 independent experiments. (C) Immunofluorescence staining of mitochondrial marker Tom20 (green), TH (blue) positive neurons, and MitoTracker Red CMXRos 60 days post differentiation to DA neuron iCont and PARKIN KO neuronal cultures. Scale bar, 25 μm. (D) Quantification of Tom20 and MitoTracker Red CMXRos intensity within TH-positive neurons. n = 3 independent experiments. Error bar represents the mean ± SEM. p values were determined using one-way ANOVA followed by Bonferroni's multiple comparisons test. Asterisks indicate the level of statistical significance: ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. See also Figure S2.\n\nFigure 3: Figure 3. Mitochondrial Autophagy Defects in PARKIN KO Neurons (A) Confocal live imaging of neurons at 60 days post differentiation to DA neurons transduced with lentivirus encoding for Mito-Keima in iCont and PARKIN KO lines. Scale bar, 25 μm. (B) Quantification of Mito-Keima in iCont and PARKIN KO neuronal cultures. n = 10 neurons in each condition. (C) Immunoblot of analysis of LC3I/II and autophagy marker P62. (D and E) (D) Quantification of LC3 I/II and (E) P62 60s day post differentiation to DA neurons. n = 5 independent experiments. Error bar represents the mean ± SEM. p values were determined using one-way ANOVA followed by Bonferroni's multiple comparisons test. Asterisks indicate the level of statistical significance: ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. See also Figure S3.\n\nFigure 4: Figure 4. Mitochondrial Biogenesis Defect in PARKIN KO Neurons (A) Immunoblot analysis of PARIS, TH, PARKIN, and in PARKIN iCont and PARKIN KO, 60 days post differentiation to DA neurons. (B and C) Quantification of immunoblot of (B) PARIS and (C) TH normalized to actin in iCont and PARKINKO neurons. (D) Immunoblot analysis of PGC-1α in iCont and PARKIN KO lines, 60 days post differentiation to DA neurons. (E) Quantification of immunoblots of PGC-1α normalized to actin in iCont and PARKIN KO neuronal cultures. n = 3 independent experiments. (F) Transmission electron microscopy images of neurons derived from iCont and PARKIN KO hESCs, 60 days post differentiation to DA neurons. Scale bar, 500 nm. (G–I) Quantification of (G) abnormal mitochondria cristae, (H) mitochondria size, and (I) mitochondria number/cell body in iCont and PARKIN KO hESC neurons. n = 16–17 cells for each condition. (J) Mitochondrial DNA quantification of tRNALeu (MT), ND1, ATP6, and COX1, 60 days post differentiation to DA neurons in iCont and PARKIN KO hESCs, normalized to nuclear β2-microglobulin gene. n = 6 independent experiments. (K) Immunoblot analysis of CytC and CoxIV in iCont and PARKIN KO hESCs, 60 days post differentiation to DA neurons. (L and M) Quantification of immunoblots of (L) CytC and (M) CoxIV in iCont and PARKIN KO neuronal cultures. n = 5 independent experiments. Error bar represents the mean ± SEM. p values were determined using one-way ANOVA followed by Bonferroni's multiple comparisons test. Asterisks indicate the level of statistical significance: ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. See also Figures S2 and S4.\n\nFigure 5: Figure 5. Mitochondrial Biogenesis Defects in PARKIN KO DA Neurons (A) Puromycin labeling SUnSET assay in iCont and PARKIN KO cells 60 days post differentiation to DA neurons. Anti-Puromycin (green), -TH (blue), and -Tom20 (red) immunofluorescence staining. Scale bar, 25 μm. (B) Quantification of immunofluorescence staining for puromycin, TH, and Tom20 within the TH-positive neurons. n = 13–16 for each condition. (C) Schematic diagram showing SNAP-tag, a protein labeling technique targeting the mitochondria. Old mitochondria are labeled with substrate 1 (green), and after 24 h substrate 2 (red) is added to label new mitochondria. (D) Confocal Z stacked images of SNAP-tag Cox8a labeled mitochondria along with anti-TH (blue) immunostained neurons. Green (old) and new (red) mitochondria are labeled. Scale bar, 25 μm. (E) Quantification of the fluorescence intensity of old (green) and new (red) Cox8a labeled mitochondria in TH (blue)-positive neurons. n = 8 in each condition. Error bar represents the mean ± SEM. p values were determined using one-way ANOVA followed by Bonferroni's multiple comparisons test. Asterisks indicate the level of statistical significance: ∗p ≤ 0.05, ∗∗p ≤ 0.01. See also Figure S5."
      }
    ]
  },
  {
    "id": "PMC7486221_multi_2",
    "image": [
      "images/PMC7486221-f6.png",
      "images/PMC7486221-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Defects in Mitochondrial Biogenesis Drive Mitochondrial Alterations in PARKIN-Deficient Human Dopamine Neurons\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Generation and Characterization of PARKIN/PARIS Knockdown (PARKIN/PARIS KD) hESCs Lines (A) Representative immunoblot of PARIS, TH, and PARKIN protein levels in iCont, PARKIN KO, and PARKIN/PARIS KD cells, 60 days post differentiation to DA neurons. (B) Quantification of the immunoblot of PARIS protein levels. n = 3–4 independent experiments. (C) Representative immunoblot for PGC-1α protein levels in iCont, PARKIN KO, and PARKIN KO/PARIS KD DA neurons in (A). (D) Quantification of immunoblots for PGC-1α. n = 3–4 independent experiments. (E) Quantification of the immunoblots of TH protein levels in iCont, PARKIN KO, and PARKIN/PARIS KD neuronal cultures in (A). n = 3–4 independent experiments. (F) Immunofluorescence staining of TH-positive neurons (green) and nuclei (blue) iCont, PARKIN KO, and PARKIN/PARIS KD cells, 60s day post differentiation to DA neurons. (G) Quantification of TH-positive neurons in (F). n = 5 independent experiments. (H) Confocal live imaging of neurons transduced with lentivirus encoding for Mito-Keima in iCont, PARKIN KO, and PARKIN/PARIS KD cells, 60 days post differentiation to DA neurons. (I) Quantification of Mito-Keima (mitophagy index) in (H). n = 19–25 neurons in each condition. (J) Representative immunoblot of P62 and LC3 I/II in iCont, PARKIN KO, and PARKIN/PARIS KD cells, 60 days post differentiation to DA neurons. (K and L) Quantification of (K) P62 and (L) LC3 I/II. n = 3–4 independent experiments. Error bar represents the mean ± SEM. p values were determined using one-way ANOVA followed by Bonferroni's multiple comparisons test. Asterisks indicate the level of statistical significance: ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. See also Figure S6 and Table S1.\n\nFigure 7: Figure 7. Rescue of Mitochondrial Function Defects in PARKIN/PARIS KD Lines (A) Mitochondrial oxygen consumption rate (OCR) by the Seahorse platform in iCont, PARKIN KO1, and PARKIN/PARIS KD cells, 55 days post differentiation to DA neurons. The green line represents iCont, the red and blue lines represent PARKIN KO-1 and PARKIN/PARIS KD neurons, respectively. (B) Quantification of basal respiration, reserve capacity, and maximal respiration in iCont, PARKIN KO1, and PARKIN/PARIS KD neurons. n = 3 independent experiment. (C) Mitochondrial DNA quantification of tRNALeu (MT), ND1, ATP6, and COX1, 60 days post differentiation to DA neurons in iCont, PARKIN KO, and PARKIN/PARIS KD cells normalized to nuclear β2-microglobulin gene. n = 4 independent experiments. (D) Puromycin labeling SUnSET assay in iCont, PARKIN KO neuronal cultures, and PARKIN/PARIS KD, 60 days post differentiation to DA neurons. Anti-Puromycin (green), anti-TH (blue), and anti-Tom20 (red) immunofluorescence staining. (E) Quantification of the SUnSET assay. n = 10–15 TH neurons in each condition. (F) Confocal Z stacked images of SNAP-tag Cox8a labeled mitochondria along with anti-TH (blue) immunostained neurons. New mitochondria are labeled in red and old mitochondria are labeled in green. Scale bar, 50 μm. (G) Quantification of the fluorescence intensity of new (red) and old (green) Cox8a labeled mitochondria in TH (blue) positive neurons. n = 16 TH neurons in each condition. (H) Transmission electron microscopy images of neurons from iCont and PARKIN KO and PARKIN/PARIS KD hESC lines from 60-day-old cultures. Scale bar, 500 nm. (I–L) Quantification of mitochondrial (I) abnormal cristae, (J) size, (K) number/cell, and (L) number of healthy and unhealthy mitochondria in iCont and PARKIN KO and PARKIN/PARIS KD hESC-derived neurons, 60 days post differentiation. n = 15–35 cells in each condition. (M) Immunofluorescence staining of Tom20 (red), TH (green), and nuclei stained with DAPI (blue) from iCont, PARKIN KO, and PARKIN/PARIS KD TH neurons, 60 days post differentiation. Colocalized Tom20 and TH are in white. Scale bar, 50 μm. (N) Quantification of colocalized Tom20and TH in iCont, PARKIN KO, and PARKIN/PARIS KD TH neurons. n = 7–15 TH neurons in each condition. Error bar represents the mean ± SEM. p value were determined using one-way ANOVA followed by Bonferroni's multiple comparisons test. Asterisks indicate the level of statistical significance: ∗p ≤ 0.05, ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. See also Figure S7 and Table S1."
      }
    ]
  },
  {
    "id": "PMC7515967_multi",
    "image": [
      "images/PMC7515967-f1.png",
      "images/PMC7515967-f2.png",
      "images/PMC7515967-f3.png",
      "images/PMC7515967-f4.png",
      "images/PMC7515967-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Elovl4 Spinocerebellar Ataxia-34 Mutation 736T>G (p.W246G) Impairs Retinal Function in the Absence of Photoreceptor Degeneration\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generation and characterization of c.736T>G, p.W246G knock-in Long-Evans rat using the CRISPR/Cas9 system. a Schematic depiction of targeting strategy. The genomic region of the rat Elovl4 locus is diagrammed (the gene is oriented from left to right; total size is 28.21 kb). Solid bars represent open reading frame (exons). Open bars represent untranslated regions. The sgRNA cut site and the single-strand oligonucleotide donor sequencing with homology arms and the mutation site is shown by the red arrow. b Genotyping of WT, HET, and MUT SCA34-KI rats by StyI restriction analysis. Seven hundred four base–pair PCR products were generated from WT, HET, and MUT rats using PCR primers. The amplicons were run undigested or purified and digested with StyI restriction enzyme. Left panel: undigested amplicons ran at 704 bp for WT, HET, and MUT rats, as expected. Right panel: digestion with StyI restriction enzyme showed the WT PCR product is resistant to Sty I digestion. In contrast, HET rats show two bands, one corresponding to the WT PCR product and a smaller, digested fragment arising from the mutant PCR product containing the StyI digestion site. MUT rats show only a single band corresponding to the digested, mutant PCR product with no WT PCR product, as expected\n\nFigure 2: Figure 2. Gross physical phenotype of SCA34-KI rats. a Gross appearance of WT and HET SCA34-KI rats is similar. MUT SCA34-KI rats show hair loss and erythrokeratodermia variabilis (EKV). b Comparison of the underside of WT and MUT SCA34-KI rats showing marked hair loss and EKV. c Hair loss around the eyes, nose, and ears (arrows) on a MUT SCA34-KI rat. d WT rat pups show normal eyelids with full opening (P45 shown). e MUT SCA34-KI rats show stiff, swollen eyelids at early ages that open incompletely (P45 shown), which resolves by about P60. Hair loss around the eye is also common in MUT rats. f Adult MUT rats show complete opening of the lids. g Male rats of all genotypes were significantly larger than female rats by P60. Female rats showed no difference in weight among genotypes, but male MUT rats were significantly smaller than male WT or HET rats. (Females: n = 29 WT, 32 HET, 33 MUT; males: n = 14 WT, 11 HET, 10 MUT. Data shown as mean ± St. Dev. 2-way ANOVA + Bonferroni post hoc test (sex, genotype). *, p < 0.05; **, p < 0.01; ***, p < 0.001; ****, p < 0.0001). h Male rats of all genotypes were larger than female rats of all genotypes at 6–7 months of age. Female rats showed no difference in weight among genotypes, but male MUT rats were significantly smaller than male WT and HET rats. (Females: n = 17 WT, 14 HET, 10 MUT; males: n = 7 WT, 10 HET, 4 MUT. Data shown as mean ± St. Dev. 2-way ANOVA + Bonferroni post hoc test (sex, genotype). *, p < 0.05; **, p < 0.01; ***, p < 0.001; ****, p < 0.0001)\n\nFigure 3: Figure 3. W246G ELOVL4 retains the ability to synthesize VLC-PUFA. Analysis of retinal glycerophospholipids from WT, HET, and MUT SCA34-KI rats shows that the W246G mutant form of ELOVL4 retains the capacity to synthesize VLC-PUFA at normal levels. No differences in total retinal levels of VLC-PUFA were present among WT, HET, and MUT rats. a VLC-PUFA were detected specifically in the phosphatidylcholine fraction (PC), but total VLC-PUFA levels showed no differences among WT, HET, and MUT rat retinas. However, significant differences were detected in non-VLC-FA (PC 34:01 and PC 40:06) among genotypes. b No VLC-PUFA were detected in the phosphatidylethanolamine (PE) fraction of WT, HET, or MUT rat retina. However, statistically significant differences were detected in PE 40:06 and PC 44:12. c No VLC-PUFA were detected in the phosphatidylserine (PS) fraction of WT, HET, or MUT rat retina. No significant differences were detected in any lipid species in the PS fraction. (Analysis by 1-way ANOVA with Tukey’s post hoc test. Data shown as mean ± St. Dev. *, MUT differs from WT; $, HET differs from WT; #, MUT differs from WT. See Supplemental Tables 1–3 for details)\n\nFigure 4: Figure 4. The W246G mutation in ELOVL4 impairs VLC-SFA synthesis. a Analysis of VLC-SFA in skin. Levels of VLC-SFA (28:0 and 30:0) and total VLC-SFA (28:0 + 30:0) were significantly reduced in the skin of MUT rats compared to WT and HET rats. b Levels of 26:0, the direct precursor for VLC-SFA synthesis, did not differ significantly across genotypes. However, levels of 24:0 were significantly elevated in the skin of HET and MUT rats compared to WT rats. (Data shown as mean ± St. Dev. Analysis by 1-way ANOVA with Tukey’s post hoc test. *, p < 0.05; **, p < 0.01; ***, p < 0.001. See Supplemental Table 4 for details)\n\nFigure 5: Figure 5. Retinal layering is normal and photoreceptors are preserved in the SCA34-KI rat retinas to at least 6–7 months. a–d Optical coherence tomography (OCT) analysis of WT, HET, and MUT SCA34 rat retinas from P30 to 6–7 months of age showed no differences in thickness of any retinal layer at any time point. (Data shown as mean ± St Dev. Analysis by 1-way ANOVA with Tukey’s post hoc test. P30: 12 WT, 13 HET, 16 MUT. P90: 9 WT, 14 HET, 10 MUT. P120: 2 WT, 2 HET, 5 MUT. 6–7 months: 7 WT, 11 HET, 7 MUT). e Eye diameter in 6–7-month-old rats also is unaffected by the W246G mutation in ELOVL4. (One-way ANOVA with Tukey’s post hoc test. Data shown as mean ± St Dev. n = 3 WT, 3 HET, 3 MUT). f Histological analysis of outer nuclear layer thickness shows no differences among WT, HET, and MUT rats along the superior to inferior axis at 6–7 months of age, indicating no significant photoreceptor degeneration. (One-way ANOVA with Tukey’s post hoc test. Data shown as mean ± St Dev. n = 3 WT, 3 HET, 3 MUT). PRL, photoreceptor layer; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer"
      }
    ]
  },
  {
    "id": "PMC7515967_multi_2",
    "image": [
      "images/PMC7515967-f6.png",
      "images/PMC7515967-f7.png",
      "images/PMC7515967-f8.png",
      "images/PMC7515967-f9.png",
      "images/PMC7515967-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Elovl4 Spinocerebellar Ataxia-34 Mutation 736T>G (p.W246G) Impairs Retinal Function in the Absence of Photoreceptor Degeneration\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The distribution of ELOVL4 is normal in the SCA34-KI rat retina. a–c ELOVL4 immunolabeling in the retina of P45 WT, HET, and MUT rats is present in the photoreceptor cells, as appropriate. The ELOVL4 antibody recognizes an epitope that is conserved in WT and W246G mutant ELOVL4. d–f Normal distribution of ELOVL4 immunolabeling is preserved in the photoreceptors in WT, HET, and MUT rats at 6–7 months of age (6–7 Mo). PRL, photoreceptor layer; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer. Scale bars = 50 μm\n\nFigure 7: Figure 7. Cone cells are preserved in the SCA34-KI rat retina. a–c Labeling of cone outer segment sheaths (arrowheads) is normal in the retina of P45 WT, HET, and MUT rats. d–f Normal PNA labeling of cone outer segment sheaths is preserved in the retinas of 6–7 month-old (6–7 Mo) WT, HET, and MUT rats. PRL, photoreceptor layer; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer. Scale bars = 50 μm\n\nFigure 8: Figure 8. Müller cells in the SCA34-KI rat retina are not reactive. a–c Müller cells in the retina of P45 WT, HET, and MUT rats show little labeling for glial fibrillary acidic protein (GFAP) as is typical of Müller cells in the healthy retina. Labeling in blood vessels (bv) is non-specific. d–f Müller cells in the retina of 6–7-month-old (6–7 Mo) WT, HET, and MUT rats also show little labeling for GFAP, indicating the absence of glial reactivity associated with retinal degeneration. PRL, photoreceptor layer; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer. Scale bars = 50 μm\n\nFigure 9: Figure 9. Effects of the W246G mutant form of ELOVL4 on the scotopic ERG. Homozygous inheritance of the W246G form of ELOVL4 reduces scotopic a-wave and b-wave ERG responses. a, c, e Scotopic ERG a-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. b, d, f Scotopic ERG b-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. (Data shown as mean ± SEM. One-way ANOVA with Tukey’s post hoc test. Asterisks indicate statistical significance at p < 0.05 (*), p < 0.01 (**), and p < 0.001 (***). P90: 14 WT, 14 HET, 17 MUT. P120: 13 WT, 15 HET, 15 MUT. 6–7 Mo: 9 WT, 14 HET, 7 MUT)\n\nFigure 10: Figure 10. Ratio of scotopic b-wave to a-wave amplitude. The scotopic b-wave to a-wave ratio in MUT rats shows a consistent reduction compared to the b-wave to a-wave ratio of age-matched HET and WT rats, suggesting that amplification of rod signals transmitted to the inner retina is reduced in MUT rats. (Data shown as mean ± SEM. One-way ANOVA with Tukey’s post hoc test. Asterisks indicate statistical significance at p < 0.05 (*), p < 0.01 (**), and p < 0.001 (***). P90: 14 WT, 14 HET, 17 MUT. P120: 13 WT, 15 HET, 15 MUT. 6–7 Mo: 9 WT, 14 HET, 7 MUT)"
      }
    ]
  },
  {
    "id": "PMC7515967_multi_3",
    "image": [
      "images/PMC7515967-f11.png",
      "images/PMC7515967-f12.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The Elovl4 Spinocerebellar Ataxia-34 Mutation 736T>G (p.W246G) Impairs Retinal Function in the Absence of Photoreceptor Degeneration\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Effects of the W246G mutant form of ELOVL4 on the photopic ERG a-wave. Homozygous inheritance of the W246G form of ELOVL4 reduces cone-driven ERG a-wave responses. a, b, c Photopic ERG a-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. d, e, f S-cone-driven ERG a-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. g, h, i M-cone-driven ERG a-wave amplitude for wild-type, heterozygote, and homozygote SCA34-KI rats at P90, P120, and 6–7 months of age. j, k, l Cone-driven flicker ERG a-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. (Data shown as mean ± SEM. One-way ANOVA with Tukey’s post hoc test. Asterisks indicate statistical significance at p < 0.05 (*), p < 0.01 (**), and p < 0.001 (***). P90: 14 WT, 14 HET, 17 MUT. P120: 13 WT, 15 HET, 15 MUT. 6–7 Mo: 9 WT, 14 HET, 7 MUT)\n\nFigure 12: Figure 12. Effects of the W246G mutant form of ELOVL4 on the photopic ERG b-wave. Homozygous inheritance of the W246G form of ELOVL4 reduces cone-driven ERG b-wave responses. a, b, c Photopic ERG b-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. d, e, f S-cone-driven ERG b-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. g, h, i M-cone-driven ERG b-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. j, k, l Cone-driven flicker ERG b-wave amplitude for WT, HET, and MUT rats at P90, P120, and 6–7 months of age. (Data shown as mean ± SEM. One-way ANOVA with Tukey’s post hoc test. Asterisks indicate statistical significance at p < 0.05 (*), p < 0.01 (**), and p < 0.001 (***). P90: 14 WT, 14 HET, 17 MUT. P120: 13 WT, 15 HET, 15 MUT. 6–7 Mo: 9 WT, 14 HET, 7 MUT)"
      }
    ]
  },
  {
    "id": "PMC7549135_multi",
    "image": [
      "images/PMC7549135-f1.png",
      "images/PMC7549135-f2.png",
      "images/PMC7549135-f3.png",
      "images/PMC7549135-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ultrastructural, Cytochemical, and Comparative Genomic Evidence of Peroxisomes in Three Genera of Pathogenic Free-Living Amoebae, Including the First Morphological Data for the Presence of This Organelle in Heteroloboseans\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Identification of peroxisomes in three genera of pathogenic free-living amoebae by transmission electron microscopy. Spherical structures with a dark granular content and limited by a single membrane were observed in Acanthamoeba griffini (A), Acanthamoeba polyphaga (B), Acanthamoeba royreba (C), Acanthamoeba castellanii (D), Balamuthia mandrillaris (E), and Naegleria fowleri (F). These structures ranged in size from 0.2 to 0.9 µm and they were morphologically similar to peroxisomes from mouse liver samples, which are shown for comparison (G, H). M, mitochondrion; Nu, nucleus. Bar = 0.5 µm.\n\nFigure 2: Figure 2. Peroxisome identification in three genera of pathogenic free-living amoebae by cytochemical staining. Thin sections of trophozoites were treated with diaminobenzidine and hydrogen peroxide to detect catalase activity. Positive reaction products were clearly seen in Acanthamoeba griffini (A), Acanthamoeba polyphaga (B), Acanthamoeba royreba (C), Acanthamoeba castellanii (D), Balamuthia mandrillaris (E) and Naegleria fowleri (F). In all of these amoebae, the labeling was deposited in round structures with a uniform electrondense content. Mouse liver samples were used as a positive control for the cytochemical staining (G). As a negative control for the cytochemical reaction, a mouse liver sample was incubated without H2O2 (H). ER, endoplasmic reticulum; M, mitochondrion; Nu, nucleus. Bar = 0.5 µm.\n\nFigure 3: Figure 3. Phylogenetic analysis of the peroxisomal biogenesis protein Pex1. The consensus tree was obtained with RAxML-HPC2 8.2.12. Bootstrap values >80% are indicated. The tree is rooted midpoint and the scale bar indicates the mean number of amino acid substitutions per site. Sequences are colored to denote the different taxonomic lineages (see box).\n\nFigure 4: Figure 4. Phylogenetic analysis of the peroxisomal biogenesis protein Pex5. RAxML-HPC2 8.2.12 was used to obtain the consensus tree. Bootstrap values >80% are shown. The tree is midpoint rooted and the scale bar shows the mean number of amino acid substitutions per site. Sequences are colored to indicate their taxonomic lineage (see box)."
      }
    ]
  },
  {
    "id": "PMC7555135_multi",
    "image": [
      "images/PMC7555135-f1.png",
      "images/PMC7555135-f2.png",
      "images/PMC7555135-f3.png",
      "images/PMC7555135-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MuRF1/TRIM63, Master Regulator of Muscle Mass\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. MuRF1 structure and known regions of interaction with some partners. MuRF1 structure is characterized by a RBCC (RING-B-box-coiled-coil) motif constituted by an N-terminal RING domain (23–79), a MuRF family specific motif (MFC) motif (79–113), a B-box type 2 (Bb2) domain (117–161), a central helical domain (166–328) with a COS-box motif (269–328) and a C-terminal acidic tail (328–353). Several regions have been identified for their interaction with MuRF1 partners (substrates in dark blue and other interactors in light blue): Titin [2], cardiac troponin I [21,28], muscle-type creatine kinase (MCK) [29], c-Jun [22], the ubiquitin conjugating enzymes (UBE2s) [30], CARP 119–325 [31]. HD, helical domain.\n\nFigure 2: Figure 2. Transcriptional Regulation of MuRF1. (a) Pathways that control MuRF1 transcription. MuRF1 transcription is regulated by different stimuli that activate several signaling pathways, and several different transcription activators and repressors. See main text for further details. GR, glucocorticoid receptor, PM, plasma membrane. (b) The promoter of the mouse (C57BL/6J) MuRF1 gene is schematically shown with the transcription factors potentially promoting or interfering with MuRF1 transcription in the skeletal muscle. Binding sites are numbered starting with the transcription initiation as base +1. Only the sites experimentally tested are shown but several other potential sites exist in the promoter sequence for most of them. For the repressor Zeb1, 30 other sites exist but they have not been individually tested and only the ones present in the proximal region of the promoter are shown. In the heart, the activity of a MEF2 binding site (−32/−23) encompassing the proximal FoxO site was reported.\n\nFigure 3: Figure 3. MuRF1 functions in skeletal muscle. MuRF1 is responsible for the coordinated breakdown of both thick and thin filament occurring during catabolic states in skeletal muscle. Like in cardiac muscle, MuRF1 probably binds to titin at the M-line in some conditions (catabolic conditions, MuRF1 excess, etc.), causing the disruption of titin/M-line interactions and hence a partial disorganization of sarcomere assembly. Upon sarcomere destabilization, MuRF1 would have access to contractile proteins (alpha-actin, troponins I, C, and T, MHC, MLC, MyBP-C), to target them for polyUb and proteasome-dependent degradation. MuRF1 also drives telethonin (Tcap) degradation, but it remains to determine which form of the telethonin is targeted by MuRF1: The free form, the titin-complexed form, or both. The inhibition of protein synthesis by MuRF1 has been reported in skeletal muscles, but more investigations are needed to confirm this role. MuRF1 was reported to target the non-functional oxidized form of muscle creatine kinase (O-MCK). CHRN is targeted to the LC3-II-positive autophagosome for selective autophagy under catabolic condition. This process is regulated and/or mediated partly by MuRF1 and its interacting partners Bif-1/EndoB1 and SQSTM1/p62. Act, alpha-actin; CHRN, cholinergic receptor, nicotinic/nicotinic acetylcholine receptor; GMEB1, glucocorticoid modulatory element binding protein-1; MHC, myosin heavy chain; MLC, myosin light chain; MyBP-C, myosin binding prot-C; O-MCK, oxidized form of muscle creatine kinase; TnnI, TnnC, troponin I and C.\n\nFigure 4: Figure 4. MuRF1 functions in cardiac muscle. MuRF1 exhibits a protective role in the heart by inhibiting pathological heart hypertrophy. Anti-hypertrophic function of MuRF1 can partly be explained by its atrophic function and the degradation of sarcomeric proteins like in skeletal muscle. Moreover, MuRF1 inhibits the protein synthesis of hypertrophy-related genes in response to hypertrophic stimuli, via the inhibition of at least three pathways (serum response factor (SRF), c-Jun N-terminal kinases (JNK), and AKT pathways). The activation of calcineurin/NFAT (nuclear factor of activated T cells) signaling alone is sufficient to induce pathological cardiac hypertrophy. MuRF1, by down-regulating the phosphatase CnA, prevents the translocation of the nuclear factor NFAT transcription from the cytosol to the nucleus and thus the consecutive transcription of hypertrophy-related genes. Moreover, MuRF1 mediates the inhibition of PKCε translocation to focal adhesions, a critical event in the hypertrophic signaling cascade. MuRF1 also limits physiological cardiac hypertrophy by inhibiting c-Jun protein expression and phosphorylation in the presence of insulin-like growth factor 1 (IGF-1). Another cardioprotective role of MuRF1 is to reduce cardiomyocytes apoptosis occurring after ischemia/reperfusion injury (I/R). During I/R, MuRF1 targets phospho-c-Jun for degradation, blocking the transcription of pro-apoptotic genes; it is noteworthy that the inhibition of JNK or c-Jun is cardioprotective in vivo. Act, alpha-actin; CnA, calcineurin A; IGF-1, insulin-like growth factor 1; MHC, myosin heavy chain; MLC, myosin light chain; MyBP-C, myosin binding prot-C; NFAT, nuclear factor of activated T cells; SRF, transcription factor serum response factor; TnnI, TnnC, troponin I and C."
      }
    ]
  },
  {
    "id": "PMC7556243_multi",
    "image": [
      "images/PMC7556243-f1.png",
      "images/PMC7556243-f2.png",
      "images/PMC7556243-f3.png",
      "images/PMC7556243-f4.png",
      "images/PMC7556243-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Baoyuan Jiedu Decoction Alleviates Cancer-Induced Myotube Atrophy by Regulating Mitochondrial Dynamics Through p38 MAPK/PGC-1α Signaling Pathway\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. UHPLC chromatogram profiles of BJD. (A) Total ion current chromatograms of BJD. Secondary mass spectrum of the 18 main components of BJD: (B) Cytidine. (C) Guanine. (D) Indole-3-acrylic acid. (E) Chlorogenic acid. (F) 2,3,4,9-Tetrahydro-1H-β-carboline-3-carboxylic acid. (G) Isoliquiritigenin. (H) Quercetin-3β-D-glucoside. (I) Cynaroside. (J) Ferulic acid. (K) Hesperidin. (L) Formononetin. (M)α-Lactose. (N) 9S,13R-12-Oxophytodienoic acid. (O) 18-β-Glycyrrhetinic acid. (P) Bis(4-ethylbenzylidene)sorbitol. (Q) α-Linolenoyl ethanolamide. (R) Hexadecanamide. (S) Stearamide.\n\nFigure 2: Figure 2. BJD prevented LCM-induced myotube atrophy in C2C12 cells. (A) The morphological changes of myotubes in C2C12 cells (×200 magnification; scale bar: 50 μm). (B,C) The transverse diameters of myotubes in C2C12 cells (μm, n = 3). (D) The relative expression of Atrogin-1 and MuRF-1 was detected by RT-qPCR, with β-actin was used as an internal gene. (E) The expression of Atrogin-1 and MuRF-1 was detected by Western blotting, GAPDH was used as a loading control. The data are presented as the mean ± SD. **P < 0.01, ***P < 0.001.\n\nFigure 3: Figure 3. BJD enhanced the mitochondria generation. The C2C12 cells were washed with pre-cooled PBS and fixed with 0.2% glutaraldehyde at 4°C for 10 min. Then the NAO solution (10 μmol/L) was added in the dark for 10 min. The imaging was observed by a fluorescence microscope at 488 nm. The picture was ×100 magnification, and the scale bar is 100 μm.\n\nFigure 4: Figure 4. BJD improved mtDNA and increased the expression of ATPase, NRF-1, TFAM, COXIV, and CytC. (A) The relative expression of mtDNA, with β-globin was used as an internal gene. (B–F) The relative expression of ATPase, NRF-1, TFAM, COXIV, and CytC, with β-actin was used as an internal gene. (G) The expression of NRF-1, TFAM, COXIV, and CytC was detected by Western blotting, GAPDH was used as a loading control. The data are presented as the mean ± SD. *P < 0.05, **P < 0.01, ***P < 0.001.\n\nFigure 5: Figure 5. BJD treatment inhibited p38 MAPK/PGC-1α signaling pathway. (A,B) The relative expression of p38 MAPK and PGC-1, with β-actin was used as an internal gene. (C) The expression of p-p38 MAPK, p38 MAPK, and PGC-1α was detected by Western blotting, GAPDH was used as a loading control. The data are presented as the mean ± SD. ***P < 0.001."
      }
    ]
  },
  {
    "id": "PMC7556243_multi_2",
    "image": [
      "images/PMC7556243-f6.png",
      "images/PMC7556243-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Baoyuan Jiedu Decoction Alleviates Cancer-Induced Myotube Atrophy by Regulating Mitochondrial Dynamics Through p38 MAPK/PGC-1α Signaling Pathway\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. BJD alleviated gastrocnemius atrophy in xenograft cachexia mice. (A) The changes in body weight in each group. (B) The terminal body weights. (C) The gastrocnemius index. (D) The pathological pictures of gastrocnemius muscle stained by H&E (×200 magnification; scale bar: 50 μm). The data are presented as the mean ± SD. *P < 0.05, ***P < 0.001.\n\nFigure 7: Figure 7. BJD inhibited p38 MAPK/PGC-1α singling pathway in mice. (A–D) The relative expression of Atrogin-1, MuRF-1, p38 MAPK, and PGC-1α was detected by RT-qPCR, with β-actin was used as an internal gene. (E–F) The expression of Atrogin-1, MuRF-1, p-p38 MAPK, p38 MAPK, and PGC-1α was detected by Western blotting, GAPDH was used as a loading control. The data are presented as the mean ± SD. ***P < 0.001."
      }
    ]
  },
  {
    "id": "PMC7567947_multi",
    "image": [
      "images/PMC7567947-f1.png",
      "images/PMC7567947-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Lipid changes in the metabolome of a single case study with maple syrup urine disease (MSUD) after five days of improved diet adherence of controlled branched-chain amino acids (BCAA)\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Euclidian hierarchical metabolome clustering of MSUD case at both time points compared to single healthy matched control.\n\nFigure 2: Figure 2. Lipid analyte Z-scores of MSUD case at Day 1 and Day 5 study visits based on healthy control data from 20 adolescent females."
      }
    ]
  },
  {
    "id": "PMC7642974_multi",
    "image": [
      "images/PMC7642974-f1.png",
      "images/PMC7642974-f2.png",
      "images/PMC7642974-f3.png",
      "images/PMC7642974-f4.png",
      "images/PMC7642974-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"E3 Ubiquitin Ligases in Neurological Diseases: Focus on Gigaxonin and Autophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Mechanism of action and classification of E3 ubiquitin ligases causing neurological diseases in human. (A) Ubiquitination cascade. E1 enzymes activate ubiquitin (Ub) in an ATP-dependent manner, forming a thioester bound with Ub. Activated-Ub is then transferred to Ub-conjugating enzymes (E2). Finally, E3 ubiquitin ligases assist or directly catalyze the transfer of Ub to substrates. Substrates can be mono-, multi- or poly-ubiquitinated, with different types of Ub chains, to modulate various processes, including protein activation, interaction, trafficking, subcellular localization, and degradation through the 26S proteasome or the autophagy pathway. (B) E3 ligases underlying neurological diseases and their classification. The three classes of E3 (HECT, RING, and RING-HECT hybrid) are represented. E3 ligases identified as the genetic cause of neurodevelopmental and neurodegenerative diseases in human are classified within each category (sub-classes with no disease representative are not shown). The HECT and RING E3 ligases differ in the way they transfer Ub to the substrate. The HECT E3s receive Ub from E2 enzymes, form a thioester intermediate with Ub, and catalyze the transfer to the substrate. RING E3s associate with E2 enzymes and substrates and mediate the transfer of Ub from E2 to the substrate. RING E3s can function as monomers, dimers or multi-subunit RING E3s. The latter class is subdivided in different groups, among which the Cullin-RING Ligases (CRLs) are the largest E3 ligase family. SCF, ECS, CRL3 and CRL4 ligases are composed of a modular E3 core containing specific Cullins (respectively CUL1, CUL2/5, CUL3, CUL4) and RBX1 (RING-box1 proteins), and a substrate specificity module composed of an adaptor (Skp1, EloC, and DDB1) and a substrate receptor. The RING-HECT hybrid ligases (RBR for RING-between-RING) interact with E2 as the RING E3 but transfer Ub with HECT-like mechanism. Finally, particular E3 are represented (“Others”): RanBP2 does not transfer Ub but Sumo (small ubiquitin-related modifier) and is neither an HECT, nor a RING E3 ligase; TOPORS has a RING domain and is a dual E3 Ub and Sumo ligase.\n\nFigure 2: Figure 2. Scheme of the main clinical features shared by E3 ligase encoding genes causing neurodevelopmental and neurodegenerative diseases. Most of the E3 ligase genes, when mutated cause neurodevelopmental diseases (intellectual disability, encephalopathy, and epilepsy), or regionalized neuropathies (cerebellar, ocular, and pyramidal syndrome) within the CNS. Some pathologies exhibit mixed symptoms that can be part of broader multisystemic disorders. E3 ligase genes inducing peripheral neuropathies are represented by Charcot-Marie-Tooth diseases (CMT), and distal hereditary motor neuropathy (HMN). The GAN E3 ligase gene causes a disease affecting broadly the nervous system, leading to a myriad of symptoms within the peripheral and the CNS. Illustration: © www.gograph.com/ Eraxion. Genes (protein if different), names of diseases and references (in alphabetical order): ASB10, Glaucoma (Pasutto et al., 2012); CCNF (cyclinF), Amyotrophic Lateral Sclerosis and Frontotemporal dementia (Williams et al., 2016); CRBN, mental retardation (MRT2A; Higgins et al., 2004); CUL4B, mental retardation (MRXS15; Zou et al., 2007); DCAF8, Charcot-Marie-Tooth disease (CMT2; Klein et al., 2014); FBXL7, Hennekam syndrome (Boone et al., 2020); FBXO7, Parkinson syndrome (PARK15; Shojaee et al., 2008); FBXO31, mental retardation (MRT45; Mir et al., 2014); FBXO38, distal hereditary motor neuropathy (HMN2D; Sumner et al., 2013); FBXW11, neurodevelopmental syndrome (Holt et al., 2019); GAN (Gigaxonin), Giant Axonal Neuropathy (Bomont et al., 2000); HACE1, neurodevelopmental syndrome (SPPRS; Hollstein et al., 2015); HECW2, neurodevelopmental syndrome (NDHSAL; Berko et al., 2017); HERC1, neurodevelopmental syndrome (MDFPMR; Nguyen et al., 2016); HERC2, mixed with mental retardation (MRT38; Puffenberger et al., 2012); HUWE1, mental retardation (MRXST; Froyen et al., 2008); ITCH (Itch), multi-system autoimmune disease with neurodevelopmental defects (Lohr et al., 2010); KLHL7, retinitis pigmentosa (RP42; Friedman et al., 2009); KLHL15, mixed with mental retardation (MRX103; Mignon-Ravix et al., 2014); LRSAM1, CMT2P (Guernsey et al., 2010); MID1, Opitz G/BBB syndrome 1 (GBBB1; Quaderi et al., 1997); MID2, mental retardation (MRX101; Geetha et al., 2014); NEDD4L, Periventricular nodular heterotopia 7 (PVNH7; Broix et al., 2016); NHLRC1 (Malin), Lafora disease (Chan et al., 2003); PARK2 (Parkin), Parkinson disease 2 (PARK2; Kitada et al., 1998); PEX10, Zellweger syndrome (Okumoto et al., 1998; Warren et al., 1998); RANBP2* (RanBP2), acute necrotizing encephalopathy (Neilson et al., 2009); RHOBTB2, epileptic encephalopathy (EIEE64; Belal et al., 2018); RLIM (RNF12) intellectual disability (Tonne et al., 2015); RNF125, overgrowth syndrome (Tenorio et al., 2014); RNF168, RIDDLE syndrome (Stewart et al., 2009); RNF170, sensory ataxia (SNAX1; Valdmanis et al., 2011); RNF216, Gordon Holmes syndrome (GHS; Margolin et al., 2013); STUB1 (CHIP), Spinocerebellar ataxia (SCAR16, SCA48, and GHS; Shi et al., 2013, 2014; Genis et al., 2018); TOPORS, retinitis pigmentosa (RP31; Chakarova et al., 2007); TRAF3*, encephalopathy (Perez de Diego et al., 2010); TRAF7, multisystem disorder with neurodevelopmental delay (Tokita et al., 2018); TRIM2, CMT2R (Ylikallio et al., 2013); TRIM32, Bardet-Biedl syndrome (BBS11; Chiang et al., 2006); TRIM36, anencephaly (Singh et al., 2017); TRIP12, intellectual disability with or without autism (O’Roak et al., 2014; Lelieveld et al., 2016); UBE3A (E6-AP), Angelman syndrome (Kishino et al., 1997; Matsuura et al., 1997); UBE3B, Kaufman oculocerebrofacial syndrome (KOS; Flex et al., 2013); VPS11, neurodevelopmental and leukoencephalopathy (Edvardson et al., 2015; Zhang et al., 2016). Asterisk (*) are susceptibility genes for viral-induced neuropathies.\n\nFigure 3: Figure 3. Giant Axonal Neuropathy. (A) Symptoms are shown in order of occurrence: from onset in childhood in the peripheral nervous system (PNS) to adulthood in the central nervous system (CNS). (B) Neuronal features: (left) nerve cross-section in the PNS shows reduced axonal content and giant axon; (right) magnetic resonance imaging of the brain reveals white matter abnormalities. Giant axons of CNS are not represented here. (C) Cellular hallmark: (from left to right) accumulation and altered distribution of neurofilaments (NFs) in giant axons, curled hair, desmin bundles in muscles and aggregates of vimentin in skin-derived fibroblasts. Copyright with permission from BioMed Central, Springer and Elsevier.\n\nFigure 4: Figure 4. Comprehensive analysis of GAN mutations. (A) Exon-intron structure of the GAN gene and domain organization of the encoded protein Gigaxonin, with a N-terminal BTB domain and a C-terminal Kelch domain (depicted in blue, linker is called BACK domain). Mapping of the 75 mutations (see also Supplementary Table 1 for details): missense mutation (red circle), nonsense mutations (black star), mutations at splicing sites (black triangle), deletions/insertion (blue triangle) and large deletion (blue line). (B) Pie charts depicting the effects of GAN mutations. Distribution of mutation types in patients (middle): 60% are missense mutations “ms,” 17.4% of nonsense mutations “ns,” 16% of deletions/insertions “del/ins,” and 6.6% mutations at donor/accepting splicing sites “sp.” Other pie charts indicate the predominance of severe forms associated with missense mutations (left) and truncations [(right), including “ns,” “sp,” “del/ins”], representing 67.7 and 93.3% of cases, respectively. On (right), flow chart showing the influence of mutations on severity. Black and red lines indicate, respectively that the patient bearing both mutations has a mild or severe form of the disease. As example, the R545H mutation leads to a severe phenotype when found homozygous, while it is attenuated by combination with R269W, which is severe when associated to I244Fs.\n\nFigure 5: Figure 5. Gigaxonin-E3 ligase: protein structure and instability as a general effect of mutations. (A) Structural model of the BTB-BACK homodimer of Gigaxonin (purple), in complex with Cul3 (green). Some mutations are represented in red (Boizot et al., 2014). (B) Representation of the top and side views of a structural model for the β-propeller Kelch domain of Gigaxonin, whose 6-blades are shown in sequence alignment below. Some mutations are represented in red. (C) In wild-type condition (left) Gigaxonin interacts with Cul3 through its N-terminal BTB domain and binds to substrates through its C-terminal Kelch domain, hence catalyzing the transfer of ubiquitin chain from the E2 to the recognized substrate. In disease (right), GAN mutations induce a general instability of Gigaxonin, by affecting the proper folding of the BTB or Kelch domain, or impairing homodimerization and interaction with Cul3. (D) Dramatic reduction of Gigaxonin levels in patient’s cells: due to instability of the mutated protein, or degradation of the corresponding mRNA, depending on the mutation type and combination. “?”: compound heterozygous mutations await to be discovered. Copyright with permission from BioMed Central."
      }
    ]
  },
  {
    "id": "PMC7642974_multi_2",
    "image": [
      "images/PMC7642974-f6.png",
      "images/PMC7642974-f7.png",
      "images/PMC7642974-f8.png",
      "images/PMC7642974-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"E3 Ubiquitin Ligases in Neurological Diseases: Focus on Gigaxonin and Autophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Biological models for GAN: strengths and weaknesses. Summary table (A) and illustrations (B) of the cellular and animal models developed for GAN. The table highlights their ability to reproduce the cellular marker and symptoms of the pathology. Green: the model satisfies the criteria; red: the model does not meet the criteria; hatched: the model partially satisfies the criteria. IF aggregation is evidenced in all cellular and animal models. Cellular loss was observed in aging GAN cortical neurons and upon specific conditions in DRG neurons. While GAN mice exhibit only modest symptoms, the gan zebrafish stands out as the first robust animal model for GAN, reproducing both neuronal loss and loss of motility, as in patients. np. not provided; nd: not determined. gan MO: transient repression using morpholino antisense oligonucleotide; gan del: genetic deletion mutant of gan. Numbers correspond to original publications: 1: patient fibroblasts with bundling of vimentin (Pena, 1981; Bomont and Koenig, 2003); 2: iPSC-derived motor neurons from GAN patients exhibiting peripherin aggregation (Johnson-Kerner et al., 2015a); 3: GAN–/– cortical neurons showing NF aggregate (Bomont: personal data). 4: GAN DRG neurons with accumulations of α-internexin (Israeli et al., 2016); 5: GAN1Δex3–5 (Ding et al., 2006); 6: Electron micrograph of the axoplasm of GAN2Δex3–5 nerves (Ganay et al., 2011), showing abnormal packing and orientation of NFs; 7: NF inclusions in GANΔex1 brain neurons (Dequen et al., 2008); 8: gan zebrafish exhibit abnormal spinal cord architecture, abolished neuromuscular junctions (left) and impaired locomotion (right: cumulative movement of larvae in a well during 1 h). Copyright with permission from Oxford University Press, BioMed Central (John Wiley & Sons) and J Clin Invest.\n\nFigure 7: Figure 7. Functions of the Gigaxonin-E3 ligase. (A) Identified substrates for Gigaxonin include cytoskeletal components (MAPs, TBCB, IFs), Shh receptor (Ptch), autophagy core protein (ATG16L1) and transcriptional factor (NFKB). (B) Gigaxonin controls the turn-over of the IF family. Through interaction with the central α-helical rod domain, a common domain of IF proteins, Gigaxonin controls the steady-level of IF family, including neuronal (NFs, peripherin, and α-internexin) and non-neuronal (vimentin, GFAP, and keratin) IF types. This is mediated by Gigaxonin-dependent ubiquitination (as revealed for peripherin). In absence of Gigaxonin (patients and GAN models), IF proteins bundle at perinuclear region, while actin and microtubules do not show overt alteration. Excess of Gigaxonin completely destroys IFs, including bundles in GAN samples. (C) Control of the initiation of Shh signaling by Gigaxonin is essential for locomotion. In normal condition (left), Gigaxonin initiates signal transduction by degrading Shh-bound Ptch receptor, hence suppressing its constitutive inhibition on the signal transducer Smo, allowing its translocation to the primary cilium, and leading to the transcriptional activation of Gli. In absence of Gigaxonin (right), the repression of Smo is maintained by accumulated Ptch receptor, which hampers the initiation of Shh signaling and favors the generation of a repressor form of Gli. In zebrafish, this defective Shh signaling impairs motility of gan larvae (cumulative representation of the spontaneous locomotion of larvae for 1 h). This severe motility defect is caused by a dramatic remodeling of spinal cord architecture, [shortening of pMNs axons (primary motor neurons, green), defective production of sMNs (secondary motor neurons, red)], and failure to generate proper neuromuscular junctions (NMJ). This phenotype is accompanied by a muscular defect (neuronal-independent or dependent), characterized by “U-shape” myofibers instead of the normal “V-shape.” (D) Gigaxonin regulates autophagosome production. Elongation of phagophore membrane involves two ubiquitin-like conjugation systems: ATG12 and LC3 undergo transfer from E1 (ATG7) to E2 (ATG10 and ATG3) enzymes. ATG12-ATG5 subsequently forms a complex with ATG16L1, which addresses it to the nascent membrane to act as an E3 ligase for the lipidation of LC3, to generate LC3-II. Gigaxonin induces the ubiquitin-dependent degradation of ATG16L1, and its absence in GAN neurons causes a failure to generate productive autophagosomes upon autophagy induction. As a result, ATG16L1 bundles in GAN neurons, the autophagy receptor P62 accumulates and autophagosome-lysosome fusion is impaired, hence blocking autophagy flux.\n\nFigure 8: Figure 8. Focus on ubiquitin(like)-dependent regulation of cellular mechanisms shared by Gigaxonin and other E3 ligases. Cytoskeleton comprises actin, microtubules (MTs) and Intermediate Filaments (IFs). Signaling pathways, selected from their roles in spinal cord development and maintenance include WNT, Sonic Hedgehog (Shh), NOTCH and Bone Morphogenetic Protein (BMP). For Fibroblast Growth Factor (FGF) and Retinoic acid (RA), no function of E3 ligases was reported to our knowledge. As substantial proportion of E3 ligases (30%) control the autophagy pathway. Some E3 ligases act at multiple levels within the same pathways (like Itch, NEDD4L), and 23% of them exhibit functions in different pathways, with Gigaxonin, TRIM32, and CHIP crossing all pathways.\n\nFigure 9: Figure 9. Regulation of the autophagy pathway by E3 ubiquitin ligases. E3 ligases mutated in neurodegenerative diseases (in green) target core components of the autophagy machinery, from the initiation (1) to the fusion of the autophagosome to lysosomes (4) to positively (+) or negatively (−) regulate autophagic flux. Following (macro)autophagy induction, the inhibitory effect of mTORC1 on the ULK complex is lifted, allowing the activation of the ULK1/2 kinases (1), leading to a cascade of phosphorylation events that contribute to the activation of the PI3KIII complex via Beclin1, to promote PI3P synthesis on nascent phagophore (2). Interacting with PI3P, WIPI2 subsequently recruits ATG16L1 in complex with ATG12-ATG5, the E3 ligase that catalyzes the lipidation of LC3 at membranes, a step (3) required for membrane elongation and autophagosome formation. Fusion with lysosome (4) leads to the degradation of sequestered material, which can be non-specific (called bulk autophagy) or specific (called selective autophagy). Selectivity is triggered by ubiquitination of substrates [(bottom panels) mitochondria, pathogens, and Ferritin], and mediated by adaptor proteins that direct them to autophagosomes thanks to LC3-interacting region (LIR domain) and ubiquitin-associated domain (UBA) domain. “Rec” for mitophagy: p62, OPTN, NDP52, TAX1BP1, NBR1, or AMBRA1; of note, some mitochondrial proteins have a LIR domain and contribute to mitophagy. “Rec” for xenophagy: p62, NDP52, NBR1. Myco., Mycobacterium tuberculosis; Salm., Salmonella Thyphimurium. mTOR signaling, which is an upstream inhibitor of autophagy induction is also regulated by E3 ligases: through action on mTOR inhibitors (DEPTOR) and transcriptional control of autophagy genes (TFEB). Dashed line: partial demonstration of mechanistic. E3 ligase-dependent ubiquitination can trigger degradative or non-degradative routes. Several E3 ligases act at multiple steps of the autophagy pathway and can have antagonized actions."
      }
    ]
  },
  {
    "id": "PMC7647121_multi",
    "image": [
      "images/PMC7647121-f1.png",
      "images/PMC7647121-f2.png",
      "images/PMC7647121-f3.png",
      "images/PMC7647121-f4.png",
      "images/PMC7647121-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Leishmania differentiation requires ubiquitin conjugation mediated by a UBC2-UEV1 E2 complex\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Fifty-eight null mutant lines were pooled (n = 6) as procyclic promastigotes and grown to stationary phase. Cells were then induced to differentiate into axenic amastigotes in vitro or metacyclic promastigotes purified and used to infect macrophages or mice. A Experimental workflow showing the time points at which DNA was extracted for barcode amplification and next generation sequencing. The heat maps for promastigote to B axenic amastigote, C macrophage infection or D mouse infection experiments show the average proportional representation of each null mutant at each experimental time point, calculated by dividing the number of reads for null mutant-specific barcodes by the total number of reads for expected barcodes. Samples included represent promastigote time-point zero (PRO 0 h), early-log phase (PRO 24 h), mid-log phase (PRO 48 h), late-log phase (PRO 72 h), stationary phase (PRO 168 h), early axenic amastigote differentiation (AXA 24 h), post-axenic amastigote differentiation (AXA 120 h), purified metacyclic promastigotes (META), early macrophage infection (inMAC 12 h), late macrophage infection (inMAC 72 h), 3 week footpad mouse infection (FP 3) and 6 week footpad mouse infection (FP 6).\n\nFigure 2: Figure 2. Sequence alignment and structural annotation were performed using T-Coffee and ESPript 3.0 respectively for A LmUBC2 and B LmUEV1. Red boxes indicate amino acid identity, red characters show similarity within the highlighted group and blue frames highlight similarity across groups. Positions of the UBC2 HPN motif and catalytic cysteine are shown by a black line and triangle respectively. Secondary structures derived from the crystallised L. mexicana UBC2-UEV1 heterodimer (Fig 4) are represented above the sequence alignment with helices represented by spirals and beta sheets by arrows. Asterisks denote important interface residues in the L. mexicana complex. Lm, Leishmania mexicana; Tb, Trypanosoma brucei; Sc, Saccharomyces cerevisiae; Hs, Homo sapiens.\n\nFigure 3: Figure 3. A SDS-PAGE gel showing recombinant UBA1a, UBC2 and UEV1 stained with InstantBlue stain. Proteins were expressed in E. coli and purified by nickel affinity and size-exclusion chromatography. 1 μg of each protein was loaded onto the gel. B Elution profiles of UBC2, UEV1 and a 1:1 molar mix of UBC2-UEV1 presented as changes in refractive index over time. Curved lines show changes in refractive index for UBC2-UEV1 (black), UBC2 (red) and UEV1 (blue). The expected mass (as estimated from light scattering data) in kDa is indicated by a dashed line above the peak corresponding to each protein sample.\n\nFigure 4: Figure 4. A Ribbon diagram showing the crystal structure of UBC2 (green) and UEV1 (blue) in complex. The location of the N- and C-termini are highlighted along with the numbering of alpha helices (α) and beta strands (β). B Zoom-in of the conserved catalytic residues in UBC2. The HPN motif and proposed catalytic cysteine are shown as cylinders coloured by atom (red, oxygen; blue, nitrogen; yellow, sulfur). C-D Zoom-in of interface between UBC2 and UEV1 with UBC2 or UEV1 as a surface fill model respectively. Amino acid residues are shown as cylinders coloured by atom (red, oxygen; blue, nitrogen). Hydrogen bonds are denoted by dashed lines.\n\nFigure 5: Figure 5. A Thioester assay demonstrating the ability of UBA1a and UBC2 to form thioester bonds with ubiquitin. UBA1a, ubiquitin and ATP were incubated with UBC2 and UEV1 as indicated in ubiquitination assay buffer for up to 10 min at room temperature. Samples were treated with either reducing or non-reducing sample buffer and visualised by SDS-PAGE with InstantBlue stain. B Di-ubiquitin formation assay. UBA1a, ubiquitin and ATP were incubated with UBC2 and UEV1 as indicated in ubiquitination assay buffer for up to 90 min at 37°C. Reactions were then treated with reducing sample buffer and visualised by immunoblotting with either ubiquitin conjugate or K63-linked ubiquitin antibodies. C Di-ubiquitin formation assay performed as for B but with wild-type ubiquitin substituted for K63R ubiquitin where shown. D UBC2 and UEV1 were pre-incubated with UBE2N inhibitor NSC697923 as indicated for 15 min prior to setting up a di-ubiquitin formation assay as in B. For C and D, samples were treated with reducing sample buffer prior to SDS-PAGE and immunoblotting with ubiquitin conjugate antibody. Data shown in A-D are representative. No 2/V1, no UBC2 or UEV1. E Schematic summarising the findings of A-D. UBA1a activates ubiquitin in an ATP-dependent manner, allowing ubiquitin to bind to the active site of UBA1a via a thioester linkage. Ubiquitin is then transferred to UBC2 (green) which, when present in complex with UEV1 (yellow), can generate free K63-linked ubiquitin chains."
      }
    ]
  },
  {
    "id": "PMC7647121_multi_2",
    "image": [
      "images/PMC7647121-f6.png",
      "images/PMC7647121-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Leishmania differentiation requires ubiquitin conjugation mediated by a UBC2-UEV1 E2 complex\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A UBA1a, ubiquitin and ATP were incubated with UBC2, UEV1 and human E3s (BIRC2, RNF8 and HUWE1) as indicated in ubiquitination assay buffer for 1 h at 30°C. Reactions were visualised by immunoblotting with either ubiquitin conjugate, K63-linked ubiquitin or GST antibodies as shown. 2, UBC2; V1, UEV1; -, no UBC2 or UEV1; no E3, no BIRC2, RNF8 or HUWE1. B Schematic summarising the findings of A. UBA1a activates ubiquitin in an ATP-dependent manner, allowing ubiquitin to bind to the active site of UBA1a via a thioester linkage. Ubiquitin is then transferred to UBC2 which can, by interacting with the human E3s BIRC2 and RNF8, form non-K63-linked polyubiquitin chains. UEV1 inhibits this association, presumably via its interaction with UBC2.\n\nFigure 7: Figure 7. A Thioester assay showing ubiquitin transfer to UBE2W from both human UBA1 and L. mexicana UBA1a. UBE2W, ubiquitin and ATP were incubated with human UBA1 or L. mexicana UBA1a as indicated in ubiquitination assay buffer for up to 10 min at room temperature. Samples were treated with either reducing or non-reducing sample buffer and visualised by SDS-PAGE with InstantBlue stain. B UBA1a, ubiquitin and ATP were incubated with UBC2, UEV1, human UBE2W and human CHIP as indicated in ubiquitination assay buffer for 1 h at 30°C. Reactions were visualised by immunoblotting with either ubiquitin conjugate or CHIP antibodies as shown. C Schematic summarising A-B. UBA1a activates ubiquitin in an ATP-dependent manner, allowing ubiquitin to bind to the active site of UBA1a via a thioester linkage. Ubiquitin is then transferred to HsUBE2W which monoubiquitinates HsCHIP. Alternatively, HsUBE2W can ubiquitinate its own N-terminus. Once primed with monoubiquitin, UBC2-UEV1 can extend ubiquitin chains on HsCHIP. Lm, Leishmania mexicana; Hs, Homo sapiens. Where species is not indicated, proteins are from L. mexicana."
      }
    ]
  },
  {
    "id": "PMC7658010_multi",
    "image": [
      "images/PMC7658010-f1.png",
      "images/PMC7658010-f2.png",
      "images/PMC7658010-f3.png",
      "images/PMC7658010-f4.png",
      "images/PMC7658010-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Fluidity and Lipid Composition of Membranes of Peroxisomes, Mitochondria and the ER From Oleic Acid-Induced Saccharomyces cerevisiae\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Isolation of peroxisomes by isopycnic density gradient centrifugation. Cells of S. cerevisiae wild-type strain were grown under oleate-inducing conditions for 16 h. A post nuclear supernatant (PNS) was prepared, and organelles were separated on an OptiPrepTM/sucrose gradient. Fractions were collected from the bottom of the gradient. Equal volumes of the indicated gradient fractions were separated by SDS-PAGE and analyzed by (A) immunoblotting using antibodies against Pcs60p (peroxisomal matrix protein), Cta1p (catalase; peroxisomal matrix protein), Pex11p (peroxisomal membrane protein), Tom40p and Por1p (mitochondrial outer membrane protein), Tim23p (mitochondrial inner membrane protein), Kar2p (ER luminal protein), Dpm1p (ER membrane protein), ALP (vacuole), and Fbp1p (cytosol), or by (B) silver staining. Peroxisome-containing fractions (3–5) were pooled, enriched and used for fluidity and lipidomic analysis. Fractions of mitochondria and ER containing membranes (13–19) were processed for further purification (Figure 2).\n\nFigure 2: Figure 2. Separation of mitochondria and ER by sucrose density gradient centrifugation. Enriched fractions 13–19 (mitochondria + ER) gained after the first isopycnic density gradient centrifugation were loaded onto a dicontinuous sucrose gradient. Fractions were collected from the top of the gradient. Equal volumes of the indicated gradient fractions (fraction 17 diluted 1:1) were separated by SDS-PAGE and analyzed by (A) immunoblotting using antibodies against Pcs60p (peroxisomal matrix protein), Cta1p (catalase; peroxisomal matrix protein), Pex11p (peroxisomal membrane protein), Tom40p and Por1p (mitochondrial outer membrane protein), Tim23p (mitochondrial inner membrane protein), Kar2p (ER luminal protein), Dpm1p (ER membrane protein), and ALP (vacuole), or by (B) silver staining. ER-peak fractions (5–11) and peak fractions of mitochondria (17–20) were used for lipidomic and fluidity measurements.\n\nFigure 3: Figure 3. Comparative analysis of isolated peroxisomes, mitochondria and ER. Equal amounts (20 μg) of the postnuclear supernatant, purified peroxisomes, the mitochondria/ER pool after the first purification step, as well as purified mitochondria and ER were separated by SDS-PAGE and analyzed by immunoblotting using antibodies against Fox1p (peroxisomal matrix protein), Pcs60p (peroxisomal peripheral membrane and matrix protein), Pex11p (peroxisomal membrane protein), Kar2p (ER luminal protein), Dpm1p (ER membrane protein), Tom40p (mitochondrial outer membrane protein) and Tim23p (mitochondrial inner membrane protein).\n\nFigure 4: Figure 4. Membrane fluidity. Generalized polarization (GP) values measured on isolated Peroxisomes (red), Mitochondria (blue), and ER (green), indicating a slightly higher fluidity (lower GP value) for peroxisomal membranes, compared to mitochondria and ER membranes. Shown are individual measurements and the mean values with standard deviation from the three independent experiments. Statistical analysis: Ordinary One-way ANOWA with multiple comparisons; ****P < 0.0001; ***P = 0.0003; ns: not significant.\n\nFigure 5: Figure 5. (A) Selected lipidomics data of isolated organelles. Peroxisomes (red, Per), mitochondria (blue, MT), and ER (green), indicating generally high levels of phospholipids (PC, PE, and PI), and in comparison, increased levels of PI for peroxisomes. Shown are mean values with standard deviation from three indipendent experiments. For more detailed lipidomics data see Supplementary Figure 1. (B) Lipidomic data of PE and PI in Peroxisomes, Mitochondra and ER were from three independent experiments. Mole percentages of the total amount of lipids are shown on the y-axis (sum amount of a lipid class divided by the total amount in the sample, multiplied by 100)."
      }
    ]
  },
  {
    "id": "PMC7672940_multi",
    "image": [
      "images/PMC7672940-f1.png",
      "images/PMC7672940-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Deciphering the modifiers for phenotypic variability of X-linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Possible modifiers associated with disease phenotypic variability. Phenotypic heterozygosity observed in a monogenic disorder can be due to the association of modifying factors such as genetic, epigenetic, and/or environmental factors, commonly termed as “modifiers.”\n\nFigure 2: Figure 2. Factors determining the onset of symptoms of cerebral demyelination. Migration of immune cells into the brain could be a rate-limiting step in the appearance of symptoms of cerebral demyelination. Onset of the migration across the blood brain barrier could be precipitated by environmental triggers, genetic or epigenetic factors and ATP Binding Cassette Subfamily D Member 1 (ABCD1) deficiency acting either alone or in concert, marking the onset of brain inflammation leading to cerebral symptoms."
      }
    ]
  },
  {
    "id": "PMC7675186_multi",
    "image": [
      "images/PMC7675186-f1.png",
      "images/PMC7675186-f2.png",
      "images/PMC7675186-f3.png",
      "images/PMC7675186-f4.png",
      "images/PMC7675186-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"CDK5 Inhibition Abrogates TNBC Stem‐Cell Property and Enhances Anti‐PD‐1 Therapy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Aberrant expressions of CDK5 and CDK5R1 clinically correlate with TNBC progression. Immunohistochemistry (IHC) detection of A) CDK5 and B) CDK5R1 expression in tissue microarrays, classified into early‐stage (I/II, n = 26) and late‐stage (III/IV, n = 44). Scale bars, 500 × 10−6 m for (5 ×) and 50 × 10−6 m for (40 ×). C) Histoscores for CDK5 and CDK5R1 staining in different stages. D) Expression of CDK5 and CDK5R1 in each clinical specimen was quantified using TissueGnostics GmbH FACS‐like Tissue Cytometry (TissueFAXS Plus). E) Kaplan–Meier analysis of the overall survival (OS) of TNBC patients according to CDK5 expression: upregulated (red line, n = 54, median OS 84.9 months), and downregulated (blue line, N = 24, OS 151 months). Data represent the analysis of n patient specimens per group, mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001.\n\nFigure 2: Figure 2. CDK5 blockade inhibits metastasis and stemness in the TNBC mouse model. A) The growth of orthotopic 4T1 tumors in mice with different treatments as indicated (n = 6 for each group). B) Left, representative images of tumor tissues isolated from mice described in A). Right, mean tumor weights are shown. C) Representative bioluminescence images of 4T1‐bearing mice with indicated treatments. D) Left, representative pictures of hematoxylin and eosin‐stained (H&E) sections of lung tissues. Right, quantification of pulmonary metastatic nodules. E) Representative flow cytometric analysis of CD44+CD24−/low BCSC population in 4T1 tumors. F) Immunoblot analysis of CSCs marker, ALDH1, expression in tumor tissues with or without Rosc treatment. β‐Actin was analyzed as a loading control. The ALDH1 expression level was quantified using ImageJ. G) Representative IHC images for ALDH1 expression in 4T1 tumor tissues with indicated treatments. The ratios of ALDH1‐positive cells in each field were quantified. H) Gene set enrichment analysis of alterations in BCSC signature genes after CDK5 inhibition. I) Immunoblot analysis of CDK5 and CDK5R1 expression in each subtype of 4T1 cells as indicated. J) Colony formation analysis of each subtype of 4T1 cells. K) Mammosphere formation in 4T1 cells treated as indicated. Left, a representative image of mammospheres. Right, quantification of mammospheres, counted using a microscope with size ≥ 50 µm. Scale bars = 50 µm. L) Representative flow cytometric analysis of CD44highCD24−/low BCSC population in mammospheres. M) mRNA level of BCSC‐related signature genes (Aldh1, Fgfr1, Notch1, Oct4, and Sox1). Data represent mean ± SEM. The experiments were repeated at least twice to observe concordant statistical significance. *p < 0.05, **p < 0.01, ***p < 0.001.\n\nFigure 3: Figure 3. CDK5 controls CD44v isoform switching promoting TNBC stemness. A) Sashimi plot showing a large number of reads spanning CD44 exons 5 and 14 junctions in Rosc‐treated cells. B) RT‐PCR detection of CD44 variant fragment expression. C) Representative immunofluorescence microscopy images for the analysis of CD44v expression (red) in 4T1‐bearing mice with/without Rosc treatment. Nuclei were counterstained with DAPI. Scale bars, 50 and 20 µm for the magnified field. D) Flow cytometric analysis of CD44v expression in 4T1 tumors. E) Mammosphere formation assay detecting self‐renewal capacity. The genetic recovery experiment was conducted by overexpressing CD44s/CD44v in CDK5‐KO cells as indicated. F) Immunoblotting analysis of the activation of CD44v downstream EGFR signaling pathway. Data represent mean ± SD. *p < 0.05, **p < 0.01, ***p < 0.001.\n\nFigure 4: Figure 4. PPARγ phosphorylation is necessary for CDK5‐induced CD44v class switching. A) Representative IHC images for CDK5 and pho‐PPARγ expression in tissue microarrays, including normal breast and tumor tissues and negative and positive lymph nodes. Typical staining in the box region was magnified and shown in the adjacent columns. Scale bars, 20 × 10−6 m for (5×) and 50 × 10−6 m for (magnified). B) Correlation of CDK5 expression and phosphorylation level of PPARγ (n = 70, Pearson's correlation coefficient R and p‐value are shown). C) Histoscores of pho‐PPARγ IHC staining. Normal breast tissue (n = 11); stage 1 (n = 26) and stage 2 (n = 44). D,E) Immunoblotting analyzing the expression of phosphorylation of PPARγ at the Ser273 site in 4T1 cells after CDK5 interruption. D) Rosc treatment; E) CDK5 knockout. The levels of pho‐PPARγ were semi‐quantified according to the gray value calculated using ImageJ (bottom panel). F) CD44v‐targeted RT‐PCR detection. Examination of CD44v expression using G) immunoblotting and H) flow cytometry in 4T1 tumors after SR‐1664 treatment. I) Mammosphere formation assay (MFA) detecting the self‐renewal capacity of transgenic 4T1 cells as indicated. J) qPCR detection of stemness‐related gene expression. Data represent mean ± SD. *p < 0.05, **p < 0.01, ***p < 0.001.\n\nFigure 5: Figure 5. Interruption of the CDK5/pho‐PPARγ axis induces fate alteration of TNBC stem cells. A) 4T1 cells were overexpressed with PPARγ‐S273A and PPARγ‐S273D. Cycloheximide treatment revealed the half‐life of PPARγ with a different mutation. B) The transgenic cells described in (A) were pre‐incubated with MG132 (10 × 10−6 m) for 2 h, then the cell lysates were subjected to ubiquitination detection. C) Immunoblotting analysis of ESPR1 expression in transgenic 4T1 cells as indicated (top) or after incubation with Rosc in different concentrations (bottom). D) RT‐qPCR detection of the expression of ESRP1 at the mRNA level. E) Co‐immunoprecipitation (co‐IP) assay analyzing the interaction between PPARγ and ESRP1 (top). The interaction was further confirmed using reverse co‐IP (bottom). F) Representative fluorescence confocal microscopy images analyzing the co‐localization (yellow) between PPARγ (red) and ESRP1 (green) in different treatments as indicated. Nuclei are stained with DAPI (blue). Scale bars, 50 µm. G,H) In 4T1 cells with different treatments as indicated, cycloheximide treatment examined the half‐life of ESRP1. G) Immunoblotting detected the residual of ESRP1 at the protein level and H) consequently quantified it by normalizing the intensity of the actin band. I) Transient overexpression of ESRP1 in CDK5‐KO and PPARγ‐S273A cells. MFA detected self‐renewal capacity. J) CD44v‐targeted RT‐PCR detection examined CD44v generation. K) Immunoblotting detected CD44v expression in the indicated cells after ESRP1 transient overexpression. Data represent mean ± SD. *p < 0.05, **p < 0.01, ***p < 0.001."
      }
    ]
  },
  {
    "id": "PMC7675186_multi_2",
    "image": [
      "images/PMC7675186-f6.png",
      "images/PMC7675186-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"CDK5 Inhibition Abrogates TNBC Stem‐Cell Property and Enhances Anti‐PD‐1 Therapy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Pharmacological inhibition of the stemness transformation of tumor cells enhances anti‐PD‐1 therapeutic efficacy. A) Therapy regimen (top panel) and mean tumor volume of orthotopic 4T1‐bearing mice treated with vehicle or Rosc (2 mg kg−1), combinational treatment with isotype and anti‐PD‐1 antibodies (100 mg per mouse) for every five days (n = 8, 1 dead in the control group, bottom panel). B) Representative photographs of 4T1 tumor tissues isolated at the time of termination of the experiment (scale bars, 1 cm). Tumor weights are presented in the right panel. C) Representative photographs of lung metastasis are shown in the left panel, and quantification of metastatic sites is shown in the right panel. D) Kaplan–Meier survival analysis for the overall survival of mice. E) Representative IHC images of Ki‐67 and ALDH1 in 4T1 tumors with indicated treatments. Apoptosis was detected using the TUNEL assay. Scale bars, 50 µm. F) Quantification of CD3+ T‐cell, G, left) CTL, and G, right) Treg populations and H) the ratio of CTLs/Tregs in 4T1 tumors at days 14 and 28 post tumor graft (n = 6) using flow cytometry. I) Representative flow cytometry images and quantification of IFN‐γ expression in CD8+ TILs (n = 6). J,K) Examination of the therapeutic effects of the combined treatment with anti‐PD‐1 and SR‐1664 in 4T1 tumors. J) mean tumor volumes were recorded at the indicated times. K) The overall survival of each group was analyzed using the Kaplan–Meier survival analysis. Data represent mean ± SD. *p < 0.05, **p < 0.01, ***p < 0.001.\n\nFigure 7: Figure 7. Schematic summary. The mechanisms underlying TNBC stemness transformation. CDK5 expression increases during TNBC cell stemness transformation, and CDK5 phosphorylates PPARγ at Ser273 and modulate its E3 ligase activity. This alteration stabilizes ESRP1 and promotes CD44v isoform generation. CD44v isoform switching causes stemness transformation and metastasis. CDK5 inhibition abrogates CD44v isoform switching and enhances anti‐PD‐1 therapy. (up arrow for increase, down arrow for decrease)"
      }
    ]
  },
  {
    "id": "PMC7691522_multi",
    "image": [
      "images/PMC7691522-f1.png",
      "images/PMC7691522-f2.png",
      "images/PMC7691522-f3.png",
      "images/PMC7691522-f4.png",
      "images/PMC7691522-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cerebellar and hepatic alterations in ACBD5-deficient mice are associated with unexpected, distinct alterations in cellular lipid homeostasis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Expression of ACBD5 in selected tissues of Acbd5+/+ and Acbd5−/− mouse strains as determined by RT-qPCR. GAPDH expression was measured for calculation of the ΔCT values. Relative expression in the tissues was normalized to Acbd5+/+ liver tissue (set to 1.0). b Expression of ACBD4 determined as above. c Antibody staining for ACBD5 in MEFs from Acbd5+/+ and Acbd5−/− mouse strains (green). PEX14 was labeled as a marker for peroxisomes (magenta). Bar graphs show data means with standard deviations. d Peroxisomes (antibody: PEX14) in MEF cells after 12 h and 24 h incubation with DHA. Narrow cut-outs represent ×4 magnifications from the images placed directly above. e Quantification of cellular peroxisome number, (f) total peroxisome area covered per cell, (g) average particle size, and (h) average index of circularity in MEFs incubated in 150 µm DHA. Box plots depict the interquartile range, medians, and minima maxima (No. of experiments = 6250 cells were quantified in each group, *p < 0.05, **p < 0.01, ***p < 0.001; unpaired t-test, two-sided).\n\nFigure 2: Figure 2. a Habitus of 1-year-old Acbd5−/− mice—the animals show examples for kyphosis and hind limb clasping observed in this study. b C26:0/C22:0 ratios of acyl-CoA concentrations in plasma and tissues of 3 months aged Acbd5+/+ and Acbd5−/− mice (n = 5/gender). c Average body weight of Acbd5−/− and Acbd5+/+ male and female mice (n = 8 per gender and age). d Composite phenotype scores for qualitative tests for hind limb clasping, ledge test, gait, and kyphosis observed in male and female Acbd5−/− and Acbd5+/+ mice (n = 8 per gender and age). Each test was separately scored using values from 0 (not affected) to 3 (severely affected) with a combined score up to 12 for all four measures15. Box plots depict the interquartile range, medians, and minima/maxima, line graphs show means with standard deviations (*p < 0.05, **p < 0.01, ***p < 0.001; unpaired t-test, two-sided).\n\nFigure 3: Figure 3. a Visualization of Purkinje cells (calbindin, blue), astro- (GFAP, green) and oligodendroglia (MBP, red) in cerebelli of 1-year-old male Acbd5−/− and Acbd5+/+ mice. b Magnification of the granular layer from the overviews depicted in (a). Arrows highlight swellings in Purkinje cells axons. Note that axonal swellings were either found still surrounded or without a myelin layer as indicated by the MBP signal (red). c Overviews of microglia in the cerebelli of Acbd5−/− and Acbd5+/+ mice; microglia was stained with antibodies against IBA-1 (green); for orientation, Purkinje cells are visualized by calbindin antibodies (blue). Note the presence of activated, ameboid microglia in the Acbd5−/− cerebelli. d Quantification of Purkinje cell densities in cerebelli from 1-year-old Acbd5−/− and Acbd5+/+ males. (n = 7, in average 12 mm Purkinje cell layer/animal). e Quantification of axon swelling found in Purkinje cell axons of the granular layer (n = 7, quantification of in average 2 mm2 granular layer/animal). f, g Quantification of total number and number of amoeboid microglia in the cerebellar cortex of 1-year-old Acbd5−/− and Acbd5+/+ (n = 4; quantification of in average 4 mm2 of cerebellar cortex/animal). h Immunoblots against MBP and PLP to estimate axon myelinization in the cerebellum (full size immunoblots are shown in Supplementary Fig. 7). Actin was applied as a loading control and used for normalization of the (i) MBP and PLP intensity quantification. All box plots depict the interquartile, medians, and minima/maxima, all bar graphs data means with standard deviations (*p < 0.05, **p < 0.01, ***p < 0.001; unpaired t-test, two-sided).\n\nFigure 4: Figure 4. a Images visualizing distribution of excitatory (VGLUT1, VGLUT2) and inhibitory synapses (VGAT) in the cerebellar molecular layer (green). For orientation, Purkinje cells are marked by calbindin antibodies (blue); VGAT and VGLUT2 were labeled in parallel using different fluorophore-coupled secondary antibodies but for clarity reasons are both shown in separate images. b Quantification of fluorescent signal densities for VGLUT1, VGLUT2, and VGAT in the cerebellar molecular layer. (n = 5, in average 0.13 mm2 molecular layer/animal). c Colocalization of calbindin (blue) and ankyrinG (red) antibody signals were used to define the AIS in Purkinje cells. The gap between an AIS (red) and correspondent Purkinje cell soma (blue) is highlighted by arrowheads in both images. d Quantification of length and axonal position of the Purkinje cell AIS (n = 5, >50 AIS/animal). For orientation, the cerebellar molecular layer is indicated by ML in all images (*p < 0.05, **p < 0.01, ***p < 0.001; unpaired t-test, two-sided; whisker plots depict the interquartile range, medians, and minima/maxima).\n\nFigure 5: Figure 5. a Representative HE staining of livers from Acbd5+/+ and Acbd5−/− mice. b Representative images of lipid droplets visualized by oil-red staining in livers from Acbd5+/+ and Acbd5−/− mice. c Peroxisomes in hepatocytes from Acbd5+/+ and Acbd5−/− mice; peroxisomes are visualized by Pex14 antibody staining (green), antibodies against ZO1 (tight junctions, magenta) were used to outline hepatocyte cell boundaries. d Quantification of lipid droplets (>2 µm) in livers from Acbd5+/+ and Acbd5−/− mice (n = 5, quantification based on 0.075 mm2/liver). e Quantification of peroxisome abundance in hepatocytes as shown in (c), data were quantified as ratio of total peroxisome (PO) covered per hepatocyte (n = 5 animals/group, 0.0 5 mm2/liver. (*p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001; unpaired t-test, two-sided; all box plots depict the interquartile range, medians and minima/maxima)."
      }
    ]
  },
  {
    "id": "PMC7691522_multi_2",
    "image": [
      "images/PMC7691522-f6.png",
      "images/PMC7691522-f7.png",
      "images/PMC7691522-f8.png",
      "images/PMC7691522-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cerebellar and hepatic alterations in ACBD5-deficient mice are associated with unexpected, distinct alterations in cellular lipid homeostasis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a Representative EM images of hepatocytes from Acbd5+/+ (WT) and Acbd5−/− mice (n = 3, age 3 months) with peroxisomes labeled by alkaline DAB staining. b Average peroxisome abundance in hepatocytes. c Immunoblots from liver homogenates (n = 5/group) detecting proteins related to pathways involved in cellular lipid metabolism. L-BP—peroxisomal L-bifunctional protein, Thiolase—peroxisomal 3-ketoacyl-CoA thiolase, ATPA—ATP synthase subunit alpha (full size immunoblots are shown in Supplementary Fig. 8). d Relative average intensities of the proteins detected in (c) after normalization against actin. e Peroxisomal protein abundance in subcellular liver fractions (full size immunoblots are shown in Supplementary Fig. 9). PNS—post-nuclear supernatant, HM—heavy mitochondrial fraction, LM—light mitochondrial fraction, FL—fluffy LM layer, MIC—microsomal fraction, CYT—cytosol, G—gradient fractions (density increasing with numbers), L-BP—peroxisomal L-bifunctional protein, ATPA—ATP-synthase, subunit α. Columns G1 (low density)—G5 (high density) represent fractions from the final density gradient. Note that G5 and G4 comprise highly pure peroxisome fractions (see Islinger et al. 2). f Acyl-CoA oxidase activities in PNS and isolated peroxisome fractions (G4 from e). g Total protein yields in peroxisome fraction (G4 + G5) isolated from livers of Acbd5+/+ and Acbd5−/− mice (average from five isolations). h Representative 3D reconstruction of serial EM sections (resolution in x, y, z-axis: 3.5 × 3.5 × 50 nm), peroxisomes are shown in magenta, mitochondria in green and ER cisternae in gray. For estimation of organelle sizes see (a). i Proportion of peroxisomes showing membrane contact sites with at least one other organelle (0.01 mm2/liver from the EM images were used for quantification). j Average minimum distance observed between ER cisternae and peroxisomes or mitochondria calculated from the 3D-reconstructions (all box plots depict the median, interquartile range, and minima/maxima; all bar graphs show data means with standard deviations, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001; unpaired t-test, two-sided).\n\nFigure 7: Figure 7. Analysis of (a) ether phospholipids (PC[O], PE[O]) and (b) ether glycerolipids (DG[O], TG[O]) in livers and cerebelli of Acbd5−/− and Acbd5+/+ male mice. c Quantification of docosahexaenoic acid-containing lyso-phosphatidylcholine (LPC(22:6)) and lyso-phosphatidylethanolamine (LPE(22:6)). d Quantification of eicosapentanoic acid-containg lyso-PC (LPC(20:5)) and Lyso-PE (LPE(20:5)). Total lipid levels are defined as the summation of the relative abundance of all identified phospholipid species of the same class normalized to the corresponding internal standard, assuming identical response with respect to internal standard. The whisker blots depict the median, interquartile range, and the maxima/minima (*p < 0.05, **p < 0.01, ***p < 0.001; unpaired t-test, two-sided).\n\nFigure 8: Figure 8. Comparison of the fatty acid composition detected in (a) lyso-phosphatidylcholines (LPC), (b) phosphatidylcholines (PC), (c) phosphatidylethanolamines (PE) and (d) triacylglycerols (TG) from liver and cerebellum of Acbd5−/− and Acbd5+/+ male mice (value obtained from 5 one-year-old males per experimental group); (*p < 0.05, **p < 0.01, ***p < 0.001, unpaired t-test, two-sided).\n\nFigure 9: Figure 9. Fatty acid elongation is performed at the ER from stored LCFA. Peroxisomes might control FA over-elongation by a competitive import of VLCFA, requiring peroxisome-ER contact sites for their full productivity. ACBD5 disruption prevents peroxisomal import of VLCFA thereby accumulating substrates for elongation of VLCFA to UCLFA, which are subsequently incorporated into membrane lipids. Likewise the C24:6 n-3 precursor of DHA, which has to be chain-shortened by one round of peroxisomal β-oxidation is further elongated and desaturated to polyenoic PUFAs. Ether lipids are synthesized in peroxisomes up to the 1-O-alkyl-2-hydroxy-sn-glycerophosphate intermediates. Subsequent conversion to 1-O-alkyl-2-acyl-sn-glycerols and at last ligation of a PE or PC head group in sn3-position to yield the mature ether-phosphoglycerolipid is performed at the ER membrane. As revealed by lipidomics, ACBD5 disruption apparently induces formation of monoalkyl-diacyl-glycerols, which are ultimately rerouted to lipid droplets. Currently, the significance of peroxisome-ER contact sites is not fully understood but may contribute to a regulatory network controlling membrane ether-lipid formation."
      }
    ]
  },
  {
    "id": "PMC7691570_multi",
    "image": [
      "images/PMC7691570-f1.png",
      "images/PMC7691570-f2.png",
      "images/PMC7691570-f3.png",
      "images/PMC7691570-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A Proposed Diagnostic Algorithm for Inborn Errors of Metabolism Presenting With Movements Disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Percentage of movement disorders in a series of 231 inborn error of metabolism disorders. Ataxia and dystonia are the most frequent MDs in IEMs, comprising about 60% of the disorders. HRS and myoclonus are the least frequent MD and for this reason, the most useful MD in guiding the diagnosis of a definite IEM.\n\nFigure 2: Figure 2. A proposed algorithm for the diagnosis of inborn error of metabolism in childhood-onset movement disorders. The most important steps of this algorithm are step 1 “Red Flags for IEMs” and step 6 “Rethink of treatable IEMs.” It is important to highlight that treatable IEMs should always be taken into consideration. The rationalization of the different steps is developed in the text of the article.\n\nFigure 3: Figure 3. Radiological patterns in selected inborn errors of metabolism. (A) Mitochondrial short-chain enoyl-CoA hydratase 1 deficiency (ECHS1). MRI (T2W) showing bilateral symmetric signal hyperintensity in globus pallidus and a small cavitation in the left globus pallidus. (B) Type 3 Gaucher disease (GBA). MRI (T1W) showing decrease volume of white matter and hydrocephalus. (C) Glutaric aciduria type 1 (GCDH). MRI (T2 FSE) showing bilateral symmetric signal hyperintensity in putamen and globus pallidus and posterior periventricular white matter abnormalities. (D) Rhizomelic chondrodysplasia punctata, type 1 (PEX7). MRI (T2) showing bilateral symmetric posterior periventricular white matter hyperintensity and ventriculomegaly. (E,F) L-2-hydroxyglutaric aciduria (L2HGA). MRI (T2 and FLAIR) showing bilateral diffuse cerebral white matter and dentate nuclei hyperintensities. (G) Methylmalonic aciduria and homocystinuria, cblC type (MMACHC). MRI (T1) showing a very thin corpus callosum. (H) Aicardi-Goutières syndrome 2 (RNASEH2B). CT showing multiple calcifications in basal ganglia.\n\nFigure 4: Figure 4. Cranial proton magnetic resonance spectroscopy (MRS). (A) Leigh syndrome (NDUFS4). Magnetic resonance spectroscopy using intermediate echo time (144 milliseconds) at the right caudate nuclei reveals the presence of an obvious inverted doublet of lactate at 1.33 ppm. (B) Cerebral creatine deficiency syndrome 1 (SLC6A8). Magnetic resonance spectroscopy using intermediate echo time (144 milliseconds) at the posterior periventricular white matter level reveals low creatine peak at 3.0 ppm. Cho, choline; Cr, creatine; NAA, N-acetyl aspartate."
      }
    ]
  },
  {
    "id": "PMC7718247_multi",
    "image": [
      "images/PMC7718247-f1.png",
      "images/PMC7718247-f2.png",
      "images/PMC7718247-f3.png",
      "images/PMC7718247-f4.png",
      "images/PMC7718247-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomes form intralumenal vesicles with roles in fatty acid catabolism and protein compartmentalization in Arabidopsis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a, b Z-projections of peroxisomes imaged using mRuby3 channel (magenta) of 8-day-old seedling cotyledon epidermal cells expressing mNeonGreen-mPTSPEX26 (a) or mPTSPEX22-mNeonGreen (b) and mRuby3-PTS1. c Merged mNeonGreen-mPTSPEX26 (green) and mRuby3-PTS1 (magenta) channels from (a). d Cross-section of peroxisome boxed in (c). e Merged mPTSPEX22-mNeonGreen (green) and mRuby3-PTS1 (magenta) channels from (b) reveals peroxisomes and fluorescence resembling ER. f Cross-section of peroxisome boxed in (e). g Z-projection of 4-day-old cotyledon epidermal cells expressing mNeonGreen-mPTSPEX26 (green) and mRuby3-PTS1 (magenta) show ILVs in all peroxisomes with a resolvable lumen. h Cross-section of peroxisome boxed in (g). i Z-projection of 3-day-old cotyledon epidermal cells expressing mPTSPEX22-mNeonGreen (green) and mRuby3-PTS1 (magenta) shows ILVs in peroxisomes and extra-peroxisomal fluorescence resembling ER. j Cross-section of peroxisome boxed in (i). k Cross-section of cotyledon cell expressing mPTSPEX26-mNeonGreen (green) and mRuby3-PTS1 (magenta) showing inner peroxisomal membranes with tubular morphology. l Cross-section of cotyledon epidermal cells expressing mNeonGreen-mPTSPEX26 (green) and stained with FM4-64 (magenta), which marks plasma membrane and endosomes (e.g., arrowheads). m Z-projection of cotyledon epidermal cells of atg7-4 expressing mNeonGreen-mPTSPEX26 (green) and mRuby3-PTS1 (magenta) showing abundant peroxisomal ILVs remain when autophagy is prevented. n Cross-section of hypocotyl cells expressing mRuby3-PTS1 (magenta) without a membrane reporter showing nonfluorescent “holes” in peroxisomes.\n\nFigure 2: Figure 2. a, b Z-projections of cotyledon epidermal cells of a 4-day-old seedling expressing mNeonGreen-mPTSPEX26 (green) and mRuby3-PTS1 (magenta) imaged with high-magnification spinning disk confocal microscopy over 5 h (a) or lower-magnification scanning confocal microscopy over 9 h (b). Individual peroxisomes are designated with differently colored arrowheads. c Diameters of individual peroxisomes marked with arrowheads of same color in panel (b).\n\nFigure 3: Figure 3. a Diagram of dominant-negative ESCRT constructs driven by the β-estradiol-inducible pXVE promoter system18. b Dominant-negative ESCRT derivatives exhibit estradiol-dependent accumulation and do not impair peroxisomal protein processing. Immunoblots of 5-day-old seedlings grown without or with 25 µM β-estradiol are shown. The PTS2 signal region of the PMDH precursor is cleaved from mature PMDH in the peroxisome lumen. Precursor accumulation in the pex12-1 mutant79 reflects protein import defects. c ESCRT disruption impairs peroxisomal ILV formation. Cotyledon epidermal cells are shown of 5-day-old seedlings expressing mNeonGreen-mPTSPEX26 (green) and mRuby3-PTS1 (magenta) and lacking (control) or carrying constructs expressing dominant-negative SNF7L22W or VPS4E232Q grown with DMSO (mock) or β-estradiol. d ESCRT disruption causes enlarged peroxisomes. Peroxisome diameter was quantified from images of four seedlings (Supplementary Fig. 2) expressing mNeonGreen-mPTSPEX26 and mRuby3-PTS1 and grown without (gray) or with (blue) 25 µM β-estradiol to induce SNF7L22W or VPS4E232Q expression. Boxes show second and third quartiles, horizontal lines are medians, and whiskers encompass data points up to 1.5 times the interquartile range past the box ends. Student’s two-tailed unpaired t tests were used to compare peroxisome size with and without β-estradiol.\n\nFigure 4: Figure 4. a, b Enlarged peroxisomes in mutants with impaired β-oxidation show disrupted ILV formation. Wild-type seedlings and various mutants with impaired β-oxidation expressing mNeonGreen-mPTSPEX26 (green) and mRuby3-PTS1 (magenta) were imaged over several days; cross-sections (a) and peroxisome diameters (b) are shown. Boxes show second and third quartiles, horizontal lines are medians, and whiskers encompass data points up to 1.5 times the interquartile range past the box ends. c Magnified peroxisome cross-sections show ILVs in wild-type peroxisomes dispersed in the lumen and residual ILVs in pxn-4, acx2-2, and mfp2-8 aggregated near the outer membrane. d Z-projections of peroxisomes in root cells show wild-type peroxisomes with densely packed inner membranes and pxa1-1 and pxn-4 pxa1-1 peroxisomes lacking most inner membranes.\n\nFigure 5: Figure 5. a Dominant-negative ESCRT induction impairs lipid mobilization. Z-projections of cotyledon epidermal cells of seedlings expressing mNeonGreen-mPTSPEX26 (green) and mRuby3-PTS1 stained with monodansylpentane (MDH) to mark lipid droplets (magenta) and grown with DMSO (mock) or β-estradiol to induce SNF7L22W expression. b Lipid droplet diameter in SNF7L22W seedlings from panel (a). Boxes show second and third quartiles, horizontal lines are medians, and whiskers encompass data points up to 1.5 times the interquartile range past the box ends. Student’s two-tailed unpaired t tests were used to compare lipid droplet size with and without β-estradiol. c Peroxisomal ILVs do not accumulate neutral lipids. Cross-section cotyledon epidermal cells from wild-type or acx2-2 expressing mNeonGreen-mPTSPEX26 (green) and lipid droplets stained with MDH (magenta)."
      }
    ]
  },
  {
    "id": "PMC7729378_multi",
    "image": [
      "images/PMC7729378-f1.png",
      "images/PMC7729378-f2.png",
      "images/PMC7729378-f3.png",
      "images/PMC7729378-f4.png",
      "images/PMC7729378-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Aspirin alleviates denervation-induced muscle atrophy via regulating the Sirt1/PGC-1α axis and STAT3 signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Aspirin alleviated denervated muscle atrophy. (A) Typical laminin staining images of muscle fiber cross-sections of the tibialis anterior (TA) muscle (bar: 20 μm); (B) statistical chart of muscle wet weight ratio of TA muscle; (C) statistical chart of cross-sectional area of TA muscle fiber. ***, P<0.001 and ****, P<0.0001 versus Ctrl group; ###, P<0.001 verbs Den group.\n\nFigure 2: Figure 2. Aspirin inhibited the hydrolysis of ubiquitin proteasome in denervated skeletal muscle. (A) Typical western blot images of myosin heavy chain (MHC), Cyclooxygenase 2 (COX2), muscle specific E3 ubiquitin ligase Muscle-specific RING finger-1(MuRF-1) and muscle atrophy F-box (MAFbx). (B) Statistical chart of relative expression of MHC, COX2, MAFbx and MuRF1. ***, P<0.001 and ****, P<0.0001 versus Ctrl group; #, P<0.05, ##, P< 0.01 and ###, P< 0.001, vs. Den group.\n\nFigure 3: Figure 3. Aspirin inhibited mitochondrial autophagy in denervated skeletal muscle. (A) Ultrastructure of muscle fibers observed using transmission electron microscopy. (B) Western blot and quantification of the autophagy-related proteins of PTEN induced putative kinase 1 (PINK1), BCL2 interacting protein 3 (BNIP3), microtubule-associated protein 1 light chain 3 beta (LC3B) and autophagy related protein 7 (Atg7). **, P<0.01 and ***, P<0.001 versus Ctrl group; #, P<0.05 and ###, P<0.001 versus Den group.\n\nFigure 4: Figure 4. Aspirin decreased the expression of proinflammatory factors induced by denervation. The muscle and serum of TA were harvested for quantitative reverse transcription-polymerase chain reaction (qRT-PCR) and enzyme-linked immunosorbent assay (ELISA). (A) qRT-PCR was performed to analyze the mRNA expression of proinflammatory factors IL-6, IL-1β and TNF-α in TA muscle of mice in each group. (B) ELISA was performed to determine the content of tumor necrosis factor-α (TNF-α), Interleukin -1β (IL-1β) and Interleukin-6 (IL-6) in mice of each group. **, P<0.01 and ***, P<0.001 versus Ctrl group; #, P<0.05 and ##, P<0.01 versus Den group.\n\nFigure 5: Figure 5. Aspirin regulated STAT3 signaling pathway in denervated skeletal muscle. (A) The representative western blots of signal transducer and activator of transcription 3 (STAT3), phosphorylated signal transducer and activator of transcription 3 (pSTAT3) and phosphorylated Janus kinase 2 (pJAK2). (B) Statistical chart of levels of pJAK2 and pSTAT3. ***, P<0.001 and ****, P<0.0001 versus Ctrl group; #, P<0.05 and ###, P<0.001 versus Den group."
      }
    ]
  },
  {
    "id": "PMC7729378_multi_2",
    "image": [
      "images/PMC7729378-f6.png",
      "images/PMC7729378-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Aspirin alleviates denervation-induced muscle atrophy via regulating the Sirt1/PGC-1α axis and STAT3 signaling\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Aspirin inhibited the increase of the proportion of type II muscle fibers in denervated skeletal muscle. (A) Immunofluorescence staining and quantification of fast myosin skeletal heavy chain in TA muscle; (B) Western blot and quantification of sirtuin 1 (SIRT1) and proliferator-activated receptor gamma coactivator 1-alpha (PGC-1α). **, P<0.01 and ****, P<0.0001 versus Ctrl group; #, P<0.05, ##, P<0.01 and ###, P<0.001 versus Den group.\n\nFigure 7: Figure 7. A schematic diagram illustrated the proposed mechanism by which Aspirin rescued peripheral nerve injury induces TA muscle atrophy."
      }
    ]
  },
  {
    "id": "PMC7749622_multi",
    "image": [
      "images/PMC7749622-f1.png",
      "images/PMC7749622-f2.png",
      "images/PMC7749622-f3.png",
      "images/PMC7749622-f4.png",
      "images/PMC7749622-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Differential effects of right and left heart failure on skeletal muscle in rats\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Animal characteristics in the two‐stage ascending aortic banding (AOB) and pulmonary artery banding (PAB) models. (A) Left ventricular (LV) weight, right ventricular (RV) weight (weight in mg per tibia in mm), liver weight (weight in g × 10 per tibia in mm), and lung weight (weight in g × 100 per tibia in mm) in sham animals, AOB animals, and PAB animals 7 weeks after surgery (compensated stage) or 22/26 weeks after surgery (decompensated stage). At the decompensated stage, results from sham animals 22–26 weeks after surgery are shown. (B) LV ejection fraction (LVEF), LV fractional shortening (LVFS), tricuspid annular plane systolic excursion (TAPSE), and RV fractional area change (RV FAC). Groups are the same as in (A). All data are mean ± standard error of the mean. n = 10–14 animals per group. * P < 0.05; ** P < 0.01; and *** P < 0.001.\n\nFigure 2: Figure 2. Muscle weights (sarcopenia index) and muscle fibre types. (A) Differences in the weight of soleus muscle, diaphragm, and gastrocnemius muscle normalized per body weight (BW) in sham animals, ascending aortic banding (AOB) animals, and pulmonary artery banding (PAB) animals 7 weeks after surgery (compensated stage) or 22/26 weeks after surgery (decompensated stage). All data are mean ± standard error of the mean. n = 10–14 animals per group. * P < 0.05. (B) Representative results from ATPase staining in soleus muscle, diaphragm, and gastrocnemius muscle to distinguish between type I fibres (white), type IIA fibres (light blue), and type IIB fibres (dark blue). The size bar indicates 50 μm. (C) Analysis of the percentage of the according fibre types at the decompensated stage depicted as a pie chart. n = 6 animals per group.\n\nFigure 3: Figure 3. Proteasome activation and expression. (A) Differences in chymotrypsin‐like and trypsin‐like proteasome activity in soleus muscle. (B) Differences in chymotrypsin‐like and trypsin‐like proteasome activity in diaphragm. (C) Differences in chymotrypsin‐like and trypsin‐like proteasome activity in gastrocnemius muscle. Data are normalized to 7‐week‐old sham animals. All data are mean ± standard error of the mean. n = 8 animals per group. * P < 0.05; ** P < 0.01. (D) Representative western blots from soleus muscle at both disease stages. (E) Representative western blots from diaphragm at both disease stages. (F) Representative western blots from gastrocnemius muscle at both disease stages. Homogenates of skeletal muscle were probed with antibodies detecting muscle‐specific RING finger 1 (MuRF1), atrogin‐1, and myostatin. GAPDH served as a loading control. n = 6 samples per group. AOB, ascending aortic banding; PAB, pulmonary artery banding.\n\nFigure 4: Figure 4. Autophagy and apoptosis. (A) Representative western blots and densitometry of protein data from soleus muscle, diaphragm, and gastrocnemius muscle at both disease stages. Homogenates of skeletal muscle were probed with an antibody detecting the autophagy marker light chain 3 (LC3, isoform A + B). The conversion of the LC3‐I form to the lower migrating form, LC3‐II, was used as an autophagy indicator. GAPDH served as a loading control. n = 6 samples per group. ** P < 0.01. (B) Ten micrograms of tissue homogenate was transferred to a 96‐well microplate, and caspase 3/7 activity was detected in sham animals, ascending aortic banding (AOB) animals, and pulmonary artery banding (PAB) animals 7 weeks after surgery (compensated stage) or 22/26 weeks after surgery (decompensated stage). All data are mean ± standard error of the mean. n = 8 samples per group.\n\nFigure 5: Figure 5. Mitochondrial function in soleus muscle. (A) Citrate synthase activity and the activity of complex I, complex II, complex III, and complex IV of the respiratory chain were measured in soleus muscle lysates. All values were normalized to total protein content of the samples. (B) Active rates of respiration (state 3) were measured in saponin‐skinned fibres of soleus muscle in the presence of 5 mM ADP and either 10 mM pyruvate + 2 mM malate or 10 mM succinate in the presence of 5 μM rotenone. All data are mean ± standard error of the mean. n = 6 samples per group. * P < 0.05. AOB, ascending aortic banding; PAB, pulmonary artery banding."
      }
    ]
  },
  {
    "id": "PMC7749622_multi_2",
    "image": [
      "images/PMC7749622-f6.png",
      "images/PMC7749622-f7.png",
      "images/PMC7749622-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Differential effects of right and left heart failure on skeletal muscle in rats\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Mitochondrial respiratory chain protein expression. (A) Representative blots and densitometry of selected protein data (complex I and complex IV) from soleus muscle at both disease stages. (B) Representative blots and densitometry of selected protein data (ND1 and COX I) from soleus muscle at both disease stages. Homogenates of skeletal muscle were probed with antibodies detecting mitochondrial respiratory chain complexes I–V (total OXPHOS), the complex I proteins ND1 and NDUFS1, and the complex IV proteins COX I and COX IV. GAPDH served as a loading control. n = 6 samples per group. ** P < 0.01; *** P < 0.001. AOB, ascending aortic banding; PAB, pulmonary artery banding.\n\nFigure 7: Figure 7. Impact of interleukin‐6 (IL‐6) and angiotensin II (Ang II) on mediators involved in muscular atrophy and autophagy. (A) Rat skeletal muscle cell (RSkMC) myoblasts (left panel) or RSkMC myotubes (right panel) were treated with increasing concentrations of IL‐6 as indicated. Homogenates of RSkMC were probed with antibodies detecting muscle‐specific RING finger 1 (MuRF1), atrogin‐1, myostatin, and light chain 3 (LC3) (isoform A + B). GAPDH served as a loading control. (B) RSkMC myoblasts (left panel) or RSkMC myotubes (right panel) were treated as described previously and probed with an antibody detecting ubiquitin. A molecular weight marker to estimate the size of the ubiquitinated proteins is included. GAPDH served as a loading control. (A, B) n = 8 samples per group, four independent experiments. (C) RSkMC myoblasts (left panel) or RSkMC myotubes (right panel) were treated with increasing concentrations of Ang II as indicated. Homogenates of RSkMC were probed with antibodies detecting MuRF1, atrogin‐1, myostatin, and LC3 (isoform A + B). GAPDH served as a loading control. (D) RSkMC myoblasts (left panel) or RSkMC myotubes (right panel) were treated as described previously and probed with an antibody detecting ubiquitin. A molecular weight marker to estimate the size of the ubiquitinated proteins is included. GAPDH served as a loading control. (C, D) n = 8 samples per group, four independent experiments.\n\nFigure 8: Figure 8. Role of interleukin‐6 (IL‐6) and angiotensin II (Ang II) pathway activation in rat skeletal myoblasts and myotubes in vitro. (A) Rat skeletal muscle cells (RSkMC) myoblasts (left panel) or RSkMC myotubes (right panel) were treated with Stattic (1 μM) or losartan (10 μM) for 1 h before adding IL‐6 (10 ng/mL) or Ang II (100 nM). Homogenates of RSkMC were probed with antibodies detecting muscle‐specific RING finger 1 (MuRF1), atrogin‐1, myostatin, light chain 3 (LC3) (isoform A + B), and pSTAT3. GAPDH served as a loading control. (B) RSkMC myoblasts (left panel) or RSkMC myotubes (right panel) were treated as described previously and probed with an antibody detecting ubiquitin. A molecular weight marker to estimate the size of the ubiquitinated proteins is included. GAPDH served as a loading control. (A, B) n = 8 samples per group, four independent experiments."
      }
    ]
  },
  {
    "id": "PMC7754141_multi",
    "image": [
      "images/PMC7754141-f1.png",
      "images/PMC7754141-f2.png",
      "images/PMC7754141-f3.png",
      "images/PMC7754141-f4.png",
      "images/PMC7754141-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Fibroblast‐specific genome‐scale modelling predicts an imbalance in amino acid metabolism in Refsum disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Developing a fibroblast‐specific model. (A) Schematic overview of relevant metabolic pathways for phytanate metabolism. (B) Schematic representation of the experimental set‐up. CTRL and RD fibroblasts were incubated with or without phytol, the precursor of phytanate, for the indicated time points. All cells were seeded and harvested under the same conditions. (C) Schematic overview of the steps to obtain a fibroblast‐specific model based on constraints of the Recon3D_FAD_x model.\n\nFigure 2: Figure 2. (A + B) Volcano plots depicting (A) the transcriptomics data and (B) proteomics data derived from fibroblasts incubated with phytol for 96 h. Genes and proteins, resp., with significant differences in expression between the diseases (RD) and CTRL groups are indicated with coloured dots. Gene names are shown for genes and proteins, resp., indicated with green dots. Blue dots represent metabolic genes, as included in the Recon3D model, that were expressed differentially at the significance level below 0.001, and their expression levels were changed by minimum onefold. (C + D) PCA for (C) transcriptomics data and (D) proteomics data. Raw expression values have been scaled and centred. (E) Correlation plot showing log2 average abundance of all proteins (x‐axis) and genes (y‐axis) that were included in the Recon3D model.\n\nFigure 3: Figure 3. Model predictions of ATP yields from a single‐carbon source. Assessment of carbon source utilisation on minimal media based on the ATP production from single‐carbon source, including Recon3D_FAD, curated Recon3D_FAD for phytanate metabolism (Recon3D_FAD_x), the fibroblast‐specific model for CTRL (fibroblast_CTRL) and diseased conditions (fibroblast_RD). Green shades in the heatmaps reflect the relative net ATP production ranging from no (white) to high (dark green), and very high ATP production (black). Crossed‐out fields symbolise model inability to metabolise a carbon source (infeasible solution) on minimal media.\n\nFigure 4: Figure 4. Model predictions of ATP yields from a single‐carbon source. Assessment of carbon source utilisation on minimal media supplemented with glutathione and pantothenic acid based on the ATP production from single‐carbon source, including Recon3D_FAD, curated Recon3D_FAD for phytanate metabolism (Recon3D_FAD_x), the fibroblast‐specific model for CTRL (fibroblast_CTRL) and diseased conditions (fibroblast_RD). Green shades in the heatmaps reflect the relative net ATP production ranging from no (white) to high (dark green), and very high ATP production (black).\n\nFigure 5: Figure 5. Simulation of phytanate metabolism. Missing reactions for phytanate metabolism, including α‐ and ω‐oxidation, were added to the Recon3D_FAD model. The curated, fibroblast‐specific model shows differences in metabolic fluxes of phytanate through the available pathways under normal (CTRL, green) and diseased conditions (RD, blue). Insert shows maximised fluxes, including blocked α‐oxidation in PHYH conditions. Predictions are shown as box‐and‐whisker (the horizontal line at median, and whiskers at min and max values, n = 10 000) plots (main figure), or bar plots (insert)."
      }
    ]
  },
  {
    "id": "PMC7754141_multi_2",
    "image": [
      "images/PMC7754141-f6.png",
      "images/PMC7754141-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Fibroblast‐specific genome‐scale modelling predicts an imbalance in amino acid metabolism in Refsum disease\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Metabolic characterisation of fibroblasts cultured in vitro. Model validation using experimental data of (A) phytanate, and (B + C) amino acid measurements. (A) Phytanate concentrations were determined in pellets from cultured cells after incubation for 96 h. Phytanate levels are increased in cells incubated with phytol. Per condition, mean per group and 95% confidence interval per group are indicated. Significant differences between the groups were determined by one‐way ANOVA (***P‐value < 0.001, n CTRL = 6, n RD = 5). (B) Significantly changed uptake and secretion rates of amino acids between healthy (n = 6) and RD (n = 5) fibroblasts exposed to phytol for 96 h (shown as mean and 95% confidence interval). Amino acid concentrations were determined in the medium of the cells 96‐h incubation with phytol. Rates were calculated based on the fresh medium measurements. Significant differences between the groups were determined using a t‐test with a two‐stage linear step‐up procedure of Benjamini, Krieger and Yekutieli, with Q = 1%, to correct for the multiple testing (**q‐value < 0.01, ***q‐value < 0.001). Rates of uptake and secretion of other amino acids are shown in Fig. S1. C) Amino acid concentrations were determined in the medium of the healthy (n = 6) and RD (n = 5) fibroblast cells after incubation at indicated time points (shown as mean ± SD). Results for other amino acids are shown in Fig. S2D.\n\nFigure 7: Figure 7. Changes at the level of secretion and uptake reactions between healthy and Refsum models forced to take up phytanate. (A–E) Secretion/uptake fluxes distributions of metabolites with the most significant differences between CTRL (CTRL + phyt, green; n = 10 000) and RD (RD + phyt, blue, n = 10 000) models forced to take up phytanate selected based on the log2(FC) > 1.3 and FDR < 0.05. Statistical differences were analysed using the Wilcoxon rank sum test; FDR values were calculated using the Bonferroni–Holm correction."
      }
    ]
  },
  {
    "id": "PMC7765395_multi",
    "image": [
      "images/PMC7765395-f1.png",
      "images/PMC7765395-f2.png",
      "images/PMC7765395-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The Molecular and Pathophysiological Functions of Members of the LNX/PDZRN E3 Ubiquitin Ligase Family\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic diagrams of the members of the human LNX family. (a) LNX1 has two splicing variants, LNX1p70 and LNX1p80. In contrast to the longer splicing variant, the shorter one does not contain the N-terminal RING domain and the two neighboring Zn finger motifs, while the other known domains following the second Zn finger motif are conserved, which include four PDZ domains and a NUMB-binding motif. Both variants bind to NUMB via the NPAY motif and contain a MAGE-B interacting region. The red dashed bar indicates the point from which the amino acid sequences become identical. (b) LNX2 showed the highest similarity with LNX1p80 in terms of primary structure. However, the major difference between LNX1p80 and LNX2 was noted at the region located between the NUMB-binding motif and the point of initiation of the first PDZ domain. While LNX1p80 has a relatively longer sequence that includes the MAGE-B18-interacting motif, LNX2 only has a 21-amino acid-spanning region. (c) LNX3 has five splicing variants. The PDZRN4 isoform 1 is the sole variant equipped with an N-terminal RING domain and a juxtaposed Zn finger flanking the C-terminal end of the RING domain. All the variants have two PDZ domains, except the third isoform, which only has one PDZ domain. (d) Among LNX4 variants, which include three isoforms, only the PDZRN4 isoform 1 has an N-terminal RING domain and a SINA-like motif. Similar to LNX3, the variants have two PDZ domains; the third isoform is an exception as it has only one relatively short PDZ domain identical to that in the PDZRN4 isoform 3. (e) LNX5 has six splicing variants. All variants have a single PDZ without any recognizable domains. The last three single letter amino acid codes represent the class I PDZ-binding motif (S/T-X-V/I/L). The scale bar on the top indicates the approximate length in terms of the number of amino acids for the comparison of individual proteins. ZF; Zn finger motif, RING; really interesting new gene, MAGE; melanoma-associated antigen, PDZ; PSD95-DLGA-ZO-1, SINA; seven in absentia, TRAF; tumor necrosis factor receptor (TNF-R)-associated factor. The schematic illustration of the alignment of the LNX/PDZRN domains are derived from the deduced amino acid sequence information retrieved from GenBank; the corresponding accession numbers have been provided: LNX1p80 (NP_001119800.1), LNX1p70 (NP_116011.2), LNX2 (NP_699202.1), PDZRN3 isoform 1 (NP_055824.1), PDZRN3 isoform 2 (NP_001290068.1), PDZRN3 isoform 3 (NP_001290069.1), PDZRN3 isoform 4 (NP_001290070.1), PDZRN3 isoform 5 (NP_001290071.1), PDZRN4 isoform 1 (NP_001158067.1), PDZRN4 isoform 2 (NP_037509.3), PDZRN4 isoform 3 (EAW57827.1), LNX5 isoform 1 (NP_001290441.1), LNX5 isoform 2 (NP_115901.2), LNX5 isoform 3 (NP_001290442.1), LNX5 isoform 4 (NP_001290443.1), LNX5 isoform 5 (NP_001290444.1), LNX5 isoform 6 (NP_001290445.1).\n\nFigure 2: Figure 2. Amino acid sequence comparison of human LNXs (a) Phylogenetic tree of the LNX proteins. Maximum likelihood analysis was performed using to RAxML under the LG+GAMMA model. Analysis was carried out with five LNXs encoding the longest of their own variants (LNX1p80, LNX2, LNX3 isoform 1, LNX4 isoform 1, and LNX5 isoform 1). The numbers on each node represent bootstrap supported values. The scale bar indicates the number of substitutions/site. (b,c) Homology comparison of each domains was highlighted by the value of percentage. (b) Pairwise comparison between LNX1 and LNX2. The scale bar on the top indicates the approximate numbers of amino acids for the comparison of individual proteins. (c) Pairwise comparison between LNX3 (PDZRN3) and LNX4 (PDZRN4).\n\nFigure 3: Figure 3. Schematic drawing of differential regulation of canonical and non-canonical Wnt signaling by LNX3. By canonical Wnt stimuli via LRP5/6 and Frizzled receptors, the Dvl recruits the β-catenin destruction complex to the plasma membrane including CK1α and GSK-3β kinases responsible for the β-catenin phosphorylation. As a consequence, the stabilized non-phospho (active) β-catenin is translocated to the nucleus where it binds to and stimulates TCF transcription factors. In noncanonical Wnt signaling, when Wnt ligand binds to Frizzled and RTK receptors, Dvl together with Frizzled undergoes endocytosis to trigger a signaling cascade that drives PKC and c-Jun activation. While PKC activates NFAT transcription factor, c-Jun in conjunction with c-Fos forms AP-1 transcription complex. The C-terminal PDZ-binding motif of LNX3 ended with TTV may directly bind to PDZ domain of Dvl, and then induce K63 linked polyubiquitylation into the Dvl, which is a prerequisite event for the subsequent endocytosis of Frizzled/Dvl complex. Though LNX3 may interfere with canonical Wnt signaling, the detailed mechanism has not been clearly validated yet. PCP; planar cell polarity, Wnt; Wingless and Int-1, LRP5/6; Low density lipoprotein receptor-related protein 5 and 6, Dvl; Dishevelled, RTK; receptor tyrosine kinase, DIX; Dishevelled homologous domain, PDZ; PSD95/DLGA/Zo-1, DEP; Dishevelled/Egl-10/Pleckstrin, GSK-3; Glycogen Synthase Kinase-3, GBP; GSK-3 binding protein, CK1; Casein kinase 1, APC; Adenomatous Polyposis Coli, TCF; T-cell factor, PKC; Protein kinase C, NFAT; Nuclear factor of activated T-cells."
      }
    ]
  },
  {
    "id": "PMC7767417_multi",
    "image": [
      "images/PMC7767417-f1.png",
      "images/PMC7767417-f2.png",
      "images/PMC7767417-f3.png",
      "images/PMC7767417-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"L-Carnitine in Drosophila: A Review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. L-Carnitine biosynthesis pathway. Drosophila orthologs are reported near each counterpart with the FlyBase CG number(s) in red. The CG numbers with the best hit(s) are underlined.\n\nFigure 2: Figure 2. An overview of the Carnitine Shuttle. The Drosophila orthologs are reported near each enzyme with their Dmel name.\n\nFigure 3: Figure 3. L-Carnitine and peroxisomes. The Drosophila orthologs are reported near each enzyme with the Dmel name or/and the corresponding FlyBase CG number(s).\n\nFigure 4: Figure 4. An overview of the antioxidant properties of L-carnitine."
      }
    ]
  },
  {
    "id": "PMC7829553_multi",
    "image": [
      "images/PMC7829553-f1.png",
      "images/PMC7829553-f2.png",
      "images/PMC7829553-f3.png",
      "images/PMC7829553-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Metabolite and Cofactor Transport in Humans\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Currently known CoA-dependent enzymatic reactions and transporters in human peroxisomes. (A) Fatty acids undergo beta-oxidation after import as acyl-CoA esters into peroxisomes. During beta-oxidation, acyl-CoAs are shortened to acyl(n-2)-CoA and acetyl-CoA molecules are produced. Peroxisomal beta-oxidation is mediated by the enzymes acyl-CoA oxidase 1, 2, and 3 (ACOX1, ACOX2, and ACOX3), L- and D-bifunctional protein (LBP and DBP), acetyl-CoA acyltransferase 1 (ACAA1), and sterol carrier protein x-related thiolase (SCPx). One CoA molecule is required for each circle of beta-oxidation. Acyl-CoA molecules produced during beta-oxidation may be hydrolyzed by thioesterases into fatty acids or acetate or converted to carnitine esters by CRAT and CROT, thereby producing free CoA. Free fatty acids and acetate can probably exit peroxisome directly after which ACSL, located on the cytosolic side of peroxisomal membrane, may be involved in the reactivation of the fatty acid and acetate. It is unclear which transporter is responsible for the export of acyl-carnitines. The peroxisomal enzyme GNPAT uses acyl-CoA esters for the acylation of DHAP during ether-linked lipid biosynthesis. During this reaction free CoA is released. Phytanoyl-CoA undergoes alpha-oxidation inside peroxisomes, resulting in the formation of formyl-CoA, which spontaneously splits into formic acid and CoA. Another product of alpha-oxidation – pristanic acid - is reactivated into pristanoyl-CoA by peroxisomal ACSVL. The bile acids THCA-CoA and DHCA-CoA are subjected to one cycle of beta-oxidation in peroxisomes during which choloyl-CoA and deoxycholoyl-CoA are produced and subsequently converted to glycine or taurine conjugates by BAAT. It is unknown how the conjugates are exported from the peroxisomes. It has been suggested that PMP34 imports free CoA into peroxisomes. The CoA diphosphohydrolases NUDT19 and NUDT7 degrade CoA into 3′,5′-ADP, and 4′-phosphopantetheine, which are subsequently exported from peroxisomes, possibly by PMP34. Proteins of the ABCD subfamily import acyl-CoA molecules into peroxisomes. During the import, the ester bond of acyl-CoA is hydrolyzed, and fatty acids subsequently undergo re-esterification by the intraperoxisomal ACSVL proteins. It is unknown whether the CoA molecule from acyl-CoA is also imported into the peroxisomal matrix after hydrolysis. (B) ABCD1, ABCD2, and ABCD3 transporters have different substrate affinities, as shown on the right. After the import of fatty acids, they are esterified by the ACSVL proteins in a CoA- and ATP-dependent reaction. ABCD proteins were shown to hydrolyze the ester bond in the CoA esters during import, although it has also been suggested that ABCD transporters import acyl-CoA molecules without hydrolysis of the ester bond (see text for more information). Enzymatic reactions or molecules belonging to the same metabolic pathway are marked with background color and listed at the bottom.\n\nFigure 2: Figure 2. Currently known NAD+/NADH- and NADP+/NADPH-dependent peroxisomal enzymatic reactions, transport of NAD+/NADH, NADP+/NADPH, NMNH+, AMP, and 2′,5′-ADP, and role of shuttle systems. NAD+/NADH and NADP+/NADPH may be imported into peroxisomes by specific transporters or co-imported with fully folded NAD(H)/NADP(H)-dependent enzymes. During peroxisomal beta-oxidation, D- and L-bifunctional proteins (DBP and LBP) catalyze the second (hydration) and third (dehydrogenation) step of beta oxidation. During the dehydrogenation, NAD+ is reduced to NADH. Subsequent reoxidation of NADH may be mediated by the three different dehydrogenases located inside peroxisomes: LDHB, which converts pyruvate into lactate; MDH1, which converts oxaloacetate into malate; GPD1, which converts DHAP into G3P. During beta-oxidation, the double bound(s) of mono-/polyunsaturated fatty acids are reduced by the peroxisomal enzyme 2,4- dienoyl-CoA reductase (DECR2). During the reduction, NADPH is oxidized to NADP+. NADPH is also oxidized by TER during convertion of phytenoyl-CoA into phytanoyl-CoA. NADP+ is reduced back to NADPH by IDH1, which converts isocitrate into 2-OG. The import and export of small metabolites [pyruvate, lactate, oxaloacetate, malate, DHAP, G3P, isocitrate, and 2-oxoglutarate (2-OG)] is probably mediated by the peroxisomal pore-forming proteins (PXMP2, Pex11α, Pex11β, and Pex11γ) that allow passage of molecules with a size below 600 Da. The role of another pore-forming protein BAK in the permeability of the peroxisomal membrane remains unclear. Monocarboxylate transporters MCT1 and MCT2 may be involved in the transport of lactate and pyruvate. The pyrophosphatase NUDT12 mediates NADH degradation (to NMNH and AMP) and NADPH degradation (to NMNH and 2’,5′-ADP). The products of NADH/NADPH degradation are subsequently exported from peroxisomes, probably by PMP34. Enzymatic reactions or molecules belonging to the same metabolic pathway are marked with background color and listed at the bottom.\n\nFigure 3: Figure 3. Currently known FAD, PLP, ThPP, FMN, and heme-dependent enzymatic reactions in the peroxisomes and transport of FAD, PLP, ThPP, heme, FMN and AMP. Most of the peroxisomal matrix proteins are imported into peroxisomes via a PTS1-specific pore. Proteins may be imported as monomers or in a fully folded form complexed with their cofactor. Cofactors that may be co-imported with proteins are FAD (with ACOX and ADHAPS proteins), FMN (HAO1, HAO2, HAO3), ThPP (with HACL1), PLP (with AGT), and heme (with catalase). It has also been suggested that the PMP34 transporter can import free FAD into peroxisomes. In the peroxisome, FAD forms an active enzyme with apoenzyme ACOX. The pyrophosphatase NUDT12 may mediate the degradation of FAD to FMN and AMP. FMN and AMP are subsequently exported from peroxisomes, probably by PMP34. Acyl-CoA oxidases (ACOX) mediate the first (dehydrogenation) reaction of the beta-oxidation. During dehydrogenation, FAD is reduced to FADH2. FADH2 is re-oxidized by direct transfer of electrons to O2, resulting in the production of H2O2. H2O2 is degraded by the heme-dependent enzyme catalase to H2O and O2. It is unclear whether free ThPP or PLP are imported into peroxisomes. Alkyl-dihydroxyacetonephosphate synthase (ADHAPS) catalyzes the exchange in acyl-dihydroxyacetonephosphate (acyl-DHAP) of the acyl chain with long-chain alcohol through a non-redox mechanism. The ThPP-dependent enzyme 2-hydroxyacyl-CoA lyase (HACL1) catalyzes the cleavage of 2-hydroxyphytanoyl-CoA into pristanal and formyl-CoA during peroxisomal alpha-oxidation of phytanoyl-CoA. The PLP-dependent enzyme alanine-glyoxylate aminotransferase (AGT) catalyzes the transamination of glyoxylate to glycine during glyoxylate detoxification. The FMN-dependent enzymes 2-hydroxyacid oxidases (HAO1, HAO2, HAO3) catalyze oxidation of glycolate to glyoxylate. Enzymatic reactions or molecules belonging to the same metabolic pathway are marked with background color and listed at the bottom.\n\nFigure 4: Figure 4. Currently known ATP-dependent enzymatic reactions in the peroxisomes and transport of ATP, AMP and PP. Intraperoxisomal ATP is required for the ACSVL-mediated activation of fatty acids after their import by the ABCD proteins. Pristanic acid formed during alpha-oxidation is activated inside peroxisomes to the corresponding CoA ester in an ATP-dependent reaction. Finally, the peroxisomal protease LonP2 hydrolyzes ATP. It is unknown which transporter mediates the import of ATP into peroxisomes. The products of ATP hydrolysis – AMP and PP are exported from peroxisomes most probably by PMP34 and PXMP2, respectively."
      }
    ]
  },
  {
    "id": "PMC7838297_multi",
    "image": [
      "images/PMC7838297-f1.png",
      "images/PMC7838297-f2.png",
      "images/PMC7838297-f3.png",
      "images/PMC7838297-f4.png",
      "images/PMC7838297-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Acyl-CoA thioesterase activity of peroxisomal ABC protein ABCD1 is required for the transport of very long-chain acyl-CoA into peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. ATPase activities of reconstituted ABCD1. (A) Purified His-ABCD1 (Eluate) and reconstituted His-ABCD1 (Liposome) were subjected to SDS-PAGE, and the gels were stained with CBB. The arrow head and the asterisk indicate His-ABCD1 and a non-specific protein, respectively. (B) ATPase activity of reconstituted ABCD1 was measured. Proteoliposomes containing ABCD1 (3.05 μg) or negative control liposomes containing non-specific protein (1.98 μg) were incubated with 5 mM ATP for 30 min at 37 °C and the phosphate that was released was measured. Error bars indicate the standard error (n = 3).\n\nFigure 2: Figure 2. ACOT activities of reconstituted ABCD1. (A) Thioesterase activity of reconstituted ABCD1. Proteoliposomes containing ABCD1 (1.84 μg) or negative control liposomes containing non-specific protein (1.62 μg) were incubated with 2 μM NBD-C16-CoA for 10, 20, and 30 min at 37 °C. The “no incubation (0 min)” was run as the reaction was stopped before the addition of NBD-C16-CoA. Each reaction was subjected to TLC to separate NBD-C16-CoA and NBD-C16. (B) The ACOT activity was determined after the amount of NBD-C16 was quantified using the image analysis software Image J, and the ACOT activity of ABCD1 (filled circle) and non-specific protein (open circle) are shown. Error bars indicate the standard error (n = 3). (C) Acylation of ABCD1 with NBD-C16-CoA. ABCD1-liposomes were incubated with NBD-C16-CoA or NBD-C16 for 30 min at 37 °C and then subjected to SDS-PAGE. The gel was fixed with methanol and stained with CBB (left panel) after the detection of NBD fluorescence (right panel). The arrow head indicates ABCD1.\n\nFigure 3: Figure 3. Amino acid residues responsible for the ACOT activity of ABCD1 (A) Proteoliposomes containing ABCD1 (2.70 μg) were incubated with NBD-C16-CoA in the presence or absence of each compound (1 mM) for 30 min at 37 °C. Aliquots were subjected to TLC as shown in Fig. S4A. Relative ACOT activities were evaluated by quantifying the intensities of NBD-C16 using the image analysis software Image J (upper graph). ACOT activity without any reagents (0.27 nmol/min/mg) has been normalized to 1. The aliquots were also subjected to SDS-PAGE and the acylation of ABCD1 with NBD-C16-CoA was analyzed (lower panel). Error bars indicate the standard error (n = 3). The arrow head indicates ABCD1. PMSF: phenylmethylsulfonyl fluoride, DFP: diisopropylfluorophosphate, BNPP: bis-(4-nitrophenyl)phosphate, pCMB: p-chloromercuribenzoic acid, DEPC: diethyl pyrocarbonate. (B) ACOT activity was measured in the presence of various concentrations of pCMB for 30 min at 37 °C. Aliquots were subjected to TLC as shown in Fig. S4B. Relative ACOT activities were evaluated by quantifying the intensities of NBD-C16 using the image analysis software Image J. ACOT activity without pCMB (0.29 nmol/min/mg) has been normalized to 1. (C) Stability of covalent linkage between ABCD1 and NBD-C16. ABCD1-liposomes were incubated with NBD-C16-CoA for 30 min at 37 °C and then subjected to SDS-PAGE. The gels were fixed and then divided. Each gel was incubated with 1 M Tris–HCl pH 7.0, 1 M Hydroxylamine pH 7.0, 0.1 N KOH or 0.1 N HCl for 18 h at room temperature, respectively. The gels were stained with CBB after the detection of NBD fluorescence. The arrow head indicates ABCD1.\n\nFigure 4: Figure 4. Substrate specificity of ABCD1-catalyzed ACOT activity. (A) Proteoliposomes containing ABCD1 (3.04 μg) were incubated with NBD-C16-CoA or NBD-C16-3′-dephosphoCoA (NBD-C16-dePiCoA) for 30 min at 37 °C. The aliquots were subjected to TLC. (B) Aliquots were also subjected to SDS-PAGE. The gel was fixed with methanol and stained with CBB (left panel) after the detection of NBD fluorescence (right panel). The arrow head indicates ABCD1. (C) Proteoliposomes containing ABCD1 (3.16 μg) were incubated with NBD-C16-CoA or NBD-C6-CoA for 30 min at 37 °C. The aliquots were subjected to TLC. (D) Aliquots were also subjected to SDS-PAGE. The gel was fixed with methanol and stained with CBB (left panel) after the detection of NBD fluorescence (right panel). The arrow head indicates ABCD1.\n\nFigure 5: Figure 5. Relationship between ATPase activity and the ACOT activity of ABCD1 (A) Effect of ATP on ABCD1-catalyzed ACOT activity. ABCD1-liposomes were incubated with NBD-C16-CoA in the presence of various concentration of ATP for 30 min at 37 °C. The aliquots were subjected to TLC as shown in Fig. S7. The relative ACOT activities were evaluated by quantifying the intensities of NBD-C16 using the image analysis software Image J. Error bars indicate the standard error (n = 3). (B) His-ABCD1(a.a.1–431) and His-ABCD1(K513A) were prepared using the same procedure as the purification of His-ABCD1 and then reconstituted into liposomes. Proteoliposomes containing ABCD1wild type, ABCD1(K513A) or ABCD1(1–431) (2.68 μg, 3.21 μg or 3.71 μg, respectively) were incubated with NBD-C16-CoA for 30 min at 37 °C. The aliquots were subjected to TLC to separate hydrolyzed NBD-C16 and NBD-C16-CoA. (C) Relative ACOT activities of ABCD1(a.a.1–431) and ABCD1(K513A) were evaluated. The intensities of NBD-C16 were normalized by the signal intensities of each of the proteins obtained by immunoblot analysis using the image analysis software Image J. Error bars indicate the standard error (n = 3). Wild type activity (0.33 nmol/min/mg) has been normalized to 1. (D) Aliquots were also subjected to SDS-PAGE. The gel was fixed with methanol and stained with CBB (left panel) after the detection of NBD fluorescence (right panel). The arrow heads indicate the wild type, a.a.1–431 or K513A."
      }
    ]
  },
  {
    "id": "PMC7838297_multi_2",
    "image": [
      "images/PMC7838297-f6.png",
      "images/PMC7838297-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Acyl-CoA thioesterase activity of peroxisomal ABC protein ABCD1 is required for the transport of very long-chain acyl-CoA into peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Transport of the NBD-C16 derived from NBD-C16-CoA into ABCD1- liposomes. (A) Proteoliposomes containing ABCD1 (4.81 μg) or non-specific protein were incubated with NBD-C16-CoA at 37 °C for the indicated periods. After incubation, the remaining NBD-C16-CoA in the outside portion of the liposomes was quenched with sodium dithionite. In some cases, the liposomes were treated with sodium dithionite after the addition of 0.01% Triton X-100. Subsequently, ABCD1-liposomes were precipitated by centrifugation and then resuspended with 80% acetone. NBD-C16 and NBD-C16-CoA were separated by TLC. (B) Transport of NBD-C16 into ABCD1-liposomes was tested under various conditions. ABCD1-liposomes were incubated with NBD-C16-CoA in the presence of pCMB (1 mM) or palmitoyl-CoA (20 μM), or in the absence of ATP. NBD-C16-3′-dephosphoCoA (NBD-C16-dePiCoA) and NBD-C6-CoA were also examined as the substrate. Relative NBD-C16 transport activities were evaluated by quantifying the intensities of NBD-C16 using the image analysis software Image J (right graph). Error bars indicate the standard error (n = 3). (C) NBD-C16 transport activity for ABCD1(K513A) was tested by the same procedure as used for the wild type. The relative transport activity ABCD1(K513A) was evaluated as follows. The intensities of NBD-C16 were normalized by the signal intensities of the wild type and K513A obtained by immunoblot analysis using the image analysis software Image J. Error bars indicate the standard error (n = 3).\n\nFigure 7: Figure 7. A hypothetical model of VLCFA-CoA transport by ABCD1. (A) Structure of VLCFA-CoA. ABCD1 strictly recognizes the VLCFA moiety and 3′-phosphate in the ribose ring of acyl-CoA, which are shown with a pink background. The thioester bond is shown with a yellow background. (B) Possible mechanism and the essential roles of acyl-CoA thioesterase activity in the transport of VLCFA by ABCD1. The transport is considered to have three steps; (i) the recognition and binding of VLCFA-CoA to the ACOT domain of ABCD1, (ii) acylation (covalent binding) of the VLCFA moiety to ABCD1, and (iii) the hydrolysis and release of VLCFA from ABCD1 with a conformational change of ABCD1 induced by ATP binding and hydrolysis. The peroxisome membrane is shown in orange. The upper or lower areas of the membrane are inside or outside of the peroxisomes, respectively."
      }
    ]
  },
  {
    "id": "PMC7847955_multi",
    "image": [
      "images/PMC7847955-f1.png",
      "images/PMC7847955-f2.png",
      "images/PMC7847955-f3.png",
      "images/PMC7847955-f4.png",
      "images/PMC7847955-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Multiparametric in vivo analyses of the brain and spine identify structural and metabolic biomarkers in men with adrenomyeloneuropathy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Cross-sectional area of the spinal cord. Spine CSA was reduced in all vertebral regions in patients with AMN (A), and the decrease was more evident in the gray matter (B). (*** p < 0.001).\n\nFigure 2: Figure 2. Metabolite alterations in the spinal cord. Absolute concentrations showed a significantly reduced tNAA and a trend to increase in myo-Ins in patients with AMN (A). The ratio of tNAA/myo-Ins was significantly decreased in patients compared to controls (B). tNAA, total N-acetylaspartate; tCr, total creatine; tCho, total choline; myo-Ins, myo-Inositol. (*** p < 0.001).\n\nFigure 3: Figure 3. Percentage MTR changes in the spinal cord. MTR was markedly reduced in cervical levels C1-C5 in patients with AMN (A) and in the spine gray matter and white matter regions examined (B). (*** p < 0.001).\n\nFigure 4: Figure 4. Alterations in DTI and FBA metrics in the spinal cord. FA was reduced in C3-C5 in patients (A), and in the gray matter and white mater regions examined (B). FC, FD and FDC were reduced in the spine of patients compared to controls (C). FC values have been log normalized for normal distribution and to center the mean around zero. FC, fiber cross-section; FD, fiber density; FDC, fiber density and cross-section. (*** p < 0.001).\n\nFigure 5: Figure 5. Effect sizes of spinal cord imaging metrics. The spinal cord imaging metrics showed very large to huge effect sizes with the exception of RD that showed a very small effect size. MTR showed the largest effect size among all the metrics. MTR, magnetization transfer ratio; FD, fiber density; FBA, fixel-based analysis; CSA, cross-sectional area; tNAA, total N-acetylaspartate; myo-Ins, myo-Inositol; MRS, magnetic resonance spectroscopy; FC, fiber cross-section; FA, fractional anisotropy; DTI, diffusion tensor imaging; FDC, fiber density and cross-section; RD, radial diffusivity."
      }
    ]
  },
  {
    "id": "PMC7884615_multi",
    "image": [
      "images/PMC7884615-f1.png",
      "images/PMC7884615-f2.png",
      "images/PMC7884615-f3.png",
      "images/PMC7884615-f4.png",
      "images/PMC7884615-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Multifunctional Protein 2 Deficiency Perturbs Lipid Homeostasis in the Retina and Causes Visual Dysfunction in Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Spatial distribution of Mfp2 transcripts in the mouse retina. Representative images of RNAscope® in situ hybridization reveals extensive Mfp2 expression throughout the retina of 9 weeks-old Mfp2+/+ mice, but not in Mfp2–/– mice (n = 3 per genotype). Nuclei were counterstained with Hoechst (blue). RPE, retinal pigment epithelium; PR, photoreceptor layer; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer.\n\nFigure 2: Figure 2. Decreased visual acuity and retinal function of Mfp2–/– mice. (A) Measurements of the optokinetic tracking response reveal reduced visual acuity in 9 weeks-old Mfp2–/– mice. ERG measurements show reduced scotopic a- and b-wave amplitudes and reduced photopic b-wave amplitudes in (B) 9 weeks-old, and (C) 3 weeks-old Mfp2–/– mice. Mean ± SEM are shown (n = 3–4 per genotype). Statistical significance was determined by two-way ANOVA with Bonferroni multiple comparisons test: ns p > 0.05, ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001.\n\nFigure 3: Figure 3. Morphological changes in Mfp2–/– retinas. (A) H&E staining reveals no gross morphological alterations, except for PR length reduction, in 3 weeks-old Mfp2–/– retinas and photoreceptor degeneration and protrusion of RPE cells in the POS layer (white arrows) in 9 weeks-old Mfp2–/– retinas. The spiderdiagrams show the quantification of the number of photoreceptor nuclei over a distance of 100 μm at six different positions: I, nasal-peripheral; II, nasal-middle; III, nasal-central; ONH, optic nerve head; IV, temporal-central; V, temporal-middle; VI, temporal-peripheral. (B) Phase-contrast microscopy of 3 and 2 weeks-old Mfp2–/– retinas show reduced photoreceptor outer (red bars) and inner segment (green bars) length. Mean ± SEM are shown (n = 3, 4 and 5 per genotype at 2, 3, and 9 weeks of age, respectively). Statistical significance was determined by two-way ANOVA with Bonferroni multiple comparisons test: ns p > 0.05, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001. (C) Increase in TUNEL-positive nuclei (white arrows) reveals an increase in apoptotic cell death of photoreceptors in 3 weeks-old Mfp2–/– mice (n = 3 per genotype). Hoechst (blue) was used as nuclear counter stain. RPE, retinal pigment epithelium; PR, photoreceptor layer; POS, photoreceptor outer segment; PIS, photoreceptor inner segment; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer.\n\nFigure 4: Figure 4. Normal POS formation in Mfp2–/– mice. TEM analysis reveals (A) unaltered POS disc organization and density and normal connecting cilium appearance and (B) normal contact of the POS with RPE cells in 3 weeks-old Mfp2–/– mice (n = 3-5 per genotype). CC, connecting cilium; POS, photoreceptor outer segment; PIS, photoreceptor inner segment; RPE, retinal pigment epithelium.\n\nFigure 5: Figure 5. Distinct transcriptomic profile of Mfp2–/– retinas. (A) Principal component analysis (PCA) and (B) volcano plot of the differential expression analysis reveal a different transcriptomic signature of 3 weeks-old Mfp2–/– retinas. Blue and red dots in (B) represent differentially expressed and unchanged genes, respectively. (C) Heat map showing the expression of selected cell type specific genes. (D) GSEA reveals a major downregulation in the phototransduction pathway and a major upregulation in cell death and inflammation related pathways. Blue and red bars represent down- and upregulated pathways, respectively (n = 4 per genotype) PR, photoreceptors; MC, Müller cells; AC, amacrine cells; BC, bipolar cells; HC, horizontal cells; GC, ganglion cells."
      }
    ]
  },
  {
    "id": "PMC7884615_multi_2",
    "image": [
      "images/PMC7884615-f6.png",
      "images/PMC7884615-f7.png",
      "images/PMC7884615-f8.png",
      "images/PMC7884615-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Multifunctional Protein 2 Deficiency Perturbs Lipid Homeostasis in the Retina and Causes Visual Dysfunction in Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. MFP2 ablation affects both rods and cones and causes secondary glial activation. Western blot analysis of (A) rhodopsin and (B) recoverin reveal decreased protein levels in 3 weeks-old Mfp2–/– retinas. Vinculin and β-actin are used as loading control in (A,B), respectively. Mean ± SEM are shown (n = 5-9 per genotype). Statistical significance was determined by unpaired t-test: ** p < 0.01, **** p < 0.0001. (C) IHC for rhodopsin reveals shorter POS length and no mislocalization of the protein. (D) PNA-labeled cones exhibit a reduction in length in Mfp2–/– retinas. Cone pedicles in the OPL (white arrows) show a decrease in signal intensity. (E) IHC for GFAP and Iba1 shows the activation of Müller cells and microglia, respectively, in the MFP2 deficient retinas of 3 and 9 weeks-old mice. In addition to their activation, microglia also migrate toward the subretinal space. Hoechst (blue) was used as nuclear counterstain (n = 3 per genotype). RPE, retinal pigment epithelium; POS, photoreceptor outer segments; PIS, photoreceptor inner segments; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer.\n\nFigure 7: Figure 7. DHA decrease is partially compensated by an increase of n-6 PUFAs in Mfp2–/– retinas. (A) Total fatty acid measurements reveal a ∼30% decrease in DHA and a compensatory increase in n-6 PUFAs, such as AA, in 3 weeks-old Mfp2–/– retinas. (B) Calculation of the double bond index (DBI) shows a 10% decrease in Mfp2–/– retinas. Mean ± SEM are shown (n = 3 per genotype). Statistical significance was determined by unpaired t-test: ** p < 0.01, **** p < 0.0001.\n\nFigure 8: Figure 8. Altered PUFA profile in 3 weeks-old Mfp2–/– retinas. (A) Evaluation of the different lipid classes reveals a general increase in ether lipid species. Lipidome analysis reveals a severe decrease in DHA- and an increase in AA-containing (B) PC and (C) PE phospholipids, but not in (D) PS phospholipids. (E) Mfp2–/– retinas display a peculiar profile of PC phospholipids containing VLC-PUFAs. PC species with 52–58 carbons and 10–12 double bonds (DB) are shown. Profile of LPC species containing PUFAs with (F) 6 and (G) 4–5 double bonds. Mean ± SEM are shown (n = 3 per genotype). Statistical significance was determined by two-way ANOVA with Bonferroni multiple comparisons test: ns p > 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001. PC, phosphatidylcholines; PE, phosphatidylethanolamines; PS, phosphatidylserines; TG, triglycerides; DG, diacylglycerides; LPC/LPE, lyso-variant of PC/PE; x(O), ether-variant of the respective lipid species.\n\nFigure 9: Figure 9. Systemic delivery and retinal traffic of DHA is impaired in Mfp2–/– retinas. Lipidome analysis reveals a decrease of DHA-containing (A) PC species and (B) LPC in plasma of 3 weeks-old Mfp2–/– mice. (C,D) Gene expression analysis by RT-qPCR reveals unchanged Mfsd2a and downregulated Adipor1 expression in the RPE of Mfp2–/– mice. Western blot analysis for ADIPOR1 shows a 70% reduction in (E) the RPE and in (F) the retina of Mfp2–/– mice. Vinculin was used as loading control. Mean ± SEM are shown (n = 4–8 per genotype). Statistical significance was determined by unpaired t-test, Mann-Whitney U-test and two-way ANOVA with Bonferroni multiple comparisons test: ns p > 0.05, *p > 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001."
      }
    ]
  },
  {
    "id": "PMC7891367_multi",
    "image": [
      "images/PMC7891367-f1.png",
      "images/PMC7891367-f2.png",
      "images/PMC7891367-f3.png",
      "images/PMC7891367-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"A primer to gene therapy: Progress, prospects, and problems\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematics of the retroviral vector transduction process. The transgene sequence contained in the single‐stranded RNA (ssRNA) vector genome (two vector genome copies per vector particle) enters the cytoplasm of the target cell (transduction) after binding to specific cell surface receptors. This binding triggers fusion between the bilipid membranes of the vector envelope and the cell plasmalemma leading to the release of the ssRNA genomes in the cytoplasm of the target cell. Next, vector particle‐associated reverse transcriptase (RT) converts the incoming ssRNA vector genomes into double‐stranded complementary DNA (cDNA) copies via intermediate RNA–DNA heteroduplexes (not shown). The vector particle‐associated integrase (IN) together with cellular factors and the reverse transcribed vector genomes form a pre‐integration complex (PIC) responsible for establishing stable transduction of the target cell via the integration of the cDNA into the chromosomal DNA. Simple retroviruses, for example, the oncoretrovirus M‐MLV, have exclusively the basic retroviral get set (ie, gag, pro, pol, and env); Complex retroviruses, for example, the lentivirus HIV‐1, in addition to the basic retroviral gene set have genes encoding accessory proteins that play an auxiliary role at different stages of the infection process. Vectors based on simple retroviruses require nuclear envelope breakdown to access the cellular DNA; whereas vectors based on complex retroviruses can translocate their PICs through the pores of intact nuclear membranes. Thus, lentiviral vectors have the distinct advantage of being able to transduce non‐dividing cells. Transcription, messenger RNA export and translation yields stable and heritable vector‐encoded protein synthesis once vector cDNA integration takes place in a genomic region conducive for gene expression. IN, integrase; Red bars, retroviral long‐terminal repeat (LTR); Yellow bars, retroviral packaging signal (Ψ). Figure adapted from 2 Bioessays review\n\nFigure 2: Figure 2. General strategy to engineer a replication‐defective vector from a replication‐competent virus. Coding trans‐acting viral sequences (green) are segregated from non‐coding cis‐acting elements containing the viral origins of replication (red) and viral genome packaging signals (yellow). The coding sequences (viral genes) specify the viral structural and non‐structural proteins (dark and light green, respectively). Viral gene removal, besides disabling the replication capacity of the vector in target cells, also creates room for a transgene expression unit (cyan) consisting of heterologous regulatory sequences (ie, promoter/enhancer elements) and a polyadenylation signal flanking an open reading frame of interest (not shown). Vector particles carrying the transgene cassette are assembled by introducing packaging and vector recombinant DNA constructs into produced cells (packaging cells). The viral gene products encoded by the packaging construct can be provided in specialized stable producer cell lines or can be introduced into vector‐producer cells by transient DNA transfection or helper vector transduction. The replicative, non‐structural, proteins (green triangles and green circles) recognize the cognate viral origins of replication resulting in the amplification of the vector genome (RNA or DNA depending on the type of vector); the structural proteins (green squares) assemble into viral particles. Finally, among the complex mixture of nuclei acids in the producer cell, the presence of packaging cis‐acting elements in the amplified vector genomes selects them for encapsidation resulting in the generation of functional vector particles. Crucially, the absence of packaging elements in helper/packaging constructs avoids their incorporation into viral particles. The vector particles are replication‐incompetent and hence can only undergo the initial cell entry stages of the parental virus “life cycle”. The resulting abortive infection (transduction) permits transgene delivery and expression in target cell nuclei without subsequent vector replication and spread to neighboring cells. Figure adapted from 2 Bioessays review\n\nFigure 3: Figure 3. Schematic outline of classic vs SIN retroviral vectors. Transcripts of classic retroviral vectors start at the U3/R border in the 5′ LTR and end at the R/U5 border in the 3′ LTR. The transcripts corresponding to full‐length vector genomes are packaged into enveloped retroviral particles and are collected to transduce target cells. Classic retroviral vectors rely on the enhancer and promoter sequences embedded in the U3 region of the viral 5′ LTR for expression of the transgene. The enhancers embedded in the U3 regions of the LTRs can affect the expression of neighboring genes once retroviral vector genomes become integrated in target cell chromosomes. The outward red arrows indicate the enhancer activity that may affect the expression of flanking cellular genes. In self‐inactivating (SIN) retroviral vectors a deletion in the U3 region of the 3′LTR (ΔU3) removes the retroviral enhancer sequences inhibiting expression of flanking genes upon SIN retroviral vector chromosomal integration. An internal heterologous promotor is necessary to drive transgene expression in these SIN vectors (green box with broken arrow). In transduced cells, during reverse transcription of vector RNA genomes into double‐stranded cDNA, the U3 sequence in the 3′ LTR serves as template for the synthesis of the U3 region in both LTRs. As a consequence, in classic and SIN retroviral vectors the complete and partially deleted U3 regions of the 3′ LTRs, respectively, are duplicated and transferred to the 5′ LTRs. LTR, long terminal repeat; Ψ, packaging signal; cDNA\n\nFigure 4: Figure 4. Schematic representation of the reactions induced by base editors. Upon binding of the cytidine deaminase base editor to the chromosomal target sequence, the cytidine deaminase enzyme converts the cytidine base to a uridine intermediate. Subsequently, DNA repair pathways favor the repair of the mismatched base (G) on the strand containing the SSB induced by the CRISPR‐Cas9 nickase, causing a G → A replacement on the nicked strand. Through further DNA processing, by either DNA replication or repair, the uridine is replaced by thymine, effectively resulting in the desired C → T edit. Of note, the U → C reversion, by cellular uracil DNA glycosylase (UG) and subsequent base excision repair, can abort the desired C → T transition, resulting in an unaltered chromosomal sequence. For this reason, cytidine base editors also incorporate as fusion partner an UG inhibitor (UGI). Adenine deaminase base editors operate through a similar series of DNA processing steps except that conversion of adenine to an inosine intermediate takes place at the beginning. After DNA mismatch repair and DNA replication this conversion results in the final A → G transition"
      }
    ]
  },
  {
    "id": "PMC7898035_multi",
    "image": [
      "images/PMC7898035-f1.png",
      "images/PMC7898035-f2.png",
      "images/PMC7898035-f3.png",
      "images/PMC7898035-f4.png",
      "images/PMC7898035-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Loss of RNF43 Function Contributes to Gastric Carcinogenesis by Impairing DNA Damage Response\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. RNF43 is involved in DDR. (A) Representative immunofluorescence images of RNF43 (red) in control and AGSD196fs cells. Scale bars: 10 μm. (B) Western blot analysis and quantification of γH2AX and CHK2 expression in WT AGS, AGSD196fs, control AGS (shCtrl), and RNF43 knockdown AGS (shRNF43) cells after γ-radiation. GAPDH was used as a protein loading control (N = 3). (C) RNF43 mRNA levels in control and RNF43 knockdown AGS and MKN45 cells. Cycle threshold (CT)values were normalized to GAPDH and fold change was calculated over control cells. (D) Representative immunofluorescence images of RNF43 (red) in control and RNF43 knockdown AGS and MKN45 cells. Scale bars: 10 μm. (E) Western blot analysis and quantification of γH2AX and CHK2 expression in control MKN45 (shCtrl) and RNF43 knockdown MKN45 (shRNF43) cells after γ-radiation. GAPDH was used as a protein loading control (N = 3). (F) Endogenous RNF43 expression in AGS and MKN45 cells detected by immunocytochemistry. Scale bar: 50 μm. Error bars indicate SD. ∗P ≤ .05, ∗∗P ≤ .01, ∗∗∗P ≤ .001, 2-tailed unpaired t test. DAPI, 4′,6-diamidino-2-phenylindole; GAPDH, glyceraldehyde-3-phosphate dehydrogenase; mRNA, messenger RNA.\n\nFigure 2: Figure 2. Loss of RNF43 function confers resistance to DNA damage-induced cell death. (A) RNF43 mRNA levels in AGS and MKN45 gastric cancer cells upon increasing doses of γ-radiation. Cycle threshold (CT) values were normalized to GAPDH and fold change was calculated over untreated cells (N = 4). (B) Cell viability of WT AGS, AGSD196fs, control MKN45 (shCtrl), and RNF43 knockdown MKN45 (shRNF43) cells after γ-radiation. Values were normalized over untreated cells (N = 4). (C) Cell viability of AGS, AGSD196fs cells, as well as control AGS and MKN45 (shCtrl) and RNF43 knockdown AGS and MKN45 (shRNF43) cells under basal conditions (N = 3). (D) Representative images and quantification of cell colonies after γ-radiation (N = 4). (E) Flow cytometry analysis of Annexin V and propidium iodide (PI)-positive AGS and MKN45 cells after irradiation. Values were normalized over untreated cells (N = 4). Error bars indicate SD. ∗P ≤ .05, ∗∗P ≤ .01, ∗∗∗P ≤ .001, 2-tailed unpaired t test. mRNA, messenger RNA.\n\nFigure 3: Figure 3. RNF43 influences susceptibility to DNA damage-inducing chemotherapeutics. (A) Cell viability of WT AGS, AGSD196fs, control MKN45 and AGS (shCtrl), and RNF43 knockdown MKN45 and AGS (shRNF43) cells after treatment with 5-fluorouracil (5-FU) or cisplatin. Values were normalized over untreated cells (N = 3). (B) RNF43 mRNA levels in AGS and MKN45 GC cells after treatment with 5-FU or cisplatin (Cis) for 48 hours. Cycle threshold (CT) values were normalized to GAPDH and fold change was calculated over untreated cells (N = 3). (C) Relative volume of xenograft tumors derived from control MKN45 (shCtrl) and RNF43 knockdown MKN45 (shRNF43) cells after treatment of mice with 5-FU or cisplatin. Relative volumes were calculated over tumor volume before treatment (N = 6/group). (D) Representative images of xenograft tumors derived from control MKN45 (shCtrl) and RNF43 knockdown MKN45 (shRNF43) cells after treatment of mice with 5-FU or cisplatin. Size and weight of the resected tumors are shown (n = 6/group). Error bars indicate SD. Horizontal lines represent the median values. ∗P ≤ .05, ∗∗P ≤ .01, and ∗∗∗P ≤ .001, (A and B) 2-tailed unpaired t test, (C and D) Mann–Whitney test.\n\nFigure 4: Figure 4. RNF43 influences susceptibility to DNA damage-inducing chemotherapeutics. Representative images showing γH2AX, cleaved caspase 3 (c-caspase 3), and Ki67 detected by immunohistochemistry in xenograft tumors that originated from control MKN45 (shCtrl) and RNF43 knockdown MKN45 (shRNF43) cells after treatment with (A) 5-fluorouracil or (B) cisplatin. Quantification of positive cells per square millimeter is shown. Each dot represents 1 mouse. (C) Viability of gastric organoids from WT or Rnf43ΔEx8 mice after treatment with 5-fluorouracil (5-FU) or cisplatin. Values were normalized over untreated (N = 3). Spearman correlation between RNF43 mRNA expression levels in human gastric tissue samples (N = 13), and viability of organoids generated from the same tissue samples after treatment with (D) 5-fluorouracil or (E) cisplatin. RNF43 mRNA levels normalized to GAPDH also are shown. (F) AXIN2 and LGR5 mRNA levels in AGS, AGSD196fs, and MKN45 control and RNF43 knockdown cells. Cycle threshold (CT)values were normalized to GAPDH and fold change was calculated over control cells (N = 3). Error bars indicate SD. Horizontal lines represent the median values. ∗P ≤ .05, ∗∗P ≤ .01, (C and F) 2-tailed unpaired t test, (A, B, D, and E) Mann–Whitney test. mRNA, messenger RNA.\n\nFigure 5: Figure 5. RNF43 is involved in H pylori–induced DDR. (A) Western blot analysis and quantification of γH2AX and CHK2 expression in WT AGS, AGSD196fs, control MKN45 and AGS (shCtrl), and RNF43 knockdown MKN45 and AGS (shRNF43) cells upon H pylori PMSS1 infection at different multiplicity of infection (MOI). GAPDH was used as a loading control (N = 4). (B) RNF43 mRNA levels after H pylori infection of AGS and MKN45 cells. Cycle threshold (CT)values were normalized to GAPDH and fold change was calculated over uninfected cells (N = 4). (C) RNF43 mRNA levels normalized to GAPDH in gastric biopsy specimens from uninfected (n = 6) and H pylori–infected (n = 6) subjects. (D) Rnf43 mRNA levels in the stomach of WT mice (n = 13) after 3-month H pylori PMSS1 infection. CT values were normalized to Gapdh and fold change was calculated over uninfected mice (n = 6). Error bars indicate SD. ∗P ≤ .05, (A and B) 2-tailed unpaired t test, (C and D) Mann–Whitney test. GAPDH, glyceraldehyde-3-phosphate dehydrogenase; mRNA, messenger RNA."
      }
    ]
  },
  {
    "id": "PMC7898035_multi_2",
    "image": [
      "images/PMC7898035-f6.png",
      "images/PMC7898035-f7.png",
      "images/PMC7898035-f8.png",
      "images/PMC7898035-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Loss of RNF43 Function Contributes to Gastric Carcinogenesis by Impairing DNA Damage Response\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. RNF43 is involved in H pylori–induced DDR. (A) Colony forming units (CFU)/mg of stomach of WT (n = 13) and Rnf43ΔEx8 mice (n = 12), and inflammatory score after H pylori infection. Activity and chronicity were evaluated in antrum and corpus according to the updated Sydney system. Representative images and quantification of CD3, γH2AX, cleaved-caspase 3 (c-casp3), chloroacetate esterase (CAE)-positive cells (neutrophils and mast cells), and nuclear β-catenin–positive cells per square millimeter of tissue stained by immunohistochemistry in murine gastric tissue samples are shown. Arrowheads indicate positive cells. (B) Cxcl1, Ifng, and Tnfa mRNA levels in the stomach after 3-month H pylori PMSS1 infection. Cycle threshold (CT)values were normalized to Gapdh and fold change was calculated over uninfected mice. Horizontal lines represent the median values. ∗P ≤ .05, ∗∗P ≤ .01, and ∗∗∗P ≤ .001, Mann–Whitney test. mRNA, messenger RNA.\n\nFigure 7: Figure 7. RNF43 expression varies during gastric carcinogenesis. (A) Representative images and quantification of RNF43 and γH2AX-positive cells per square millimeter of human gastric tissue of healthy individuals (n = 20), and patients with gastritis (n = 24), intestinal metaplasia (n = 27), and intestinal-type (n = 20) or diffuse (n = 25) gastric cancer. Horizontal lines represent the median values. Each dot represents 1 sample. ∗P ≤ .05, ∗∗P ≤ .01, and ∗∗∗P ≤ .001, 1-way analysis of variance multiple comparisons. (B) Spearman correlation between the number of RNF43 and γH2AX-positive cells per square millimeter of human gastric tissue. Diff, diffuse; IM, intestinal metaplasia; Int, intestinal.\n\nFigure 8: Figure 8. RNF43 mutations upstream of the RING domain confer resistance to DNA damage. (A) Viability of gastric organoids (n = 40) carrying different SNP variants of RNF43 after treatment with 5-fluorouracil (5-FU) or cisplatin. Fold change was calculated over untreated organoids. Horizontal lines represent the median values. Mann–Whitney test. (B) Representative images and quantification of cell colonies after γ-radiation. (n = 4). (C) Cell viability after treatment with 5-FU or cisplatin. Values were normalized over untreated cells (n = 4). Error bars indicate SD. ∗P ≤ .05, 2-tailed unpaired t test. Rel, relative.\n\nFigure 9: Figure 9. RNF43 is up-regulated in response to DNA damage and it is recruited to sites of DNA damage. Representative immunofluorescence images of RNF43 (red) and γH2AX (green) in control and irradiated (A) AGS and (B) MKN45 cells. Scale bars: 10 μm. (C) Immunoprecipitation of RNF43 (human influenza hemagglutinin, HA) from AGS cells transfected with HA-tagged RNF43 upon γ-radiation (20 Grey), followed by Western blot analysis (n = 3; 1 representative experiment is shown). (D) Immunoprecipitation of γH2AX from AGS and MKN45 cells after radiation (20 Grey), followed by Western blot analysis. -, whole lysate. Quantification of ubiquitinated γH2AX from total γH2AX is shown (n = 3). Error bars indicate SD. ∗P ≤ .05, 2-tailed unpaired t test. DAPI, 4′,6-diamidino-2-phenylindole; IP, immunoprecipitation."
      }
    ]
  },
  {
    "id": "PMC7926225_multi",
    "image": [
      "images/PMC7926225-f1.png",
      "images/PMC7926225-f2.png",
      "images/PMC7926225-f3.png",
      "images/PMC7926225-f2-2.png",
      "images/PMC7926225-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MITOL promotes cell survival by degrading Parkin during mitophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. AMITOL interacts with Parkin under CCCP treatment. HeLa cells or HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 4 h. Lysates of cells were subjected to an IP assay with anti‐myc antibody and IB assay with the indicated antibodies.BInteraction of endogenous MITOL and Parkin in HeLa cells stably expressing HA‐Parkin. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 12 h and subjected to an IP‐IB assay with the indicated antibodies.CPINK1 knockdown decreases interaction between MITOL and Parkin. HeLa cells stably expressing HA‐Parkin were transfected with PINK1 siRNA or control siRNA and treated with DMSO or CCCP (10 μM) for 4 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP assay with anti‐myc antibody and IB assay with the indicated antibodies.DMITOL overexpression enhances the ubiquitination of Parkin. HeLa cells or HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. WT, wild‐type; CS, MITOL C65/67S mutant lacking ubiquitin ligase activity.EMITOL fails to ubiquitinate the Parkin K220R mutant. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after CCCP treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of WT, K129R, K220R, and K427R HA‐Parkin.FParkin is ubiquitinated by K48‐polyubiquitin in mitophagy. HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) for 48 h together with MG132 (30 μM) for the final 45 h. Parkin was immunoprecipitated from cell lysates and then performed ubiquitin restriction assay with AMSH, OTUB1, and USP2 using UbiCRest kit. Lysates of cells were subjected to an IB assay with the indicated antibodies. DUBs, deubiquitinating enzyme.GEndogenous MITOL enhances the K48‐polyubiquitin chains of Parkin. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) for indicated time. MG132 (30 μM) was added 3 h after CCCP treatment. Lysates of cells were fractionated into cytosolic, mitochondrial, and ER fractions, and then subjected to an IP‐IB assay with the indicated antibodies. K48‐polyubiquitin chains were immunoblotted with K48‐specific ubiquitin antibody. MITOL interacts with Parkin under CCCP treatment. HeLa cells or HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 4 h. Lysates of cells were subjected to an IP assay with anti‐myc antibody and IB assay with the indicated antibodies. Interaction of endogenous MITOL and Parkin in HeLa cells stably expressing HA‐Parkin. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 12 h and subjected to an IP‐IB assay with the indicated antibodies. PINK1 knockdown decreases interaction between MITOL and Parkin. HeLa cells stably expressing HA‐Parkin were transfected with PINK1 siRNA or control siRNA and treated with DMSO or CCCP (10 μM) for 4 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP assay with anti‐myc antibody and IB assay with the indicated antibodies. MITOL overexpression enhances the ubiquitination of Parkin. HeLa cells or HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. WT, wild‐type; CS, MITOL C65/67S mutant lacking ubiquitin ligase activity. MITOL fails to ubiquitinate the Parkin K220R mutant. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after CCCP treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of WT, K129R, K220R, and K427R HA‐Parkin. Parkin is ubiquitinated by K48‐polyubiquitin in mitophagy. HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) for 48 h together with MG132 (30 μM) for the final 45 h. Parkin was immunoprecipitated from cell lysates and then performed ubiquitin restriction assay with AMSH, OTUB1, and USP2 using UbiCRest kit. Lysates of cells were subjected to an IB assay with the indicated antibodies. DUBs, deubiquitinating enzyme. Endogenous MITOL enhances the K48‐polyubiquitin chains of Parkin. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) for indicated time. MG132 (30 μM) was added 3 h after CCCP treatment. Lysates of cells were fractionated into cytosolic, mitochondrial, and ER fractions, and then subjected to an IP‐IB assay with the indicated antibodies. K48‐polyubiquitin chains were immunoblotted with K48‐specific ubiquitin antibody.\n\nFigure 2: Figure 2. AInteraction of endogenous MITOL and Parkin in SH‐SY5Y cells. SH‐SY5Y cells were treated with DMSO or CCCP (10 μM) for 12 h and subjected to an IP‐IB assay with the indicated antibodies.BParkin interacts with C‐terminal region of MITOL. The schematic diagram shows the three truncated MITOL fragments that were fused to GST (Top). HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 4 h. Lysates of cells were performed GST pull‐down assay and then subjected to an IB assay with anti‐HA or anti‐GST antibodies (Bottom). (a) N‐terminal RING domain (1–90 aa); (b) second loop domain (160–209 aa); (c) C‐terminal domain (254–278 aa); TM, transmembrane.CThe C‐terminal deleted MITOL mutant failed to interact with Parkin. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 4 h. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. ΔRING, 14–68 aa deletion. Δ2nd, 160–209 aa deletion. ΔC, 254–278 aa deletion.DMITOL interacts with RING2 domain of Parkin. The schematic diagram shows the six truncated Parkin fragments that were fused to GST (Top). Mitochondrial fractions were isolated from HeLa cells and performed a GST pull‐down assay. IB assay was subjected with anti‐MITOL or anti‐GST antibodies (Bottom). (a) UBL domain (1–76 aa); (b) RING0 domain (141–224 aa); (c) RING1 domain (225–326 aa); (d) IBR domain (327–377 aa); (e) REP domain (378–409 aa); (f) RING2 domain (410–465 aa).EParkin K211N fails to interact with MITOL. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 4 h. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies.FParkin K211N mutant fails to translocate to the mitochondria in CCCP‐treated cells. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 8 h. Cells were immunostained with indicated antibody. Scale bar, 10 μm. Interaction of endogenous MITOL and Parkin in SH‐SY5Y cells. SH‐SY5Y cells were treated with DMSO or CCCP (10 μM) for 12 h and subjected to an IP‐IB assay with the indicated antibodies. Parkin interacts with C‐terminal region of MITOL. The schematic diagram shows the three truncated MITOL fragments that were fused to GST (Top). HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 4 h. Lysates of cells were performed GST pull‐down assay and then subjected to an IB assay with anti‐HA or anti‐GST antibodies (Bottom). (a) N‐terminal RING domain (1–90 aa); (b) second loop domain (160–209 aa); (c) C‐terminal domain (254–278 aa); TM, transmembrane. The C‐terminal deleted MITOL mutant failed to interact with Parkin. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 4 h. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. ΔRING, 14–68 aa deletion. Δ2nd, 160–209 aa deletion. ΔC, 254–278 aa deletion. MITOL interacts with RING2 domain of Parkin. The schematic diagram shows the six truncated Parkin fragments that were fused to GST (Top). Mitochondrial fractions were isolated from HeLa cells and performed a GST pull‐down assay. IB assay was subjected with anti‐MITOL or anti‐GST antibodies (Bottom). (a) UBL domain (1–76 aa); (b) RING0 domain (141–224 aa); (c) RING1 domain (225–326 aa); (d) IBR domain (327–377 aa); (e) REP domain (378–409 aa); (f) RING2 domain (410–465 aa). Parkin K211N fails to interact with MITOL. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 4 h. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. Parkin K211N mutant fails to translocate to the mitochondria in CCCP‐treated cells. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 8 h. Cells were immunostained with indicated antibody. Scale bar, 10 μm.\n\nFigure 3: Figure 3. AUbiquitylation of MITOL occurs in the early phase but not the late phase of mitophagy. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for indicated times. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. WT, wild‐type; CS, MITOL C65/67S mutant lacking ubiquitin ligase activity.BMITOL fails to ubiquitinate the Parkin K211N mutant. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of WT and K211N HA‐Parkin. Parkin K211N mutant; impaired mitochondrial translocation.C, DMITOL mediates K48‐linked polyubiquitination of Parkin. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies, and compared the effect of various KR FLAG‐ubiquitin (Ub) mutants (C) or RK FLAG‐Ub mutants (D) on MITOL‐mediated Parkin ubiquitination. KR ubiquitin mutant, turn single lysine to arginine (K48R or K63R); RK ubiquitin mutant, turn all lysine to arginine and then put back single lysine (R48K or R63K). Ubiquitylation of MITOL occurs in the early phase but not the late phase of mitophagy. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for indicated times. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. WT, wild‐type; CS, MITOL C65/67S mutant lacking ubiquitin ligase activity. MITOL fails to ubiquitinate the Parkin K211N mutant. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of WT and K211N HA‐Parkin. Parkin K211N mutant; impaired mitochondrial translocation. MITOL mediates K48‐linked polyubiquitination of Parkin. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies, and compared the effect of various KR FLAG‐ubiquitin (Ub) mutants (C) or RK FLAG‐Ub mutants (D) on MITOL‐mediated Parkin ubiquitination. KR ubiquitin mutant, turn single lysine to arginine (K48R or K63R); RK ubiquitin mutant, turn all lysine to arginine and then put back single lysine (R48K or R63K).\n\nFigure 2: Figure 2. AMITOL degrades Parkin through the ubiquitin–proteasome system. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h alone or either with bafilomycin A1 (10 μM) or lactacystin (10 μM) for the final 5 h. Lysates of cells were subjected to an IB assay with the indicated antibodies.BOverexpression of MITOL CS mutant fails to degrade Parkin. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for the indicated time. Lysates of cells were subjected to an IB assay with the indicated antibodies. MITOL CS mutant; lacking ubiquitin ligase activity.CParkin K220R mutant is not regulated by MITOL in mitophagy. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for the indicated time. Lysates of cells were subjected to an IB assay with the indicated antibodies.DEndogenous MITOL attenuates Parkin in both CHX‐ and CCCP‐treated conditions. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) as indicated times. CHX (30 μM) was added 5 h after CCCP treatment. Lysates of cells were subjected to an IB assay with the indicated antibodies.EMITOL regulates mitophagy. MITOL WT HeLa cells, MITOL KO HeLa cells, and KO HeLa cells transfected with MITOL WT plasmids 0.5 μg (+) and 5 μg (++) stably expressing HA‐Parkin and mt‐Keima were treated with CCCP (10 μM) for 8 h. Then, mKeima was measured at 488 (pH 7) and 561 (pH 4) nm lasers using Flow Cytometer. Percentages of mitophagy were calculated from 30,000 cells in each independent experiment. Data represent the mean ± SD of three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01. MITOL degrades Parkin through the ubiquitin–proteasome system. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h alone or either with bafilomycin A1 (10 μM) or lactacystin (10 μM) for the final 5 h. Lysates of cells were subjected to an IB assay with the indicated antibodies. Overexpression of MITOL CS mutant fails to degrade Parkin. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for the indicated time. Lysates of cells were subjected to an IB assay with the indicated antibodies. MITOL CS mutant; lacking ubiquitin ligase activity. Parkin K220R mutant is not regulated by MITOL in mitophagy. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for the indicated time. Lysates of cells were subjected to an IB assay with the indicated antibodies. Endogenous MITOL attenuates Parkin in both CHX‐ and CCCP‐treated conditions. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) as indicated times. CHX (30 μM) was added 5 h after CCCP treatment. Lysates of cells were subjected to an IB assay with the indicated antibodies. MITOL regulates mitophagy. MITOL WT HeLa cells, MITOL KO HeLa cells, and KO HeLa cells transfected with MITOL WT plasmids 0.5 μg (+) and 5 μg (++) stably expressing HA‐Parkin and mt‐Keima were treated with CCCP (10 μM) for 8 h. Then, mKeima was measured at 488 (pH 7) and 561 (pH 4) nm lasers using Flow Cytometer. Percentages of mitophagy were calculated from 30,000 cells in each independent experiment. Data represent the mean ± SD of three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01.\n\nFigure 5: Figure 5. AMITOL overexpression degrades Parkin on mitochondrial membrane. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 12 h. Lysates of cells were fractionated into mitochondria‐rich membrane fraction (Memb) and supernatant (Sup), and then subjected to an IB assay with the indicated antibodies. Loading was adjusted for approximately equal concentrations of VDAC in the membrane fraction (Memb).BEndogenous MITOL attenuates mitophagy in CHX‐treated cells. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 30 h. CHX (30 μM) was added 5 h after CCCP treatment. Lysates of cells were subjected to an IB assay with the indicated antibodies.CMITOL has the specificity for the substrate. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of HA‐Parkin and MITOL‐HA to Mito‐GFP.DParkin K220R mutant normally translocated to the mitochondria in CCCP‐treated cells. HeLa cells were transfected with indicated vectors and treated with CCCP (10 μM) for 3 h. Cells were immunostained with indicated antibody. Scale bar, 10 μm.EMt‐Keima signal is responding to autophagy process. MITOL WT HeLa cells and MITOL KO HeLa cells expressing HA‐Parkin and mt‐Keima were treated with DMSO or CCCP (10 μM) for 8 h alone or either with bafilomycin A1 (10 μM). Then, mKeima was measured at 488 (pH 7) and 561 (pH 4) nm lasers using Flow Cytometer. Percentages of mitophagy were calculated from 30,000 cells.FParkin K220R mutant induces mitophagy even in the overexpression of MITOL. HeLa cells stably expressing mt‐Keima were transfected with indicated vectors and treated with CCCP (10 μM) for 8 h. Then, mKeima was measured at 488 (pH 7) and 561 (pH 4) nm lasers using Flow Cytometer. Percentages of mitophagy were calculated from 30,000 cells in each independent experiment. Data represent the mean ± SD of three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01. MITOL overexpression degrades Parkin on mitochondrial membrane. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 12 h. Lysates of cells were fractionated into mitochondria‐rich membrane fraction (Memb) and supernatant (Sup), and then subjected to an IB assay with the indicated antibodies. Loading was adjusted for approximately equal concentrations of VDAC in the membrane fraction (Memb). Endogenous MITOL attenuates mitophagy in CHX‐treated cells. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 30 h. CHX (30 μM) was added 5 h after CCCP treatment. Lysates of cells were subjected to an IB assay with the indicated antibodies. MITOL has the specificity for the substrate. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 8 h. MG132 (30 μM) was added 3 h after each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of HA‐Parkin and MITOL‐HA to Mito‐GFP. Parkin K220R mutant normally translocated to the mitochondria in CCCP‐treated cells. HeLa cells were transfected with indicated vectors and treated with CCCP (10 μM) for 3 h. Cells were immunostained with indicated antibody. Scale bar, 10 μm. Mt‐Keima signal is responding to autophagy process. MITOL WT HeLa cells and MITOL KO HeLa cells expressing HA‐Parkin and mt‐Keima were treated with DMSO or CCCP (10 μM) for 8 h alone or either with bafilomycin A1 (10 μM). Then, mKeima was measured at 488 (pH 7) and 561 (pH 4) nm lasers using Flow Cytometer. Percentages of mitophagy were calculated from 30,000 cells. Parkin K220R mutant induces mitophagy even in the overexpression of MITOL. HeLa cells stably expressing mt‐Keima were transfected with indicated vectors and treated with CCCP (10 μM) for 8 h. Then, mKeima was measured at 488 (pH 7) and 561 (pH 4) nm lasers using Flow Cytometer. Percentages of mitophagy were calculated from 30,000 cells in each independent experiment. Data represent the mean ± SD of three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01."
      }
    ]
  },
  {
    "id": "PMC7926225_multi_2",
    "image": [
      "images/PMC7926225-f3-2.png",
      "images/PMC7926225-f7.png",
      "images/PMC7926225-f4.png",
      "images/PMC7926225-f9.png",
      "images/PMC7926225-f5-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MITOL promotes cell survival by degrading Parkin during mitophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 3: Figure 3. AMITOL was not degraded in mitophagy. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 48 h and subjected to an IB assay with the indicated antibodies.BSchematic diagram of EGFP knock‐in for N‐terminal tagging. MITOL‐specific and PITCh‐specific sgRNAs expressed from pX330A‐MITOL/PITCh (not shown) individually target the MITOL exon 1 locus and the donor vector. This allows for both the cleavage of the genomic locus and the release of the EGFP‐containing cassette. MMEJ leads to the repair of double‐strand break via the insertion of the EGFP‐containing cassette, resulting in endogenously EGFP tagged MITOL.CEndogenous MITOL translocates to the ER in later phase of mitophagy. EGFP‐MITOL knock‐in HeLa cells were transfected with HA‐Parkin and treated with DMSO or CCCP (10 μM) as indicated times. Cells were fixed, permeabilized, and subjected to immunofluorescence analysis with the indicated antibodies. Colocalization was quantified by Manders’s coefficient. Means ± SEM of more than 10 cells obtained from three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey's multiple comparisons test was performed, ****P < 0.0001. Scale bar represents 1 μm.DMITOL interacts with FKBP38. HeLa cells or HeLa cells stably expressing mCherry‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for indicated times. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies.EER‐localized MITOL is transported from the mitochondria and is not newly synthesized protein. HeLa cells stably expressing HA‐Parkin were co‐transfected with vectors for MITOL‐KikGR and FLAG‐FKBP38. After ultraviolet light (365 nm) exposure to the whole plate, cells were incubated with or without CCCP (10 μM) for indicated time, and monitored for red and green KikGR fluorescence. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown in the small panel. Right panel is schematic experimental model for KikGR in this study. MITOL was not degraded in mitophagy. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 48 h and subjected to an IB assay with the indicated antibodies. Schematic diagram of EGFP knock‐in for N‐terminal tagging. MITOL‐specific and PITCh‐specific sgRNAs expressed from pX330A‐MITOL/PITCh (not shown) individually target the MITOL exon 1 locus and the donor vector. This allows for both the cleavage of the genomic locus and the release of the EGFP‐containing cassette. MMEJ leads to the repair of double‐strand break via the insertion of the EGFP‐containing cassette, resulting in endogenously EGFP tagged MITOL. Endogenous MITOL translocates to the ER in later phase of mitophagy. EGFP‐MITOL knock‐in HeLa cells were transfected with HA‐Parkin and treated with DMSO or CCCP (10 μM) as indicated times. Cells were fixed, permeabilized, and subjected to immunofluorescence analysis with the indicated antibodies. Colocalization was quantified by Manders’s coefficient. Means ± SEM of more than 10 cells obtained from three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey's multiple comparisons test was performed, ****P < 0.0001. Scale bar represents 1 μm. MITOL interacts with FKBP38. HeLa cells or HeLa cells stably expressing mCherry‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for indicated times. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. ER‐localized MITOL is transported from the mitochondria and is not newly synthesized protein. HeLa cells stably expressing HA‐Parkin were co‐transfected with vectors for MITOL‐KikGR and FLAG‐FKBP38. After ultraviolet light (365 nm) exposure to the whole plate, cells were incubated with or without CCCP (10 μM) for indicated time, and monitored for red and green KikGR fluorescence. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown in the small panel. Right panel is schematic experimental model for KikGR in this study.\n\nFigure 7: Figure 7. AMITOL translocates from the mitochondria to the ER in the late phase of mitophagy with FKBP38. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 48 h. Cells were fixed, permeabilized, and subjected to immunofluorescence analysis with indicated antibodies. Colocalization was quantified by Manders’s coefficient. Means ± SEM of more than 10 cells obtained from three independent experiments. For statistical analysis, Student’s t‐tests were performed, ****P < 0.0001. Scale bar represents 10 μm. Higher magnification images of the boxed regions are shown in the small panel.BInteraction of endogenous MITOL and FKBP38. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for indicated times and subjected to an IP‐IB assay with the indicated antibodies.C, DMITOL translocation depends on FKBP38. HeLa cells stably expressing HA‐Parkin were transfected with FKBP38 siRNA or control siRNA and treated with DMSO or CCCP (10 μM) for 30 h. Lysates of cells were fractioned into whole‐cell, cytosolic, ER, and mitochondrial fractions and then subjected to an IB assay with the indicated antibodies (C). MITOL KO HeLa cells stably expressing HA‐Parkin were transfected with MITOL‐myc and treated with DMSO or CCCP (10 μM) for 48 h. Cells were immunostained with indicated antibodies (D). Scale bar, 10 μm. MITOL translocates from the mitochondria to the ER in the late phase of mitophagy with FKBP38. HeLa cells stably expressing HA‐Parkin were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for 48 h. Cells were fixed, permeabilized, and subjected to immunofluorescence analysis with indicated antibodies. Colocalization was quantified by Manders’s coefficient. Means ± SEM of more than 10 cells obtained from three independent experiments. For statistical analysis, Student’s t‐tests were performed, ****P < 0.0001. Scale bar represents 10 μm. Higher magnification images of the boxed regions are shown in the small panel. Interaction of endogenous MITOL and FKBP38. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for indicated times and subjected to an IP‐IB assay with the indicated antibodies. MITOL translocation depends on FKBP38. HeLa cells stably expressing HA‐Parkin were transfected with FKBP38 siRNA or control siRNA and treated with DMSO or CCCP (10 μM) for 30 h. Lysates of cells were fractioned into whole‐cell, cytosolic, ER, and mitochondrial fractions and then subjected to an IB assay with the indicated antibodies (C). MITOL KO HeLa cells stably expressing HA‐Parkin were transfected with MITOL‐myc and treated with DMSO or CCCP (10 μM) for 48 h. Cells were immunostained with indicated antibodies (D). Scale bar, 10 μm.\n\nFigure 4: Figure 4. APhosphorylated Parkin accumulates in MITOL KO cells. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for the indicated time and subjected to IB assay with the indicated antibodies. Other cell lysates were subsequently separated on a Phos‐tag gel, followed by IB with anti‐Parkin antibodies (Phos‐tag). p‐Parkin, phosphorylated Parkin.BAccumulation of activated Parkin in MITOL KO cells. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) for 30 h and then performed Duolink in situ proximity ligation (PLA) assay demonstrating the interaction between Parkin and Ubiquitin. Scale bar, 5 μm. Higher magnification images of the boxed regions are shown in the small panel.CPhosphorylated Parkin accumulates in the ER fraction in the absence of MITOL. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 48 h. Lysates of cells were fractionated into cytosolic, mitochondrial, and ER fractions, and then subjected to an IB assay with the indicated antibodies. Phospho‐Ser65‐Parkin is detected by using specific antibody. Right panels are the quantification of IB about Phospho‐Ser65‐Parkin protein levels of the ER fraction. The data represent the mean ± SD for three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01.DParkin is detected at the ER in the absence of MITOL. HeLa cells were transfected with vectors for KikGR‐Parkin. After ultraviolet light (365 nm) exposure to the whole plate, cells were incubated with or without CCCP (10 μM) for indicated time, and monitored for red and green KikGR fluorescence. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown in the small panel. Phosphorylated Parkin accumulates in MITOL KO cells. HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for the indicated time and subjected to IB assay with the indicated antibodies. Other cell lysates were subsequently separated on a Phos‐tag gel, followed by IB with anti‐Parkin antibodies (Phos‐tag). p‐Parkin, phosphorylated Parkin. Accumulation of activated Parkin in MITOL KO cells. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with CCCP (10 μM) for 30 h and then performed Duolink in situ proximity ligation (PLA) assay demonstrating the interaction between Parkin and Ubiquitin. Scale bar, 5 μm. Higher magnification images of the boxed regions are shown in the small panel. Phosphorylated Parkin accumulates in the ER fraction in the absence of MITOL. WT or MITOL KO HeLa cells stably expressing HA‐Parkin were treated with DMSO or CCCP (10 μM) for 48 h. Lysates of cells were fractionated into cytosolic, mitochondrial, and ER fractions, and then subjected to an IB assay with the indicated antibodies. Phospho‐Ser65‐Parkin is detected by using specific antibody. Right panels are the quantification of IB about Phospho‐Ser65‐Parkin protein levels of the ER fraction. The data represent the mean ± SD for three independent experiments. For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01. Parkin is detected at the ER in the absence of MITOL. HeLa cells were transfected with vectors for KikGR‐Parkin. After ultraviolet light (365 nm) exposure to the whole plate, cells were incubated with or without CCCP (10 μM) for indicated time, and monitored for red and green KikGR fluorescence. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown in the small panel.\n\nFigure 9: Figure 9. AParkin accumulation in the ER does not depend on FKBP38. MITOL KO HeLa cells stably expressing HA‐Parkin were transfected with FKBP38 siRNA or control siRNA and treated with CCCP (10 μM) for 48 h. Lysates of cells were fractionated into ER fractions and then subjected to IB assay with indicated antibodies.BFKBP38IYFFT and FKBP38ActA are accurately localized in each targeting organelle. HeLa cells stably expressing HA‐Parkin were transfected with indicated vectors and immunostained with indicated antibodies. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown in the small panel. Parkin accumulation in the ER does not depend on FKBP38. MITOL KO HeLa cells stably expressing HA‐Parkin were transfected with FKBP38 siRNA or control siRNA and treated with CCCP (10 μM) for 48 h. Lysates of cells were fractionated into ER fractions and then subjected to IB assay with indicated antibodies. FKBP38IYFFT and FKBP38ActA are accurately localized in each targeting organelle. HeLa cells stably expressing HA‐Parkin were transfected with indicated vectors and immunostained with indicated antibodies. Scale bar, 10 μm. Higher magnification images of the boxed regions are shown in the small panel.\n\nFigure 5: Figure 5. AUbiquitination of FKBP38 depends on Parkin E3 activity. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for indicated times. MG132 (30 μM) was added 1 h before each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. WT, wild‐type.BParkin fails to ubiquitinate the FKBP38 K271/273R mutant. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 30 h. MG132 (30 μM) was added 5 h after CCCP treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of WT, K271R, K273R, and K271/273R FLAG‐FKBP38.COverexpression of WT FKBP38 is degraded in MITOL KO cells in mitophagy. MITOL KO HeLa cells stably expressing HA‐Parkin were transfected with WT or K271/273R mutant FLAG‐FKBP38 and treated with DMSO or CCCP (10 μM) for 24 h. Lysates of cells were subjected to an IB assay with the indicated antibodies.DMITOL KO increases degradation of ER targeting FKBP38. HeLa cells stably expressing HA‐Parkin were transfected with mitochondrial targeting FLAG‐FKBP38 (FKBP38ActA) and ER targeting FLAG‐FKBP38 (FKBP38IYFFT), and treated with DMSO or CCCP (10 μM) for 24 h. Lysates of cells were subjected to an IB assay with FLAG antibodies for organelle targeting FKBP38 or indicated antibodies. Another cell lysates were subsequently separated on a Phos‐tag gel, followed by IB with anti‐Parkin antibodies (Phos‐tag).E–GMITOL partly prevents CCCP‐induced cell death by reducing Parkin‐mediated degradation of FKBP38. WT or MITOL KO HeLa cells stably expressing HA‐Parkin and HeLa cells were transfected with the indicated vectors, and treated with DMSO or CCCP (10 μM) for 24 h. Cells were stained with propidium iodide (PI) for counting the percentage of dead cells using fluorescence microscopy. Data represent the mean ± SD of five independent experiments (>100 individual cells were counted). For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01. KR, FKBP38 K271/273R. Ubiquitination of FKBP38 depends on Parkin E3 activity. HeLa cells were transfected with the indicated vectors and treated with DMSO or CCCP (10 μM) for indicated times. MG132 (30 μM) was added 1 h before each treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies. WT, wild‐type. Parkin fails to ubiquitinate the FKBP38 K271/273R mutant. HeLa cells were transfected with the indicated vectors and treated with CCCP (10 μM) for 30 h. MG132 (30 μM) was added 5 h after CCCP treatment. Lysates of cells were subjected to an IP‐IB assay with the indicated antibodies and compared ubiquitination levels of WT, K271R, K273R, and K271/273R FLAG‐FKBP38. Overexpression of WT FKBP38 is degraded in MITOL KO cells in mitophagy. MITOL KO HeLa cells stably expressing HA‐Parkin were transfected with WT or K271/273R mutant FLAG‐FKBP38 and treated with DMSO or CCCP (10 μM) for 24 h. Lysates of cells were subjected to an IB assay with the indicated antibodies. MITOL KO increases degradation of ER targeting FKBP38. HeLa cells stably expressing HA‐Parkin were transfected with mitochondrial targeting FLAG‐FKBP38 (FKBP38ActA) and ER targeting FLAG‐FKBP38 (FKBP38IYFFT), and treated with DMSO or CCCP (10 μM) for 24 h. Lysates of cells were subjected to an IB assay with FLAG antibodies for organelle targeting FKBP38 or indicated antibodies. Another cell lysates were subsequently separated on a Phos‐tag gel, followed by IB with anti‐Parkin antibodies (Phos‐tag). MITOL partly prevents CCCP‐induced cell death by reducing Parkin‐mediated degradation of FKBP38. WT or MITOL KO HeLa cells stably expressing HA‐Parkin and HeLa cells were transfected with the indicated vectors, and treated with DMSO or CCCP (10 μM) for 24 h. Cells were stained with propidium iodide (PI) for counting the percentage of dead cells using fluorescence microscopy. Data represent the mean ± SD of five independent experiments (>100 individual cells were counted). For statistical analysis, a one‐way ANOVA with Tukey post‐test was performed, **P < 0.01. KR, FKBP38 K271/273R."
      }
    ]
  },
  {
    "id": "PMC7935121_multi",
    "image": [
      "images/PMC7935121-f1.png",
      "images/PMC7935121-f2.png",
      "images/PMC7935121-f3.png",
      "images/PMC7935121-f4.png",
      "images/PMC7935121-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Trim46 contributes to the midbrain development via Sonic Hedgehog signaling pathway in zebrafish embryos\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematic diagrams of the ORF of trim46a and protein structures of Trim46a. (A) Zebrafish trim46a is present on chromosome 16 and spans 27,494 bp on the genome. trim46a includes 2322 bp of open reading frame (ORF) encoding 773 amino acids long Trim46a. (B) Trim46a contains RING_Ubox superfamily domain (amino acids 26–60), zf-B box domain (amino acids 221–263), DUF745 superfamily domain (amino acids 289–360), FN3 domain (amino acids 430–540), and SPRY superfamily domain (amino acids 548–748).\n\nFigure 2: Figure 2. Spatiotemporal expression patterns of trim46a in zebrafish embryos at 1 cell, sphere, shield, bud, 18 hpf and 24 hpf. trim46a transcripts were distributed in the precursor region of brain along the central nervous system. (A) Maternal messages of trim46a were present at 1-cell stage. (B) trim46a transcripts were abundant in the deep cell layer (DEL), enveloping layer (EVL) and I-YSL (yolk syncytial layer) at sphere stage. (C) trim46a transcripts were localized to the ventral & dorsal region at shield stage. (D) trim46a transcripts were abundant in the central nervous system at bud stage. (E and F) trim46a transcripts were evenly distributed in the brain region. (G and H) Lateral (G) and anterior (H) view of zebrafish embryos at 24 hpf; trim46a messages were restricted to the forebrain through the telencephalon, diencephalon, midbrain, MHB, cerebellum and rhombomere. All embryos were collected synchronously from WT zebrafish for WISH analysis at the corresponding stages. MHB, midbrain-hindbrain boundary; DMB, diencephalic-mesencephalic boundary; c, cerebellum; rh, rhombomere; t, telencephalon; m, midbrain; d, diencephalon; f, forebrain. (A–H) Scale bars: 50 μm.\n\nFigure 3: Figure 3. Putative cis-acting elements in the promoter region (3899 bp) of trim46a. Putative cis-acting elements defined by the Transfac database (Wingender et al. 1996). (A) Schematic representation of zebrafish trim46a genomic region. Twelve exons (E1 to E12) and eleven introns are depicted; the translation initiation site is indicated with an arrow. (B) List of the sixteen transcription factors which might bind to their corresponding response elements within the trim46a promoter (3899 bp). (C) The putative transcription factors are highlighted in bold and blue color represents exon1 (Cut-off p-value = 0).\n\nFigure 4: Figure 4. Inhibition of SHH signaling with cyclopamine resulted in developmental defects in the midbrain of zebrafish embryos at 24 hpf. (A–D) Zebrafish embryos at 24 hpf which were treated 0.2% and 0.6% EtOH from 4 hpf. 0.6% EtOH-exposed embryos showed similar phenotypes of midbrain and MHB in comparison to those of 0.2% EtOH-exposed embryos. (E and F) Cyclopamine-treated embryos (20 μM) showed reduction in width of the midbrain and dorsally shrunken midbrain in comparison to those of EtOH controls. (G and H) 60 μM cyclopamine-treated embryos exhibited severe defects in the midbrain. (I–L) Spatiotemporal expression patterns of otx2b in the midbrain of cyclopamine-treated embryos at 24 hpf. CCP, cyclopamine. (A–L) Scale bars: 50 μm.\n\nFigure 5: Figure 5. Inhibition of SHH signaling by cyclopamine decreased the level of trim46a transcripts in dose-dependent manners. (A–D) WISH analysis using foxa2 specific probe detected foxa2 transcripts in the midbrain at 24 hpf. Level of foxa2 transcripts decreased in the embryos treated with cyclopamine versus the control. (E–H) WISH analysis of cyclopamine-treated embryos using trim46a as a probe. Cyclopamine caused reduction in the level of trim46a transcripts in comparison to those of EtOH control in dose-dependent manners. (I) Quantification of foxa2 transcripts in the ZLI, and trim46a transcripts in the forebrain, midbrain and cerebellum at 24 hpf using ImageJ software. CCP, cyclopamine. (A–H) Scale bars: 50 μm."
      }
    ]
  },
  {
    "id": "PMC7952519_multi",
    "image": [
      "images/PMC7952519-f1.png",
      "images/PMC7952519-f2.png",
      "images/PMC7952519-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Case Report: A Novel de novo Mutation in DNM1L Presenting With Developmental Delay, Ataxia, and Peripheral Neuropathy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Brain magnetic resonance imaging (MRI) findings. (A) Bilateral symmetrical hyperintense lesions of periventricular white matter on T2-weighted images. (B) Thinning of the corpus callosum from sagittal view shown on axial T1-weighted images.\n\nFigure 2: Figure 2. Structure-based domain architecture of human DNM1L. The first and last residue of each domain are labeled. The classical predicted domain assignments including the G domain, middle assembly domain (MSD), B domain, and the GTPase effector domain (GED) are shown below. The mutation p.G149R was located at the G domain (black arrow).\n\nFigure 3: Figure 3. Crystal structure of DNM1L in ribbon representation (pdb code 4BEJ). The identified mutation site in the nucleotide-binding cleft is indicated."
      }
    ]
  },
  {
    "id": "PMC7966871_multi",
    "image": [
      "images/PMC7966871-f1.png",
      "images/PMC7966871-f2.png",
      "images/PMC7966871-f3.png",
      "images/PMC7966871-f4.png",
      "images/PMC7966871-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of hepatic circadian metabolism by the E3 ubiquitin ligase HRD1-controlled CREBH/PPARα transcriptional program\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Hepatic HRD1/Sel1L expression exhibits circadian rhythmicity and is regulated by CREBH. (A) Western blot analysis of rhythmic levels of HRD1, Sel1L, CREBH, and GAPDH proteins in the livers of CREBH KO and WT mice, collected every 4 h in a 24-h circadian period. Liver protein lysates from 3 to 5 mice per time point per genotype group were used. The graphs show the quantification of the protein levels in mouse livers over the circadian cycle. The intensity of the protein signals, determined by Western blot densitometry, was normalized to that of GAPDH. Fold changes in protein levels were determined by comparison to the protein level in one of the WT control mice at 6 PM. Data are mean ± SEM (n = 3 experimental replicates). ∗P < 0.05. Black and white bars represent circadian light/dark phases. P, CREBH precursor; A, activated form of CREBH. (B–C) Rhythmic expression levels of HRD1 and Sel1L genes in the livers of CREBH KO and WT control mice across a 24-h circadian cycle. The mRNA expression levels were determined by qPCR. Fold changes in mRNA levels were determined by comparison to levels in one of the WT control mice at 6 PM. Data represent means ± SEM (n = 3–5 mice/genotype/time point). ∗P < 0.05.\n\nFigure 2: Figure 2. CREBH and PPARα directly activate expression of the Hrd1 and/or Sel1L genes in the liver. (A) Illustration of CREBH- or PPARα-binding sites in the promoter region of the human (hs) or mouse (ms) Hrd1 and Sel1L genes. (B) ChIP analysis of CREBH- and PPARα-binding activities to the endogenous Hrd1 and Sel1L gene promoters in the livers of WT mice. For ChIP-PCR, isolated mouse chromatins were immunoprecipitated with the antibody against CREBH, PPARα, or no antibody. Non-immunoprecipitated chromatins were included as input controls. PCR reactions were conducted using the primers amplifying the CRE or PPRE-binding motif present in the mouse Hrd1 or Sel1L gene promoter (sequences provided in S-Figure 1). The amplified PCR products were visualized on agarose gels. (C–D) Binding activities of mouse liver NEs expressing GFP, CREBH, or PPARα to the CRE- or PPRE-containing promoter regions of mouse Hrd1 or Sel1L genes. EMSA was performed using the liver NEs from WT mice infected with adenovirus expressing GFP, CREBH, or PPARα and the mouse Hrd1 or Sel1L gene probe containing the CRE- and/or PPRE-binding motifs. Free probe (FP) indicates the control reaction with the CRE or PPRE probe in the absence of NE. The sequences of mouse Hrd1 or Sel1L promoter oligonucleotides containing CRE or PPRE motif used for EMSA were indicated. The protein-DNA binding complexes were visualized by shifted signals and highlighted by arrows. (E) Expression levels of Hrd1 and Sel1L mRNAs in the livers of mice infected with adenovirus (Ad) overexpressing GFP, activated CREBH, or PPARα. mRNA expression levels were determined by qPCR. Fold changes in mRNA levels were determined. Data represent means ± SEM (n = 3). ∗P < 0.05, ∗∗P < 0.01. (F–G) PPARα-null mice were infected with recombinant adenovirus (Ad) expressing GFP or the activated form of CREBH, whereas CREBH-null mice were infected with Ad expressing GFP or PPARα via tail vein injection. Total liver RNAs and protein samples were prepared from mice under 14 h fasting. Levels of the Hrd1 and Sel1L mRNAs (F) or CREBH, PPARα, HRD1, Sel1L, and GAPDH proteins (G) in mouse livers were determined by qPCR or Western blot analysis. The graphs in panel G show the fold changes of HRD1 and Sel1L protein levels, determined by Western blot densitometry, in mouse livers. Fold change of the normalized protein levels was calculated by comparing to the level in one of PPARα KO mice expressing GFP. Data represent means ± SEM (n = 3 experimental replicates). ∗P < 0.05 and ∗∗P < 0.01 for PPARα KO + CREBH vs PPARα KO + GFP or CREBH KO + PPARα vs CREBH KO + GFP.\n\nFigure 3: Figure 3. BMAL1 controls circadian rhythmic expression of HRD1/Sel1L in the liver through regulating CREBH. (A) Rhythmic expression levels of Bmal1, CrebH, Hrd1, and Sel1L genes in the livers of Bmal1 LKO and fl/fl control mice across a 24-h circadian cycle. The liver total RNAs were prepared from the mice collected every 3 h during a 24-h circadian period. The mRNA expression levels were determined by qPCR. Fold changes in mRNA levels were determined by comparison to levels in one of the control mice at 10 AM. Data represent means ± SEM (n = 3–4 mice/genotype/time point). ∗P < 0.05, ∗∗P < 0.01. (B) Western blot analysis of HRD1, Sel1L, CREBH, BMAL1, and GAPDH protein levels in Bmal1 knockdown and control primary hepatocytes during a 48-h circadian cycle. Mouse primary hepatocytes were infected with adenovirus expressing Bmal1 shRNA or control LacZ shRNA for 24 h before being subjected to horse serum shock for circadian synchronization. Cell lysates were collected at 8-h intervals during a 48-h circadian cycle for Western blot analysis to determine levels of HRD1, Sel1L, BMAL1, and GAPDH. The graphs show the rhythmic fold changes of HRD1 and Sel1L proteins in Bmal1 knockdown and control primary hepatocytes during the circadian cycle. Protein signals, determined by Western blot densitometry, were normalized to that of GAPDH. Fold change of the normalized HRD1 or Sel1L protein levels at each circadian time point was calculated by comparing to the level in control cells at the starting circadian time. Data are mean ± SEM (n = 3 experimental replicates). ∗P < 0.05, ∗∗P < 0.01. CT, circadian time. (C) Western blot analyses of BMAL1, CREBH, HRD1, Sel1L, and GAPDH in Bmal1-knockdown and WT control mouse primary hepatocytes expressing the activated CREBH or GFP control under the circadian clock. Mouse primary hepatocytes were infected with Ad expressing Bmal1 shRNA, the activated form of CREBH (Flag-tagged), or GFP before being subjected to horse serum shock for circadian synchronization. Primary hepatocytes from WT mice were infected with Ad expressing GFP (WT-GFP) were included as a control. Cell lysates were collected throughout a 32-h circadian cycle for Western blot analyses. The graphs show the rhythmic fold changes of HRD1 and Sel1L protein levels, determined by Western blot densitometry, in Bmal1-knockdown and WT control hepatocytes expressing CREBH or GFP control. Fold change of normalized protein levels at each circadian time point was calculated by comparing to the level in control cells at the starting circadian time. Data are mean ± SEM (n = 3 experimental replicates). ∗P < 0.05, ∗∗P < 0.01.\n\nFigure 4: Figure 4. HRD1 is required to maintain circadian rhythmic levels of circulating TG, FFA, BOH, and glucose in mice. (A–D) Levels of serum TG, FFA, BOH, and glucose in HRD1 LKO and WT mice under the circadian clock. Blood samples were collected every 3 h across a 24-h circadian cycle. (E) Levels of hepatic TG of HRD1 LKO and WT mice under the circadian clock. The liver tissue samples from HRD1 LKO and WT control mice were collected every 3 h across a 24-h circadian cycle. Data are mean ± SEM (n = 3 mice/genotype/time point). ∗P < 0.05, ∗∗P < 0.01. TG, triglycerides; FFA, free fatty acids; BOH, β-Hydroxybutyrate.\n\nFigure 5: Figure 5. HRD1 regulates rhythmic expression of the gene involved in hepatic FA oxidation, TG lipolysis, lipophagy, and gluconeogenesis. (A–E) Rhythmic expression of the genes encoding the key enzymes or regulators involved in FA oxidation, TG lipolysis, lipophagy, and gluconeogenesis in HRD1 LKO and WT mouse livers across the circadian cycle. Levels of mRNA were determined by qPCR. Fold changes of mRNA levels were calculated by comparing to the level in one of the WT mice at 6 PM. Data are mean ± SEM (n = 3 mice/genotype/time point). ∗P < 0.05, ∗∗P < 0.01."
      }
    ]
  },
  {
    "id": "PMC7966871_multi_2",
    "image": [
      "images/PMC7966871-f6.png",
      "images/PMC7966871-f7.png",
      "images/PMC7966871-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of hepatic circadian metabolism by the E3 ubiquitin ligase HRD1-controlled CREBH/PPARα transcriptional program\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. HRD1 LKO mice contrast with CREBH KO mice in circadian rhythmic profiles of energy consumption. (A–B) Circadian rhythmic profiles of RER (respiratory exchange ratio) of HRD1 LKO, CREBH KO, and WT control mice under the circadian clock, determined by the comprehensive metabolic cage PhenoMaster System. The graphs show quantification of RERs of HRD1 LKO, CREBH KO, and WT control mice during the nighttime (6 PM–6 AM) and daytime (6 AM–6 PM) periods. Each bar donates mean ± SEM (n = 10 mice for HRD1 LKO vs WT or 6 mice for CREBH KO vs WT). ∗p < 0.05; ∗∗p < 0.01. (C–D) Quantification of lean body VO2 (C) and energy expenditure (D) of HRD1 LKO, CREBH KO, and WT control mice during the nighttime and daytime periods. The quantitative analyses were based on the data generated through the measurement by the comprehensive metabolic cage PhenoMaster System. Each bar denotes mean ± SEM (n = 10 mice for HRD1 LKO vs WT or 6 mice for CREBH KO vs WT). ∗p < 0.05; ∗∗p < 0.01.\n\nFigure 7: Figure 7. HRD1 promotes circadian rhythmic polyubiquitination and degradation of CREBH protein. (A) Circadian rhythmic expression of the CrebH mRNA in HRD1 LKO and WT mouse livers. Levels of mRNA were determined by qPCR. Fold changes of mRNA levels were calculated by comparing to the level in one of the WT mice at 6 PM. Data are mean ± SEM (n = 3 mice/genotype/time point). ∗∗P < 0.01. (B) IP-Western blot analyses of CREBH protein polyubiquitination and CREBH-HRD1 interaction in the livers of HRD1 LKO and WT control mice across the circadian cycle. The liver protein lysates were prepared from liver tissues of HRD1 LKO and WT mice collected every 3 h during a 24-h circadian period (n = 3 mice/genotype/time point). The liver protein lysates were pulled down by the rabbit polyclonal anti-CREBH antibody, followed by immunoblotting with the anti-ubiquitin (Ub), anti-HRD1, or anti-CREBH antibody. Levels of GAPDH were determined by immunoblotting as controls. (C) Western blot analyses of CREBH, PPARα, HRD1, and GAPDH protein levels in the livers of HRD1 LKO and WT control mice across the circadian cycle. The liver protein lysates were prepared from liver tissues of HRD1 LKO and WT mice collected every 3 h during a 24-h circadian period (n = 3 mice/genotype/time point). P, CREBH precursor/full-length protein; A, activated/cleaved CREBH protein. The graphs show rhythmic fold changes of CREBH and PPARα protein levels, determined by Western blot densitometry, in the livers of HRD1 LKO and control. Fold change of the normalized protein levels was determined by comparing to the level in one of the WT mice at 6 PM. Data are mean ± SEM (n = 3 experimental replicates). ∗P < 0.05.\n\nFigure 8: Figure 8. Suppression of CREBH rescues the elevated circadian expression of the major lipid mobilization-promoting factors and the reduction of serum lipids in HRD1 LKO mice. (A) Western blot analyses of PPARα, SIRT1, HRD1, CREBH, and GAPDH in the livers of WT or HRD1 LKO mice infected with Ad expressing CREBH shRNA or control shRNA at the representative nighttime (6 PM) or daytime (6 AM) period. The liver protein lysates were prepared from liver tissues of WT or HRD1 LKO mice (n = 3 mice/genotype/time point). The graphs show the rhythmic fold changes of PPARα and SIRT1 protein levels, determined by Western blot densitometry, in WT or HRD1 LKO mouse livers expressing CREBH shRNA or control shRNA. Fold change of the normalized protein levels was calculated by comparing to the level in one of WT mice at 6 PM. The bars denote mean ± SEM (n = 3 experimental replicates). ∗P < 0.05, ∗∗P < 0.01. (B) Expression levels of the genes involved in FA oxidation, TG lipolysis, and lipophagy in the livers of WT or HRD1 LKO mice infected with Ad expressing CrebH shRNA or control shRNA at the representative nighttime (6 PM) or daytime (6 AM) period. Levels of mRNA were determined by qPCR. Fold changes of mRNA levels were calculated by comparing to the level in one of the WT mice at 6 PM. Data are mean ± SEM (n = 3 mice/genotype/time point). ∗P < 0.05 and ∗∗P < 0.01 for HRD1 KO-CrebH shRNA vs HRD1 KO-ctl shRNA. (C–D) Levels of serum TG and free FA in WT or HRD1 LKO mice infected with Ad expressing CrebH shRNA or control shRNA at the representative nighttime or daytime period. Data are mean ± SEM (n = 3 mice/genotype/time point). ∗∗P < 0.01 for HRD1 KO-CrebH shRNA vs HRD1 KO-ctl shRNA."
      }
    ]
  },
  {
    "id": "PMC7990330_multi",
    "image": [
      "images/PMC7990330-f1.png",
      "images/PMC7990330-f2.png",
      "images/PMC7990330-f3.png",
      "images/PMC7990330-f4.png",
      "images/PMC7990330-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"De novo ATP1A3 variants cause polymicrogyria\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Brain MRI scans of patient 1 [(A) and (B) at 1 day old, (C) and (D) at 2 years and 10 months], patient 3 [(E) and (F) at 2 months old, (G) and (H) at 8 months], patient 4 [(I) and (J) at 3 days old, (K) and (L) at 4 months], patient 5 [(M) and (N) at 2 days old], patient 6 [(O) and (P) at 2 months old], patient 7 [(Q) and (R) at 5 months old, (S) and (T) at 3 years old], patient 8 [(U) and (V) at 2 months old], and a neurologically normal control [(W) and (X) at 3 years old]. All images are T2-weighted axial brain MRI, except for a T2-weighted sagittal MRI (M), a fluid-attenuated inversion recovery axial MRI (N), and an axial cranial CT (S and T). Brain MRI showed irregular small gyri with apparent cortical thickening, compatible with polymicrogyria, over the perisylvian cortex (arrowheads). Patients 1, 3, and 4 (A to L) showed progressive atrophic changes with dilation of the subarachnoid space and lateral ventricles.\n\nFigure 2: Figure 2. (A) The crystal structure of Na+/K+ ATPase, composed of α- (pink), β- (cyan), and γ-subunits (green), from Squalus acanthias (PDB code: 2ZXE) is shown with the residues (magenta spheres) corresponding to the identified variants in humans. The squares (b to e) correspond to the magnified areas (B to E), respectively. In the right structure, spheres indicate the residues corresponding to the previously reported variants associated with AHC (orange), RDP (cyan), both AHC and RDP (green), and other phenotypes (yellow). (B) The p.Arg182 (cyan) of the β-subunit interacting with p.Gln895 (magenta) in a loop of p.Asp882–Trp896 (red wire) of the α-subunit via hydrogen bonds (black dotted lines). The residue numbering is based on human Na+/K+ ATPase. (C) The interactions between α- and β-subunits around the p.Gly854 to Phe857 region of the α-subunit. The side chains of p.Phe856 and p.Phe857 and their interacting residues (β-subunit) are shown by sticks with translucent van der Waals spheres. The conformation of p.Met57 (β-subunit) in humans was modeled instead of leucine in the S. acanthias structure. The sulfur and oxygen atoms are shown in yellow and red, respectively. The residues interacting with K+ ions (green) are depicted as sticks. (D) The interactions between α and β subunits around the p.Tyr991-Arg995 region of the α-subunit. The p.Tyr991 and its interacting residues, p.Phe38 and p.Phe42 (β-subunit), are shown as sticks with translucent spheres. The conformation of p.Ile994 in humans was modeled instead of methionine in the S. acanthias structure. (E) A hydrophobic core involving p.Cys596 near the p.Asp366 phosphorylation site. The magnesium and fluorine atoms of a phosphate analog, MgF42−, are shown in orange and gray, respectively. (F) Free-energy changes upon the substitution of p.Cys596Tyr and p.Gln895Pro, as predicted by FoldX (31, 32).\n\nFigure 3: Figure 3. (A) The black bars represent transmembrane domains (TM1 to TM10), while the lines represent the intracellular and extracellular domains of the Na+/K+ ATPase α3-subunit. A hatchet-shaped light brown structure depicts the β-subunit. The symbols and colors used for explaining variants are described in the legend. Numbers indicate the residue number at each site. A, N, and P stand for the actuator, nucleotide binding, and phosphorylation regions, respectively. Large circles represent the commonly observed variants. (B) Graph of nontruncating variant distribution of AHC, RDP, CAPOS, others, and polymicrogyria. X axis: amino acid number; y axis: each phenotype. Dashed and dotted lines indicate the median and quartile, respectively. **P < 0.01 and ***P < 0.001 using the Kolmogorov-Smirnov test. PMG, polymicrogyria; others: phenotypes other than AHC, CAPOS, RDP, and polymicrogyria, including developmental and epileptic encephalopathy, such as EIEE with or without apnea, relapsing encephalopathy with cerebellar ataxia, or fever-induced paroxysmal weakness and encephalopathy.\n\nFigure 4: Figure 4. Black, blue, and purple/red bars indicate the wild-type (WT), AHC/RDP-associated, and polymicrogyria-associated variants, respectively. The upper right box shows color-coded information. Error bars, means ± SD. *P < 0.05, **P < 0.01, and ***P < 0.001. (A) ATPase activity in COS-7 cells. N = 3. (B) Expression of myc-tagged ATP1A3 and HaloTag-fused ATP1B1 in human embryonic kidney (HEK) 293T cells. Left: A representative blot. Right: The relative ATP1A3 and mature β1-subunit expression, normalized to the wild type. N = 3. WB, Western blot. (C) Coimmunoprecipitation of myc-tagged ATP1A3 and HaloTag-fused ATP1B1 in HEK293T cells. Left: A representative blot. Middle: The relative ATP1B1 recovery rate. N = 3. Right: The proportion of N-glycosylated ATP1B1 bound to ATP1A3. (D) The total HEK293T cell components cotransfected with ATP1A3 (wild type, p.Ile758Ser, or p.Gln895Pro) and ATP1B1 cDNA vectors were separated into three fractions: cytosol, organelles, and plasma membrane. Left: A representative blot. A dashed rectangle denotes Western blotting on a different cartridge. The second panel from the left: The relative ATP1A3 expression in respective fraction. N = 3. The second panel from the right: The proportion of ATP1A3 in each fraction for respective condition. N = 6. Right: The relative expression of differently N-glycosylated ATP1B1 in the plasma membrane fraction. N = 6.\n\nFigure 5: Figure 5. Through (A) to (C), the left and right panels show immunofluorescence under the cotransfection of wild-type ATP1A3 and wild-type ATP1B1 plasmids and p.Gln895Pro ATP1A3 and wild-type ATP1B1 plasmids, respectively. Scale bars, 5 μm. (A) ATP1A3 and ATP1B1 colocalizing at the cis-Golgi network in both panels (arrowhead). (B) ATP1A3 and ATP1B1 colocalizing at the trans-Golgi network in both panels (arrowhead). (C) ATP1A3 and ATP1B1 colocalizing at the plasma membrane in both panels (arrowhead). For (A) and (B), lower images are the pseudocolored maps of the product of the differences from the mean analysis (PDM maps) for the respective upper images. For (C), lower right panels are the PDM maps for the upper two images. In the PDM maps, positive correlation is indicated in yellow, negative correlation in blue, and random distribution in black."
      }
    ]
  },
  {
    "id": "PMC7990330_multi_2",
    "image": [
      "images/PMC7990330-f6.png",
      "images/PMC7990330-f7.png",
      "images/PMC7990330-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"De novo ATP1A3 variants cause polymicrogyria\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A) The production of in situ PLA fluorescent spots (Duolink) indicates the subcellular sites where myc-tagged ATP1B1 and HaloTag-fused ATP1B1 colocalize within 40 nm. Immunofluorescence study showing that Duolink signals were substantially decreased at HaloTag-fused ATP1B1 expressed in the plasma membrane in HEK293T cells cotransfected with p.Gln895Pro ATP1A3 and ATP1B1 plasmids, compared with those with p.Ile758Ser ATP1A3/ATP1B1 and wild-type ATP1A3/ATP1B1 plasmids. Scale bars, 20 μm. DAPI, 4′,6-diamidino-2-phenylindole. (B) Mean intensity in the specified region was significantly decreased in HEK293T cells cotransfected with p.Gln895Pro ATP1A3 and ATP1B1 plasmids, while those with p.Ile758Ser ATP1A3/ATP1B1 did not appear to differ in mean signal intensity compared with wild-type ATP1A3/ATP1B1. We confirmed this tendency with replicate experiments (N = 4). a.u., arbitrary units.\n\nFigure 7: Figure 7. (A) Schematic of the study design using mice. (B and C) Plasmids expressing the wild-type, p.Asp992del, p.Gln895Pro, and p.Ile758Ser variants of ATP1A3 were introduced, together with GFP-expressing plasmids, into the ventricles of mice on E14.5. After in utero electroporation, the embryonic brains were collected and fixed at E18.5, and migration was quantified using cell distributions. The total cortical thickness was divided into five equal parts, named BIN1 to BIN5. The number of cells that were distributed in each BIN was counted and expressed as a percentage. Scale bars, 50 μm. *P < 0.05 (Student’s t test). (B) denotes cell distribution across the cortex as a summary, while (C) shows a representative image of the mouse cortex expressing either GFP, mutant ATP1A3, or wild-type ATP1A3. (D) Left: Representative images of monitored cultured neurons introduced with wild-type or p.Asp992del ATP1A3 plasmids together with GCaMP plasmids. Regions of interest (ROIs) were marked with four different colors to monitor the intensities of GCaMP signals. Right: Graphs of intensity plot in one recording (8 min). The same colors of ROIs are used for GCaMP signal recording. (E) Peak numbers (upper) and heights (lower) of calcium spikes of the recordings. For peak height, fold increases of GCaMP signal intensity compared to the average intensity were shown. *P < 0.05 and ***P < 0.001.\n\nFigure 8: Figure 8. A schematic showing an overview of ATP1A3-related disorders as ion channel diseases throughout the human life span, together with other known genes, based on the latest knowledge (29). The x axis approximately (not linearly) shows the life span of a human, from newborn to adulthood. The y axis represents disease severity. MCD, malformation of cortical development; DEE, developmental and epileptic encephalopathy."
      }
    ]
  },
  {
    "id": "PMC7996761_multi",
    "image": [
      "images/PMC7996761-f1.png",
      "images/PMC7996761-f2.png",
      "images/PMC7996761-f3.png",
      "images/PMC7996761-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Two Italian Patients with ELOVL4-Related Neuro-Ichthyosis: Expanding the Genotypic and Phenotypic Spectrum and Ultrastructural Characterization\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clinical features: mild facial dysmorphism and erythema (A), proximal and distal limb hypertonia and neck erythema (B), slight thigh hyperkeratosis with fine whitish desquamation (C) in patient 1 at 7 months of age. Similar skin findings (D–F) and plantar keratoderma with erythema (F) are visible in patient 2 at 19 months of age. In the latter case, note also pectum carenatum and the dystonic posturing of the trunk, proximal limb hypotonia with frog-leg positioning and distal limb hypertonia with clenched fists (D).\n\nFigure 2: Figure 2. Brain magnetic resonance imaging in patient 1 at age 10 months. Corpus callosum is thin and mildly dysplastic at the level of isthmus (arrow in (A), sagittal view, T1-weighted image). The deep and periventricular white matter appears hyperintense compared to the grey matter (arrows in (B), axial view, FLAIR image), a similar abnormal high signal also involves the optic radiations (arrow in (C), axial view, FLAIR image). Finally, mild hyperintensity of the cerebellar dentate nuclei is visible (arrows in (D), axial view, T2 weighted image). T1-IR images confirm the involvement of dentate nuclei (arrows in (E), axial view) and optic radiations (arrow in (F), axial view).\n\nFigure 3: Figure 3. Ultrastructural features. Abnormal lamellar bodies with disorganized and disrupted lamellar content (asterisks) and some empty vacuoles (arrows) within the upper spinous and granular layer in patient 1 (A). Dilated horny layer intercellular spaces filled with disorganized lamellar structures (arrow) in patient 1 (B). Dilated intercellular spaces within the granular layer containing amorphous material in patient 2 (asterisks) and empty vacuoles (arrow) (C). Large membrane-bound cytoplasmic vacuoles (asterisks) with a finely granular content within the lower epidermis in patient 2 (D). Ba r= 1 µm in (A–C), 2 µm in (D).\n\nFigure 4: Figure 4. Molecular genetic testing. Next generation sequencing (NGS) singleton analysis shows the ELOVL4 (NM_022726.3) variant c.435dup, p.(Ile146Tyrsfs*29) at the homozygous state in patient 1 (A), and Sanger analysis confirms the presence of the same mutation in the homozygous proband and his heterozygous parents (B); trio-based NGS analysis identifies the ELOVL4 paternal variant c.208C>T, p.(Arg70*) (left image) and the maternal variant c.487T>C, p.(Cys163Arg) (right image) in patient 2 (C)."
      }
    ]
  },
  {
    "id": "PMC8026396_multi",
    "image": [
      "images/PMC8026396-f1.png",
      "images/PMC8026396-f2.png",
      "images/PMC8026396-f3.png",
      "images/PMC8026396-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"An autosomal dominant neurological disorder caused by de novo variants in FAR1 resulting in uncontrolled synthesis of ether lipids\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Molecular structures of glycerolipids and glycerophospholipids. These types of lipids contain a glycerol backbone (red) attached to one or two fatty acid/fatty alcohol (blue) substituents at the sn-1 and sn-2 position and a headgroup R (green) attached at the sn-3 position. When R is a hydrogen or a fatty acid the molecule is a glycerolipid; when R is a phosphate linked to a species characteristic headgroup (choline, ethanolamine, etc.) the molecule is a glycerophospholipid, also known as a phospholipid. In ether phospholipids, the fatty linkage at the sn-1 position is either an ether (plasmanyl) or a vinyl ether (plasmenyl); the latter substitution defines the subclass that is known as plasmalogens. In analogy to ether phospholipids, ether variants of glycerolipids also exist with an ether fatty linkage on the sn-1 position. b Ether lipid biosynthesis. Dihydroxyacetone phosphate (DHAP)-acyltransferase (DHAPAT), esterifies DHAP at the sn-1 position with a long-chain fatty acyl-CoA yielding 1-acyl-DHAP. Next, alkylglycerone phosphate synthase (AGPS) replaces the acyl unit by a fatty alcohol, produced by reduction of an acyl-CoA by fatty acyl-CoA reductase 1 (FAR1), resulting in the formation of 1-alkyl-DHAP. 1-Alkyl-DHAP is then reduced to 1-alkylglycerolphosphate by acyl/alkyl-DHAP reductase (PexRAP), which is converted to 1-alkyl-2-acylglycerol (DG[O]) at the endoplasmic reticulum (ER). Exogenous 1-alkylglycerol (for example 1-hexadecylglycerol [HDG]) can be phosphorylated to 1-alkylglycerolphosphate, which then bypasses the peroxisomal steps in ether lipid biosynthesis. DG[O] can be converted to plasmanyl-PE and plasmanyl-PC by condensation with CDP-ethanolamine and CDP-choline, respectively. Creation of a vinyl ether by desaturation in the ER yields plasmenyl-PE, which can be converted to plasmenyl-PC, both of which are called plasmalogens. PC and PE ether phospholipids, thus including plasmanyl and plasmenyl-species, are collectively called PC[O] and PE[O], respectively. DG[O] can also be acylated which yields 1-alkyl-2,3-diacylglycerol (TG[O]).\n\nFigure 2: Figure 2. a Plasmalogen levels in cultured skin fibroblasts from a reference population (Ref), controls (C) (Ref and C, both black diamonds) and FAR1 p.Arg480His/Cys patients (gray, P1 = square, P2 = circle, P3 = triangle). The control samples were analyzed in the same experiments as the patient samples. C16:0- and C18:0-plasmalogens are expressed as % of total palmitate (C16:0) and stearate (C18:0), respectively, and were significantly elevated when compared with the control samples (t-test, two sided, p < 0.0001, indicated by **). b FAR1 enzyme activity in cultured skin fibroblasts of controls (C1–C3, black) and patients (P1–P3, gray). Measurements were performed in duplicate (except for C2). c Immunoblot analysis of FAR1 in fibroblast homogenates of controls and patients. The upper panel shows the (cropped) immunoblot using antibodies against FAR1 (59 kDa) and the lower panel the same blot reprobed with antibodies against β-actin as loading control. d Immunofluorescence microscopy analysis in fibroblasts of P2 of peroxisomal membrane protein ABCD3 (green, upper left) and FAR1 (red, upper right) and overlay (lower left) and magnification (lower right). FAR1 p.Arg480His/Cys variants are normally localized to peroxisomes.\n\nFigure 3: Figure 3. Fibroblasts of control subjects (n = 6) and p.Arg480His/Cys FAR1 patients (P1–P3) were treated for 24 and 48 hours with 10 μM HDG followed by immunoblot analysis for FAR1 and measurement of the plasmalogen levels. Two independent experiments were performed (a indicating the first experiment, b the second), each including three (×2) control cell lines and the three patient cell lines (P1 = square, P2 = circle, P3 = triangle). a Immunoblot analysis of FAR1 in fibroblast homogenates of controls and patients using antibodies against FAR1 (59 kDa) and β-actin as loading control (same blot reprobed). Blots (cropped) of both experiments are shown. b Quantification of the FAR1 protein level as ratio over β-actin in control and patient cells in untreated and HDG-treated cells. Results are shown for each cell line as % of the untreated condition. c C16:0-Plasmalogen levels (expressed as % of total palmitate [C16:0]) in untreated and HDG-treated control and patient cells.\n\nFigure 4: Figure 4. Summation of lipidomic species per major class for controls (n = 3, black diamonds), patients 1, 2, and 3, (P1 = square, P2 = circle, P3 = triangle); mean is shown and x-fold difference of the patient mean compared with that of controls if p ≤ 0.005. a Diradylphospholipid species, b monoradylphospholipid species, and c neutral lipid species (“radyl” means either a fatty acid or fatty alcohol substituent). DG diacylglycerol, DG[O] 1-alkyl-2-acylglycerol, (L)PC (lyso)phosphatidylcholine, (L)PC[O] (lyso)plasm(a/e)nylcholine, (L)PE (lyso)phosphatidylethanolamine, (L)PE[O] (lyso)plasm(a/e)nylethanolamine, TG triacylglycerol, TG[O] 1-alkyl-2,3-diacylglycerols. d LPC[O] levels 16:0–18:0 are elevated in patients with the FAR1 variants (10log-scale). e 2Log(fold-change) of the average levels of patients and controls for PC[O] and PC species with 40–44 carbon atoms in the fatty acid side chains. PC[O] species with more double bonds (containing polyunsaturated fatty acids) accumulated more in patients whereas the corresponding PC species were reduced. f Overview of the experiment to assess ether lipid and nonether lipid synthesis from exogenous C17:0-acid in control fibroblasts and patient fibroblasts with the p.Arg480His/Cys FAR1 variants. C17:0-acid can be directly incorporated in nonether lipids or converted by FAR1 to a C17:0-alcohol which in turn can be incorporated in ether lipids. g Comparison of incorporation of C17:0-acid and C17:0-alcohol in LPC(17:0) and LPC(O-17:0), respectively. C17:0-acid is incorporated in comparable amounts in LPC(17:0) in both controls and patients whereas C17:0-alcohol incorporation in LPC(O-17:0) is fourfold elevated in patients when compared with control."
      }
    ]
  },
  {
    "id": "PMC8067556_multi",
    "image": [
      "images/PMC8067556-f1.png",
      "images/PMC8067556-f2.png",
      "images/PMC8067556-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Neurological Disorders Associated with WWOX Germline Mutations—A Comprehensive Overview\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. WW domain-containing oxidoreductase (WWOX) interaction partners and signaling pathways in the nervous system. WWOX protein–protein interactions and signaling in the nervous system involves: I. The Wnt/β-catenin signaling pathway, where WWOX negatively regulates this pathway through interaction with Dishevelled (Dvl) proteins and/or glycogen synthase kinase-3 β (GSK-3β). WWOX deficiency has been shown to be associated with increased nuclear β-catenin activity. II. WWOX has been also shown to modulate the transforming growth factor-β (TGF-β) signaling pathway through regulation of the SMAD proteins and the trafficking protein particle complex 6AΔ (TPC6AΔ). In the absence of WWOX, the SMAD/co-SMAD complex is inhibited, and TPC6AΔ and anti-apoptotic factor 1 (TIAF1) aggregate in the mitochondria, contributing to CNS pathologies. III. WWOX could also modulate the receptor tyrosine kinase (RTK) and c-Jun N-terminal kinase (JNK) signaling pathways to regulate tau phosphorylation and the formation of neurofibrillary tangles (NFT). Other abbreviations used: APC, adenomatosis polyposis; CKIα, casein kinase Iα; TCF/LEF, T-cell factor/lymphoid enhancing factor; ROS, reactive oxygen species; ASK1, apoptosis signal-regulating kinase 1; MKK4/7, mitogen-activated kinase kinase 4/7; RAF, rapidly accelerated fibrosarcoma; MEK: mitogen-activated protein Kinase; ERK, extracellular signal-regulated kinase. Figure was created via BioRender.\n\nFigure 2: Figure 2. Summary of the neurological disorders associated with WWOX germline mutations. Upper panel (A) shows phenotypes associated with WWOX deficiency in rodents. Lower panel (B) summarizes neuropathological diseases associated with WWOX gene mutations in humans. NFTs, neurofibrillary tangles; TPC6AΔ, trafficking protein particle complex 6A; TIAF1, TGF-β1 induced antiapoptotic factor; APP, amyloid precursor protein. Figure was generated with BioRender.com.\n\nFigure 3: Figure 3. WWOX variants identified in patients with SCAR12 and WOREE syndrome. (A) Deletions leading to copy number variations in the WWOX gene. (B) Single-nucleotide variations (SNVs) leading to point mutations and protein changes. Mutation diagram circles are colored to indicate type of mutations: green for missense, orange for splice site, and black for truncating mutations including nonsense, frameshift deletion, and frameshift insertion. SCAR12 is mostly associated with missense mutations (red), while WOREE is associated with the deletions, missense, and nonsense mutations (black). Number of patients with increased frequency of a given mutation is indicated (height of the vertical lines)."
      }
    ]
  },
  {
    "id": "PMC8071455_multi",
    "image": [
      "images/PMC8071455-f1.png",
      "images/PMC8071455-f2.png",
      "images/PMC8071455-f3.png",
      "images/PMC8071455-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Disorders and Their Mouse Models Point to Essential Roles of Peroxisomes for Retinal Integrity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Spatial distribution of PEX14 protein and Mfp2 mRNA in the mouse retina. IHC for PEX14 (green) and RNAscope® in situ hybridization for Mfp2 (red) reveals the presence of peroxisomes in the RPE, photoreceptors, interneurons and ganglion cells. Nuclei were counterstained with Hoechst (blue). PEX14, peroxin 14; Mfp2, multifunctional protein 2; RPE, retinal pigment epithelium; PR, photoreceptor layer; ONL, outer nuclear layer; OPL, outer plexiform layer; INL, inner nuclear layer; IPL, inner plexiform layer; GCL, ganglion cell layer.\n\nFigure 2: Figure 2. Overview of peroxisomal α- and β-oxidation of substrates relevant for retinal homeostasis. Phytanic acid is catabolized via peroxisomal α-oxidation, resulting in the formation of the 2-methyl branched chain fatty acid pristanic acid that subsequently undergoes peroxisomal β-oxidation similar to other substrates, including VLCFAs and PUFAs. After activation to a CoA ester, substrates are translocated in peroxisomes via three ABCD transporters, which exert a differential, although not absolute, substrate specificity. Peroxisomal β-oxidation occurs in four steps whereby the second and third step are catalyzed by a multifunctional protein. Of note, pristanic acid first needs to be converted into the S-configuration by AMACR. Furthermore, ACBD5 is assumed to present VLCFAs to the ABCD transporters, besides its role in the tethering of peroxisomes to the endoplasmic reticulum. ABCD, ATP binding cassette subfamily D; ACAA1, acetyl-CoA acyltransferase 1; ACBD5, Acyl-CoA binding domain containing protein 5; ACOX, acyl-CoA oxidase; D/THCA, di- and trihydroxycholestanoic acid; MFP, multifunctional protein; PUFAs, polyunsaturated fatty acids; SCPx, sterol carrier protein x; VLCFAs, very long chain fatty acids.\n\nFigure 3: Figure 3. De novo biosynthesis of DHA. ALA is elongated and desaturated to THA in the ER and subsequently retroconverted to DHA via one cycle of peroxisomal β-oxidation (also known as the “Sprecher shunt”). However, whereas it was previously thought that DPA cannot be directly converted to DHA, FADS2 activity on DPA was recently shown [99], but the contribution to DHA synthesis in different cell types has not been resolved. ALA, α-linolenic acid; DHA, docosahexaenoic acid; DPA, docosapentaenoic acid; FADS, fatty acid desaturase; THA, tetrahexaenoic acid.\n\nFigure 4: Figure 4. PUFA profile of Mfp2−/− neural retinas. Lipidome analysis on Mfp2−/− neural retinas revealed a severe decrease in DHA- and an increase in AA-containing PC phospholipids. The PC phospholipids containing VLC-PUFAs show a peculiar profile, as phospholipids containing ≤56 carbons in their side chains are severely reduced, while those containing >56 carbons accumulate. These PC species contain a VLC-PUFA and DHA moiety in the sn-1 and sn-2 position, respectively. Data are presented as log transformation of relative values to WT values."
      }
    ]
  },
  {
    "id": "PMC8076533_multi",
    "image": [
      "images/PMC8076533-f1.png",
      "images/PMC8076533-f2.png",
      "images/PMC8076533-f3.png",
      "images/PMC8076533-f4.png",
      "images/PMC8076533-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Downregulation of Cullin 3 Ligase Signaling Pathways Contributes to Hypertension in Preeclampsia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Downregulation of CRL3 function with accumulation of WNK kinases and PDE5 was detected in the placentas of PE patients. (A, B) Western blotting was performed in the placentas of PE patients and healthy pregnancies, including (1) CUL3 and the ratio of neddylated CUL3 to deneddylated CUL3, (2) the member of the COP9 signalosome JAB1, (3) the adaptors of CRL3 including KLHL2 and RhoBTB1 and their specific substrates including WNK3 and PDE5, and (4) cardioprotective molecule PPARγ and hypoxia-inducible factor 1α (HIF1α). Expressions of these proteins in the placentas were all statistically significant (t-test) after normalization to GAPDH between PE and control group. PE indicates preeclampsia (n = 5), and Con indicates control (n = 5). Data are presented as the mean ± SEM. *p < 0.05 and **p < 0.01. (C) Systolic blood pressure were detected among control, l-NAME, and l-NAME + PPI group at E8.5 and E18.5. Data are presented as the mean ± SEM. ANOVA with Tukey post hoc analysis, *p < 0.05.\n\nFigure 2: Figure 2. Downregulation of CRL3 function caused accumulation of PDE5 and WNK kinases and increased RhoA/ROCK activity in the aortic tissues of pregnant l-NAME–treated mice. Protein levels were detected by Western blotting, including (1) hypoxia-inducible factor 1α (HIF1α), member of the COP9 signalosome JAB1, CUL3 abundance and neddylation, and cardioprotective molecule PPARγ; (2) adaptor protein RhoBTB1 and its substrate PDE5 and the index of RhoA/ROCK activity phosphorylated MYPT1; (3) adaptor protein KLHL2 and its substrates including WNK1 and WNK3 and downstream phosphorylated SPAK/OSR1; and (4) autophagy markers mTOR and LC3-II/LC3-I. Expressions of these proteins in the aortic tissues were all statistically significant after normalization to GAPDH among control, l-NAME, and l-NAME + PPI group (ANOVA with Tukey post hoc analysis). Data are presented as the mean ± SEM. **p < 0.01 compared between control and l-NAME group. #p < 0.05 and ##p < 0.01 compared between l-NAME and l-NAME + PPI group. †p < 0.05 and ††p < 0.01 compared between control and l-NAME + PPI group.\n\nFigure 3: Figure 3. Downregulation of CRL3 function was involved in the accumulation of WNK kinases in the kidney of pregnant l-NAME–treated mice. Protein levels were detected by Western blotting, including (1) hypoxia-inducible factor 1α (HIF1α), member of the COP9 signalosome JAB1, CUL3 abundance and neddylation, NEDD8 conjugates and adaptor KLHL3; (2) substrates of CRL3 including WNK4 and WNK1 and phosphorylated NCC (pNCC) and total NCC (tNCC); and (3) autophagy marker mTOR. Expressions of these proteins in the kidney were statistically all significant after normalization to GAPDH among control, l-NAME, and l-NAME + PPI group (ANOVA with Tukey post hoc analysis). Data are presented as the mean ± SEM. *p < 0.05 and **p < 0.01 compared between control and l-NAME group. #p < 0.05 and ##p < 0.01 compared between l-NAME and l-NAME + PPI group. †p < 0.05 and ††p < 0.01 compared between control and l-NAME + PPI group.\n\nFigure 4: Figure 4. Distal renal tubule remodeling of pregnant l-NAME–treated mice. Representative immunofluorescence images including total NCC (tNCC), phosphorylated NCC (pNCC), and phosphorylated SPAK/OSR1 (pSPAK/OSR1) staining images of the distal renal tubules. Scale bars: 100 μm. Histological analysis of the length and area expressing tNCC in the distal renal tubule among control (n = 6), l-NAME (n = 6), and l-NAME + PPI group (n = 6) (ANOVA with Tukey post hoc analysis). Data are presented as the mean ± SEM (*p < 0.05 and **p < 0.01).\n\nFigure 5: Figure 5. JAB1 promoted HIF1α expression and decreased neddylation of CUL3, and KLHL3 degradation was mediated by autophagy in HEK293 cells under hypoxia. (A) Protein levels of CUL3 abundance and neddylation, NEDD8 conjugates, adaptor KLHL3 and downstream phosphorylated SPAK/OSR1, and member of the COP9 signalosome JAB1 were detected in HEK293 cells after transfection with KLHL3. Expressions of these proteins in HEK293 cells were all statistically significant (t-test) after normalization to GAPDH between hypoxia (n = 3) and control (n = 3) group. (B) Representative images of protein levels of hypoxia-inducible factor HIF1α, JAB1, CUL3 abundance and neddylation in HEK293 cells after transfected with JAB1 and its siRNA, respectively (n = 3). (C, D) Representative immunofluorescence images of subcellular localization of KLHL3 and autophagy marker LC3. The yellow fluorescence indicated the overlap of KLHL3 and LC3 expression. Scale bars: 100 μm. Statistical analyses of KLHL3 and autophagy marker LC3 colocalization using Pearson correlation coefficient in HEK293 cells (n = 10–15). (E) Representative immunoblots of WNK4, KLHL3, and CUL3 abundance and neddylation in HEK293 cells after administration with inhibitor of autophagy bafilomycin A1 (Baf1) under hypoxia. Data are presented as the mean ± SEM (*p < 0.05 and **p < 0.01)."
      }
    ]
  },
  {
    "id": "PMC8076533_multi_2",
    "image": [
      "images/PMC8076533-f6.png",
      "images/PMC8076533-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Downregulation of Cullin 3 Ligase Signaling Pathways Contributes to Hypertension in Preeclampsia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Hypoxia downregulated the function of CRL3 and increased autophagy-mediated degradation of KLHL2 in MOVAS cells. (A) Protein levels of NEDD8 conjugates, the components of CRL3, including CUL3 abundance and neddylation, adaptors KLHL2 and RhoBTB1 with substrate PDE5, member of the COP9 signalosome JAB1, and autophagy marker LC3-II/LC3-I were detected in MOVAS cells of hypoxia and control groups. Expressions of these proteins in the MOVAS cells were all statistically significant (t-test) after normalization to GAPDH among hypoxia (n = 3) and control (n = 3) group. (B) Representative immunoblots of the adaptor KLHL2, hypoxia-inducible factor HIF1α, and downstream phosphorylated SPAK/OSR1 in MOVAS cells after administration with inhibitor of autophagy bafilomycin A1 (Baf1) under hypoxia (n = 3). (C) Representative immunofluorescence images of subcellular localization of phosphorylated SPAK/OSR1 in MOVAS cells between the hypoxia and control groups. Scale bars: 100 μm. Data are presented as the mean ± SEM (*p < 0.05 and **p < 0.01).\n\nFigure 7: Figure 7. Schematic view of molecular mechanisms of accumulation of WNK kinases and PDE5 under preeclampsia. Increased JAB1 abundance stabilizes HIF1α and upregulates its expression under ischemia/hypoxia. Increased HIF1α decreases PPARγ expression and then downregulates CUL3 abundance. Upregulated CSN also causes lower CUL3 neddylation. Decreased abundance and neddylation of CUL3 lead to CUL3 dysfunction. Increased autophagy promotes degradation of adaptors KLHL3/2, and decreased abundance of PPARγ downregulates adaptor RhoBTB1 expression. Subsequent accumulation of substrates including WNK kinases and PDE5 results in the abnormal vasoconstriction and vasodilation and NCC activation. JAB1, a component of the COP9 signalosome; HIF1α, hypoxia-inducible factor 1α; PPARγ, peroxisome proliferator–activated receptor γ."
      }
    ]
  },
  {
    "id": "PMC8119579_multi",
    "image": [
      "images/PMC8119579-f1.png",
      "images/PMC8119579-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Pain Study in X-Linked Adrenoleukodystrophy in Males and Females\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Graphical representation of the 10 body points per side and anatomical landmarks description\n\nFigure 2: Figure 2. QST: mechanical detection threshold (MDT). Mean MDT values at one representative point (foot, external left, f-ext L) in all clusters"
      }
    ]
  },
  {
    "id": "PMC8127006_multi",
    "image": [
      "images/PMC8127006-f1.png",
      "images/PMC8127006-f2.png",
      "images/PMC8127006-f2-2.png",
      "images/PMC8127006-f3.png",
      "images/PMC8127006-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"TRIM37 prevents formation of condensate-organized ectopic spindle poles to ensure mitotic fidelity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Consequences of TRIM37 loss in interphase RPE1 cells and mulibrey nanism patient-derived fibroblasts. (A) Schematic of TRIM37, which has a RING–B-box–coiled-coil (RBCC) ubiquitin ligase domain. Mutation of catalytic Cys18 to Arg (Ligmut TRIM37) disrupts ligase activity. (B) Expansion microscopy of centrioles colabeled for acetylated tubulin and the distal centriole component CEP290. Normal centrioles at different cell cycle stages and rare aberrant centriolar configurations are shown in TRIM37Δ RPE1 cells. Scale bar, 2 µm. (C) Quantification of mother centriole length from expansion microscopy of the indicated conditions. Error bars represent standard deviation. n, number of centrioles; ns, not significant, based on a t test. (D) Quantification of centriole number for the indicated cell lines following expansion microscopy as in B. Normal G1, S, G2, and M centriolar configurations were counted as “2 (single or duplicated)”. For B–D, cells were expanded twice with similar results; images and quantification of centriole length are from one experiment, and the centriole number data is pooled from both experiments. (E) Analysis of ciliogenesis, assessed by ARL13B labeling, in control RPE1 and TRIM37Δ RPE1 cells. Scale bar, 10 µm. The experiment was performed twice, once in triplicate and once in duplicate, with similar results; ciliation frequency from one experiment is shown here and from the second experiment in Fig. S1 A. (F) Immunostaining of TRIM37Δ and control USP28Δ RPE1 cells for centrobin and PLK4. Scale bars, 5 µm and 1 µm (insets). (G) Quantification of immunofluorescence signals at centrosomes in control USP28Δ cells and at centrosomes and condensates in TRIM37Δ cells. The signal for both centrosomes in a cell was measured together. Values were normalized relative to the mean centrosomal signal in USP28Δ cells; inset in the centrobin graph shows centrosome signals plotted on a different y-axis scale. Mean and 95% confidence interval (CI) are plotted on top of individual values; P value is from an unpaired t test. The condensate signal values plotted here are the same as those shown in Fig. S4 B (−Dox). Experiments in F and G were repeated twice; images and quantification are from one experiment. (H) Immunostaining of control and mulibrey nanism patient-derived fibroblasts. Scale bars, 5 µm and 1 µm (insets). The experiment was performed once; data for each cell line were pooled from three replicate wells imaged in parallel. (I) Localization of mNG-fused TRIM7 (WT or Ligmut) expressed in TRIM37Δ cells. TRIM37 activity reduces its own levels; hence, the signal for WT TRIM37-mNG was enhanced to show centrosomal localization. Scale bars, 5 and 1 µm (insets). The experiment was performed once; an equivalent experiment with similar results was performed using an HA tag shown in (Meitinger et al., 2020). (J) Top: Schematic of condensate observed in TRIM37Δ RPE1 cells and mulibrey nanism patient fibroblasts. Bottom: Summary of the localization of centrosomal components in TRIM37Δ cells; components shown in brackets localize to centriolar satellites. Analysis of CPAP, CEP63, CEP135, PCM1, KIAA0753, and CCDC14 is from Meitinger et al. (2020) and was conducted with PLK4 colabeling. In F, H, and I, centrosomes (white arrowheads) and the condensate (yellow arrows) are indicated, and numbers below images indicate percentage of cells with a condensate.\n\nFigure 2: Figure 2. Analysis of TRIM37 localization and additional characterization of phenotypes of TRIM37Δ RPE1 cells. (A) Independent experiment analyzing ciliation frequency (left) and quantification of primary cilium length (right). n, number of cells analyzed; median and 95% CI are shown on top of individual data points in the right graph. The experiment was performed twice, the first experiment in triplicate and the second experiment in duplicate, with similar results; ciliation frequency and cilium length quantified from the second experiment are shown here, and ciliation frequency from the first experiment is shown in Fig. 1 E. (B) Immunofluorescence of centrobin and the indicated centrosomal components in USP28Δ and TRIM37Δ RPE1 cells. Scale bars, 5 µm (1 µm in insets). The experiment was performed once. (C) Expanded view of CLEM analysis of the cell shown in Fig. 2 B. Additional serial sections of the condensate and centrosome, a low-magnification EM view, and a higher-magnification view of the condensate are shown along with replication of the images shown in Fig. 2 B. White scale bar, 20 µm. Black scale bars: low magnification view, 2 µm; condensate and centrosome serial sections, 0.5 µm; zoomed-in view of punctate sheet condensate, 0.1 µm. (D) 3D STORM of condensates labeled with centrobin or PLK4. Reference widefield images are on the left. The STORM images are color coded for depth. Scale bars, 10 µm (widefield), 0.5 µm (STORM). Experiment performed twice with similar results; images are from one experiment. Red arrows indicate that the images on the bottom are higher magnification views of the corresponding regions of the images on top. (E) TRIM37-mNG localization at centrosomes visualized using SIM. CEP152 marks the proximal end of centrioles. CEP164 marks the distal end of the mother centriole. TRIM37 is broadly localized to the centrosome; it does not concentrate in a specific subdomain. Scale bars, 1 µm. The experiment was performed twice with similar results; images are from one experiment. mag, magnification. (F) Rare example of condensate fusion observed by live imaging of Ligmut TRIM37-mNG expressed in TRIM37Δ cells. The fused condensate retains an elongated shape. Scale bar, 5 µm.\n\nFigure 2: Figure 2. CLEM of TRIM37Δ cells expressing mNG-fused Ligmut TRIM37. (A) Top left: Overlay of DIC and mNG fluorescence channels for three cells analyzed by serial section EM. Colored boxes in low-magnification (1,900×) views indicate the mNG-labeled condensate and the centrosome. Higher-magnification views (11,000×) of serial sections through the condensates reveal a highly ordered striated structure; a zoomed-in view shows regularly spaced stripes ∼90 nm apart; n, number of measurements. In cell 3, the condensate is associated with a centrosome. (B) Left: DIC-mNG overlay of a cell with a condensate close to a centrosome; this cell is in early mitosis. High-magnification view (11,000×) reveals a sheet-like object composed of hexagonally packed electron-dense puncta; the bottom part of the condensate appears to narrow and transition to the striated pattern seen in A. White scale bars in DIC-mNG overlay images, 20 µm. Black scale bars in EM images: low magnification, 2 µm; condensate and centrosome serial sections, 0.5 µm; zoomed-in view, 0.1 µm. S, section.\n\nFigure 3: Figure 3. Condensates exhibit two related types of structural organization and form by budding off of centrosomes. (A) Exp-SIM of condensates in TRIM37Δ cells and in TRIM37Δ cells expressing Ligmut TRIM37 immunostained for centrobin. Widefield images are shown on the left; black-and-white images are examples of condensates from different cells. Surface rendering of a condensate in a TRIM37Δ cell is also shown. Scale bars: widefield, 20 µm and 2 µm (panels below image); Exp-SIM, 2 µm. (B) STED microscopy images showing the linear, striated condensates. Scale bars, 0.5 µm. Experiment performed three times with similar results. (C) Quantification of condensate morphologies (see A for example images) from the Exp-SIM analysis. n, number of condensates. The experiment shown in A and C was performed twice with similar results; data shown are from one experiment. (D) Quantification of interstripe or interpuncta distance measured using different methods; n, number of measurements. 10th–90th percentile box-and-whiskers plots with outliers are shown. (E) Live imaging of Ligmut TRIM37-mNG-labeled condensates in a TRIM37Δ cell expressing mRuby-fused MAP4 microtubule-binding domain to label microtubules; the centrosome (cyan arrowhead) and the condensate (yellow arrow) are indicated. Scale bars, 5 µm. Times are in minutes. (F) Summary of timing of condensate splitting from the centrosome in 24 imaged untreated cells (blue arrows) and 23 imaged cells acutely treated with centrinone (red arrows). Time is in hours relative to mitosis of each mother cell. The experiment shown in E and F was performed once; data for each condition was pooled from two replicate wells imaged in parallel.\n\nFigure 4: Figure 4. Condensates form ectopic spindle poles during mitosis in TRIM37Δ RPE1 and mulibrey nanism patient cells. (A) Left: Expansion microscopy images of mitotic TRIM37Δ RPE1 cells labeled for acetylated tubulin showing three mitotic configurations. Right: Quantification of mitotic configurations in the indicated cell lines; note that the rarest category, multipolar with a small acetylated tubulin focus, is marked in blue. Scale bars, 20 µm and 2 µm (insets). The experiment was performed three times; quantification was of the pooled data. (B) Images of mitotic cells at different stages stained for microtubules, centrobin, and CEP192; centrosomes (white arrowheads) and condensates (yellow arrows) are marked. Scale bars, 5 µm and 2 µm (insets). (C) Z sections spaced 0.2 µm apart through a metaphase condensate. Scale bar, 2 µm. The experiment in B and C was performed three times. (D) Quantification of condensate-associated ectopic MTOCs in mitotic TRIM37Δ cells. n, number of condensates. (E) Control and mulibrey nanism primary fibroblasts labeled for microtubules and PLK4 (left) or centrobin (right). The condensate (arrows) is marked. Scale bar, 5 µm. Each experiment was performed once. (F) Stills from live imaging analysis of microtubules labeled by expression of mRuby-MAP4-MBD in TRIM37Δ RPE1 cells. Images are of spindles in two different cells. Arrow points to an ectopic spindle pole. Scale bar, 10 µm. The experiment was performed once. (G) Stills from live imaging of TRIM37Δ cells expressing mRuby-MAP4-MBD (pseudocolored green) and WT TRIM37-mNG or Ligmut TRIM37-mNG (pseudocolored magenta). Three observed phenotypes of mitotic TRIM37Δ cells with a Ligmut TRIM37-mNG-labeled condensate (arrows) are shown. Times are in minutes; 0 min is the first time point after nuclear envelope breakdown. Scale bars, 5 µm. (H) Frequency of ectopic spindle poles observed in the indicated conditions analyzed by live imaging of microtubules; cells that exhibited eventual multipolar segregation are indicated. n, number of imaged cells. For G and H, the data from three independent experiments were pooled. (I) Immunostaining of the three configurations observed for mitotic cells with a condensate (arrows) and the normal number of two centrosomes. Scale bar, 5 µm. (J) Relative frequency of the three configurations shown in I. For I and J, the experiment was performed once; data were pooled from seven replicate wells imaged in parallel."
      }
    ]
  },
  {
    "id": "PMC8127006_multi_2",
    "image": [
      "images/PMC8127006-f7.png",
      "images/PMC8127006-f5-2.png",
      "images/PMC8127006-f11.png",
      "images/PMC8127006-f6.png",
      "images/PMC8127006-f13.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"TRIM37 prevents formation of condensate-organized ectopic spindle poles to ensure mitotic fidelity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. Analysis of centrosomal component localization to centrobin condensate-based ectopic spindle poles and microtubule nucleation activity of mitotic condensates following microtubule depolymerization. (A) Analysis of centrosomal component localization in mitotic TRIM37Δ cells with an ectopic condensate-based spindle pole. Scale bars, 5 µm and 1 µm (insets). (B) Microtubule regrowth analysis comparing control RPE1 and TRIM37Δ RPE1 mitotic cells. The protocol used for this analysis is schematized on the top. Cells were plated overnight (ON), chilled on ice for 40 min, and fixed (0 min) or warmed with 37°C medium for 1 min and then fixed (1 min). Example images of prophase and prometaphase/metaphase stage cells for the 0-min and 1-min conditions are shown. In mitotic TRIM37Δ cells, condensates that nucleated microtubules and condensates that did not were both observed; quantification of the ability of condensates in TRIM37Δ cells to nucleate microtubules after 1 min rewarming is plotted below the images. Scale bars, 10 µm and 2 µm (insets). The experiment was performed once.\n\nFigure 5: Figure 5. Condensate-based ectopic spindle poles cause chromosome missegregation. (A) Fixed analysis of chromosome segregation in anaphase-to-telophase stage cells. Left: Images of multipolar segregation and lagging chromosomes; the condensate (arrows) is marked. Graph on the right plots the frequency of these events in control and TRIM37Δ RPE1 cells. Scale bar, 5 µm. Pooled data from six independent samples. (B) Analysis of micronuclei frequency. Left: Image of a cell with a micronucleus (arrow). Right: Graph of results from three experiments together with the mean; error bars represent standard deviation, and ntot is the total number of cells scored. Scale bar, 5 µm. (C) FISH analysis of chromosomes 17 and 18 in telophase cells. Left: Example images of different classes of telophase figures observed. Right: Quantification of the different categories. The experiment was performed once. Scale bar, 10 µm.\n\nFigure 11: Figure 11. Strategy used to engineer inducible CNTROB knockout and validation of knockout by genotyping and centrosome immunofluorescence. (A) Strategy used to engineer iCNTROB KO in TRIM37Δ and USP28Δ RPE1 cells (i) and details of the CNTROB gRNA, indicating target site in the CNTROB locus (ii). Note that both cell lines have in situ mNG-tagged CEP192. To validate the efficacy of the knockout, tracking of indels by decomposition (TIDE) analysis (Brinkman et al., 2014) was conducted 4 d after induction with 1 µM doxycycline. In both cell lines, ∼80% indels were observed in the induced population. (B) Quantification of centrobin signal at centrosomes 4 d after induction of the knockout. Mean and 95% CI are plotted on top of measurements of individual centrosome pairs (the signal for both centrosomes in a cell was measured together); P value is from an unpaired t test. Experiment performed twice; data shown is from one experiment.\n\nFigure 6: Figure 6. Centrobin is required to form the condensate but not centrin-containing foci in TRIM37Δ cells. (A) Localization of centrobin and PLK4 in the indicated conditions; centrosomes (white arrowheads) and condensates (yellow arrow) are indicated. The strategy to inducibly knock out CNTROB (iCNTROB KO) and efficacy of the knockout are shown in Fig. S3 A. Graph on the right plots frequency of condensates with and without addition of doxycycline to induce CNTROB KO. Scale bars, 5 µm and 1 µm (insets). Experiment was performed three times with similar results; data shown are from one experiment. (B) Localization of PLK4 and centrin in the indicated conditions; centrosomes (white arrowheads) and condensates (yellow arrow) are indicated. Graphs below plots the frequency of cells with centrin foci (left) and the number of centrin foci per cell (right). Scale bars, 5 µm and 1 µm (insets). Since iCNTROB KO is not 100% efficient, only cells that lacked centrosomal centrobin were quantified in the (+) condition in A and B. The experiment was performed once. (C) Schematics summarizing independent suppression of the condensate and centrin foci by TRIM37.\n\nFigure 13: Figure 13. Analysis of the inducible PLK4 knockout and of centrin in the inducible CNTROB knockout. (A) Immunofluorescence analysis of iPLK4 KO after 4 d induction. At this time point, the majority of cells (73.5% in USP28Δ RPE1 (n = 181) and 71% in TRIM37Δ RPE1 (n = 186) are acentrosomal, indicating loss of PLK4 function. No focal localization of PLK4 or centrobin is observed in acentrosomal USP28Δ RPE1 cells generated by inducible PLK4 knockout. In acentrosomal TRIM37Δ RPE1 cells generated by inducible PLK4 KO, 11.8% have no condensate, whereas the rest have a condensate of varying size that contains both PLK4 and centrobin. Scale bars, 5 µm and 1 µm (insets). (B) Quantification of PLK4 and centrobin signal at condensates that persist after 4-d inducible PLK4 knockout in TRIM37Δ RPE1 cells. All of the analyzed cells were acentrosomal, indicating sufficient loss of PLK4 function to prevent centriole duplication. Mean and 95% CI are plotted on top of the individual values. Both PLK4 and centrobin are reduced at the condensates following PLK4 knockout (P values from unpaired t tests; **, P < 0.01). Note that the control (−Dox) data for condensates are the same as that shown in Fig. 1 G (analysis of this pair of USP28Δ and TRIM37Δ cell lines, ODCL0079 and ODCL0080, is reported in Fig. 1 G without Cas9 induction). The experiment shown in A and B was performed three times with similar results; data shown are from one experiment. (C) Centrin localization in mitotic control USP28Δ and TRIM37Δ cells following inducible knockout of CNTROB. The centrobin condensate is no longer detected in TRIM37Δ cells, but ectopic centrin foci (orange arrows) persist. Note that centrin is also present at centrosomes (white arrowheads). Scale bar, 5 µm. The experiment was performed three times with similar results; data shown are from one experiment."
      }
    ]
  },
  {
    "id": "PMC8127006_multi_3",
    "image": [
      "images/PMC8127006-f7-2.png",
      "images/PMC8127006-f8-2.png",
      "images/PMC8127006-f17.png",
      "images/PMC8127006-f9-2.png",
      "images/PMC8127006-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"TRIM37 prevents formation of condensate-organized ectopic spindle poles to ensure mitotic fidelity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. Centrobin removal suppresses ectopic spindle pole formation in TRIM37Δ cells. (A) Images of mitotic cells labeled for microtubules, centrobin, and DNA for the indicated conditions. Scale bar, 5 µm. (B) Quantification of ectopic spindle pole frequency for the indicated conditions. The experiment was performed once. (C) Stills from live imaging of mitotic chromosome dynamics for the indicated conditions; time 0 is nuclear envelope breakdown (NEBD). Transient multipolarity is evident in the chromosome configuration (arrow) in a subset of TRIM37Δ cells. Scale bar, 10 µm. (D) Quantification of transient multipolarity and multipolar segregation (left graph) and of mitotic duration (right graph), defined as the time from NEBD to chromosome decondensation. Mean and 95% CI for mitotic duration are plotted on top of the values for individual cells; P values are from unpaired t tests. The experiment shown in C was performed twice with similar outcomes; data from one experiment are quantified in D. ****, P < 0.0001.\n\nFigure 8: Figure 8. TRIM37 interacts with and ubiquitinates centrobin. (A) Immunoblotting of centrobin in the indicated cell lines. Graph on right plots centrobin levels relative to the mean control value (n = 3). (B) Schematic of coexpression-based analysis of regulation of centrobin by TRIM37 shown in C–G. (C) Immunoblotting of crude extracts with the indicated antibodies. (D) Supernatant (S) and pellet (P) fractions immunoblotted with the indicated antibodies. α-tubulin fractionates into the supernatant, as expected for extracts prepared after cold treatment. Even under the denaturing conditions used, centrobin and Ligmut TRIM37 were not consistently quantitatively recovered from the pellet. (E) Band signal intensity values from two independent experiments of total centrobin in crude extract (left), relative centrobin enrichment in pellet (middle), and relative Ligmut TRIM37 enrichment in pellet; the Ligmut TRIM37 pellet enrichment plot has a logarithmic y axis. Sup, supernatant. (F) Anti-Myc and Anti-FLAG immunoblotting of anti-Myc immunoprecipitates (IP). (G) Centrobin ubiquitination by TRIM37; a plasmid encoding HA-ubiquitin was included in the coexpression. The input shown is the crude extract. (H and I) FRAP analysis of Ligmut TRIM37-mNG localized to condensates in TRIM37Δ cells. In H, multiple time point images and quantification of signal intensity along a 10-pixel-wide line is shown. The intensity value at the left most position before the condensate was used as the background and subtracted; after background subtraction, all pixel values were normalized by dividing by the average prebleach signal. In I, selected images are shown above the linescan plots. Images of the condensates from individual time-lapse movie frames were cropped and rotated before montaging. Scale bars, 1 µm. The experiment was performed five times with similar results; three examples are shown. α-Tubulin serves as a loading control in A, C, D, and G. high exp., higher exposure; low exp., lower exposure.\n\nFigure 17: Figure 17. Additional coexpression analysis of centrobin regulation by TRIM37. (A–C) Results of an independent experiment assessing the effect of coexpressing TRIM37 (WT versus Ligmut) and centrobin on centrobin levels (A) and relative solubility (B). In addition, interaction of Ligmut TRIM37 with centrobin was analyzed (C). Quantification of levels and relative solubility is shown in Fig. 8 E. (D) Interaction of WT or Ligmut TRIM37 with centrobin was analyzed in MG132-treated cells using the protocol schematized on the top. Anti-Myc and Anti-FLAG immunoblotting of anti-Myc immunoprecipitates is shown on the bottom. A plasmid encoding HA-ubiquitin was included in the coexpression. α-Tubulin serves as a loading control in A, B, and D.\n\nFigure 9: Figure 9. PLK4-scaffolded foci that accelerate acentrosomal mitosis in TRIM37Δ cells are centrobin-independent. (A and B) Immunostaining and fluorescent signal of in situ–tagged CEP192-mNG in USP28Δ and TRIM37Δ RPE1 cells treated with DMSO or centrinone (A) and additionally treated with doxycycline to induce CNTROB or PLK4 knockout (B). Scale bars, 5 µm and 1 µm (insets). (C) Graph of the percentage of cells with condensates and CEP192-PLK4 foci in the indicated conditions. The experiment shown in A and B was performed twice with similar outcomes; data from one experiment are quantified in C. (D) Quantification of mitotic duration, measured as in Fig. 7 D, for the indicated conditions. Mean and 95% CI are plotted on top of the individual values; P values are from t tests. ****, P < 0.0001. The experiment was performed twice with similar outcomes; data from one experiment are quantified. (E) Images of acentrosomal spindles in centrinone-treated TRIM37Δ cells, with and without centrobin. The centrobin-scaffolded condensate (yellow arrow) and the PLK4-scaffolded foci (cyan arrowheads) are marked. Scale bar, 5 µm. The experiment was performed twice with similar outcomes. (F) Schematic summary of analysis of acentrosomal mitosis following centrinone treatment. The PLK4-scaffolded foci, and not the centrobin-scaffolded condensate, improve acentrosomal mitosis following centrinone treatment.\n\nFigure 10: Figure 10. Model for TRIM37 function in ensuring accurate chromosome segregation and its relevance to mulibrey nanism. In the absence of TRIM37 activity, an ectopic centrobin-scaffolded condensate and centrin foci are formed. Approximately 25% of centrobin-scaffolded condensates assemble an ectopic spindle pole, resulting in both multipolar segregation and an elevated rate of lagging chromosomes. We propose that these low-frequency segregation errors caused by the centrobin-scaffolded ectopic spindle pole are major contributors to the pathology of mulibrey nanism. The centrin foci observed in TRIM37Δ cells are independent of the centrobin-scaffolded condensate; the functional impact of their formation remains to be elucidated."
      }
    ]
  },
  {
    "id": "PMC8134739_multi",
    "image": [
      "images/PMC8134739-f1.png",
      "images/PMC8134739-f2.png",
      "images/PMC8134739-f3.png",
      "images/PMC8134739-f4.png",
      "images/PMC8134739-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Plasmalogen attenuates the development of hepatic steatosis and cognitive deficit through mechanism involving p75NTR inhibition\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PlsEtn synthesis was impaired in APP/PS1 and HFD-fed mice. (A) Biosynthetic and catabolic pathways of plasmalogens. (B) Heatmaps illustrate the fold change in individual plasmalogen species in the hippocampus of APP/PS1 mice compared against WT mice. (C and D) Relative mRNA expressions related to peroxisomes homeostasis and PlsEtn synthesis pathway in the hippocampus and liver of APP/PS1 mice compared against WT mice. (E) Heatmaps illustrate the fold change in individual plasmalogen species in the hippocampus of HFSD-fed mice compared against chow diet-fed mice. (F) Heatmaps illustrate the fold change in individual plasmalogen species in the liver of HFSD-fed mice compared against chow diet-fed mice. (G and H) Relative mRNA expressions related to peroxisomes homeostasis and PlsEtn synthesis pathway in the hippocampus and liver of HFSD-fed mice compared against chow diet-fed mice. Statistical significance was determined by Student's t-test, *p < 0.05, **p < 0.01 vs WT or Chow diet-fed mice.\n\nFigure 2: Figure 2. PlsEtn deficiency aggravates hepatic steatosis via p75NTR. (A) AML12 cells were transfected with shGNPAT or scrambled control (shCTRL1) and subsequently exposed to 400 μM PA for an additional 48 h. Lipid droplets accumulation within the AML12 cells were determined by Oil-red O staining and quantified at 500 nm. (B) Representative Western blot indicating the protein expression of p75NTR and lipolysis related genes in AML12 cells treated with shGNPAT. (C) AML12 cells were transfected with shp75NTR or scrambled control (shCTRL2) and subsequently exposed to 400 μM PA for an additional 48 h. Lipid droplets accumulation were determined by Oil-red O staining and quantified at 500 nm. (D) 6-week old mice was used to develop hepatic steatosis under high fat high fructose diet and treated with recombinant AAV virus of shGnpat. (E) Photomicrographs depicting the liver from AAV-shGnpat-treated and HFSD-fed mice (n = 5 mice/group) stained for H&E and Oil red O. (F) Representative Western blot indicating the protein expression of p75NTR and lipolysis related genes in AAV-shGnpat-treated and HFSD-fed mice. (G) Hepatic triglyceride levels in AAV-shGnpat-treated and HFSD-fed mice. (H) Hepatic total cholesterol in AAV-shGnpat-treated and HFSD-fed mice. (I) Representative Western blot indicating the protein expression of p75NTR and lipolysis related genes in AML12 cells treated with shp75NTR. Statistical significance was determined by Student's t-test, *p < 0.05, **p < 0.01 vs scrambled control. (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)\n\nFigure 3: Figure 3. PlsEtn supplementation ameliorates hepatic steatosis in HFSD-fed mice. (A and B) AML12 cells were exposed to 400 μM PA in the presence or absence of PlsEtn (200 μg ml−1) for 48 h. Lipid droplets accumulation were determined by Oil-red O staining and quantified at 500 nm. (C) Photomicrographs depicting the liver from PlsEtn treated and HFSD-fed mice (n = 5 mice/group) stained for H&E and Oil red O. (D) Serum triglyceride levels in PlsEtn-treated APP/PS1 mice measured by lipids quantification. (E and F) Representative Western blot indicating the protein expression of p75NTR and lipolysis related genes in the liver of HFSD-fed mice (n = 5 mice/group). Statistical significance was determined by Student's t-test, *p < 0.05, **p < 0.01 vs HFSD-feed group; #p < 0.05, ##p < 0.01 vs Chow diet group. (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)\n\nFigure 4: Figure 4. PlsEtn treatment restores TrkA/p75NTR signaling, ameliorates neurodegeneration and neural death in APP/PS1 mice. (A and B) Representative Western blot indicating the expression of neurotrophins and their receptors in the hippocampus of APP/PS1 mice (n = 6 mice/group). (C) Photomicrographs depicting the hippocampus from APP/PS1 mice (n = 6 mice/group) stained for NGF. Scale bar, 200 μm. (D) Photomicrographs depicting the hippocampus from APP/PS1 mice (n = 6 mice/group) stained for MAP-2 (Red), NeuN (Green), and ChAT. Scale bar, 50 μm. (E) NFTs in APP/PS1 mice were reduced with the treatment of PlsEtn, as judged by a Bielschowsky silver staining method for detecting neurofibrillary tangles. Scale bar, 100 μm. (F and G) Dendritic spine and its density was conducted by Golgi staining measured then (n = 9 sections from 3 mice in each group). (H and I) Representative Western blot indicating the expression of apoptosis related markers in the hippocampus of APP/PS1 mice (n = 6 mice/group). (J) Photomicrographs depicting the hippocampus from APP/PS1 mice (n = 6 mice/group) stained for Cas3 (Red) and NeuN (Green). Scale bar, 50 μm. (K) Photomicrographs depicting the hippocampus from APP/PS1 mice (n = 6 mice/group) stained for TUNEL. Scale bar, 200 μm. Statistical significance was determined by Student's t-test, *p < 0.05, **p < 0.01 vs APP/PS1 mice; #p < 0.05, ##p < 0.01 vs WT mice. (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)\n\nFigure 5: Figure 5. PlsEtn supplementation ameliorates memory deficits, Aβ and Tau pathology. (A) Escape latency to the platform during the training trails in a Morris water maze (n = 5 mice/group). (B) Time spent in target quadrant in the MWM test at day 5. (C) Times crossing the target sites after retrieval of the platform at day 5. (D) Entries in target quadrant. (E) Average speed to find the platform. (F) Assessment of search strategy (spatial, non-spatial, repetitive) in the acquisition phase of the water maze test. (G) The percentage of time engaged in spatial search strategies during the 60-s trial was calculated, with search strategies combined into 3 groups based on functional similarity (Spatial Direct, Spatial Indirect, and Focal Correct strategies). (H and I) Photomicrographs of Aβ plaques within the hippocampus of APP/PS1 and PlsEtn-fed mice (n = 6 mice/group). Scale bar, 200 μm. (J and K) Quantitative analysis for the soluble and insoluble forms of Aβ1-40 and Aβ1-42 in hippocampus of APP/PS1 mice (n = 6 mice/group). (L and M) Representative Western blot of APP processing. (N and O) Representative Western blot of tau and p-Tau. Statistical significance was determined by Student's t-test, *p < 0.05, **p < 0.01 vs APP/PS1 mice; #p < 0.05, ##p < 0.01 vs WT mice."
      }
    ]
  },
  {
    "id": "PMC8144742_multi",
    "image": [
      "images/PMC8144742-f1.png",
      "images/PMC8144742-f2.png",
      "images/PMC8144742-f3.png",
      "images/PMC8144742-f4.png",
      "images/PMC8144742-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Endothelial ether lipids link the vasculature to blood pressure, behavior, and neurodegeneration\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PEKO (PexRap Endothelial KnockOut) mice have decreased circulating PE plasmalogens, but normal concentrations of other lipids and a normal response to hindlimb ischemia. A: QRT-PCR of PexRAP mRNA in lung endothelial cells from control and PEKO mice with representative images of PexRAP and L32 amplification products above graphs. B: Total PE plasmalogens determined by mass spectrometry in plasma from control and PEKO mice. C: Individual PE plasmalogen species in plasma from control and PEKO mice. D: Total PC plasmalogens, (E) total ester phosphatidylcholine species, and (F) total ester phosphatidylethanolamine species in plasma from control and PEKO mice. G–I: Fasting triglycerides (G), cholesterol (H), and nonesterified fatty acids (NEFA, I) in plasma from control and PEKO mice. J: Angiogenesis responses following hindlimb ischemia in control and PEKO mice. K: Representative laser Doppler imaging of mice before and after femoral artery ligation. Data are presented as individual data points with mean ± SEM, box and whisker plots, or mean ± SEM over time. PE, phosphatidylethanolamine.\n\nFigure 2: Figure 2. PEKO mice have decreased blood pressure and increased plasma renin activity. A–D: Tail cuff determinations of systolic (A), diastolic (B), and mean (C) blood pressure as well as heart rate (D) in control and PEKO mice. E and F: Telemetry-determined blood pressure and heart rate in unrestrained mice. G: Plasma renin activity in control and PEKO mice. H–K: Tail cuff determinations of systolic (H), diastolic (I), and mean (J) blood pressure as well as heart rate (K) in control and PEKO mice in the setting of salt loading. Data are presented as individual data points with mean ± SEM or mean ± SEM over time. PEKO, PexRAP endothelial knockout.\n\nFigure 3: Figure 3. Decreased physical activity in PEKO mice. A and B: Home cage movement in the horizontal plane (X+Y) (A) and vertical rearing (Z) (B) in control mice and mice with endothelial-specific PexRAP deficiency (PEKO mice). C, D, Home cage movement in the horizontal plane (C) and vertical rearing (D) in control mice and mice with whole body heterozygous PexRAP deficiency (Dhrs7b+/- mice). E and F: Home cage movement in the horizontal plane (E) and vertical rearing (F) in control mice and mice with skeletal muscle-specific PexRAP deficiency (PMKO mice). Data are presented as mean ± SEM for the preceding 2 h time period. PEKO, PexRAP endothelial knockout; PMKO, PexRAP muscle knockout.\n\nFigure 4: Figure 4. Behavioral phenotyping in PEKO and control mice. A and B: One hour locomotor activity testing for ambulatory activity (A) and vertical rearing (B) performed with lights on during daytime in control and PEKO mice. C and D: Novel object recognition testing employing a sample trial (C) and test trial (D). E and F: Assessment of attention devoted to a hanging object included measurements of total rearing time as a control procedure (E) and investigative rearing time as an index of attention (F). G: Time required for control and PEKO mice to reverse position and climb to the top of a 60° inclined screen. H: Daytime sleep duration. I: Probe trial data from the Morris water maze procedure. Data are presented as mean ± SEM for the preceding 10 min time period, box and whisker plots, or individual data points with mean ± SEM. PEKO, PexRAP endothelial knockout.\n\nFigure 5: Figure 5. Characterization of the locus coeruleus, hippocampus, and dorsal root ganglia in PEKO and control mice. A: Area of tyrosine hydroxylase positive neurons based on genotype. B: Representative images from sections quantified for panel A. Scale = 1 mm. C: Locus coeruleus silver staining. D: GFAP quantification in hippocampus based on genotype. E: Representative images (red = GFAP) from sections quantified for panel D. Scale = 100 microns. F: Hippocampal silver staining. G: Quantification of PE plasmalogens in the hippocampus of control and PEKO mice. H: GFAP quantification in dorsal root ganglia based on genotype. I: Representative images (green = GFAP, blue = DAPI, red = TuJ1) from sections quantified for panel H. Scale = 100 microns. Data are presented as individual data points with mean ± SEM or box and whisker plots. PE, phosphatidylethanolamine; PEKO, PexRAP endothelial knockout."
      }
    ]
  },
  {
    "id": "PMC8147788_multi",
    "image": [
      "images/PMC8147788-f1.png",
      "images/PMC8147788-f2.png",
      "images/PMC8147788-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Mechanisms and Functions of Pexophagy in Mammalian Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Model for the import of peroxisomal matrix proteins. PTS1-containing cargos are synthesized in the cytoplasm and recognized by the receptor PEX5 (①). PEX5 interacts with the peroxisome-associated docking proteins PEX13 and PEX14 and transports the cargos to the matrix (②). After the release of the cargos (③), PEX5 is recycled back to the cytoplasm for the next round of import (④⑤⑥). Extraction of PEX5 from peroxisomes depends on the monoubiquitination of PEX5 at C11, which is catalyzed by the E3 ligase complex (PEX2, PEX10, and PEX12) (④). The AAA complex (PEX1-PEX6-PEX26) facilitates the extraction process (⑤).\n\nFigure 2: Figure 2. Mechanisms of ubiquitin-dependent pexophagy. (A) PEX5 fused to a C-terminal bulky tag can be monoubiquitinated at C11 but fails to be extracted back to the cytosol by the AAA complex. The accumulated monoubiquitination of the PEX5 fusion proteins serves as a signal to direct pexophagy. (B) Loss of AAA complex function (dashed border) results in the accumulation of monoubiquitinated PEX5 proteins in peroxisomes, which promotes pexophagy. (C) Activation of ATM by ROS phosphorylates PEX5 at S141, which facilitates PEX5 monoubiquitination at K209 by the PEX2, PEX10, and PEX12 complex (E3 ligase complex). The autophagy receptor p62 recognizes ubiquitinated PEX5 and recruits the core autophagy machinery to eliminate damaged peroxisomes in response to oxidative stresses. (D) Under conditions of amino acid starvation, PEX2 proteins are stabilized upon mTORC1 inhibition. Upregulation of PEX2 promotes the ubiquitination of peroxisomal proteins, including PEX5, PMP70, and other unknown proteins, which serve as signals for NBR1 and p62-mediated pexophagy. The deubiquitinase USP30 removes the ubiquitin from peroxisomal proteins and inhibits pexophagy during amino acid starvation.\n\nFigure 3: Figure 3. Mechanisms of ubiquitin-independent pexophagy. (A,B) LC3 outcompetes PEX5 for binding to PEX14 and sequesters peroxisomes into autophagosomes for autophagic degradation under starvation conditions. In parallel, TNKS1/2 proteins associate with PEX14 and ATG9A and promote starvation-induced pexophagy. (C) Noise overexposure increases cellular ROS and causes oxidation of pejvakin at C328/C343, which is required for pejvakin-LC3B interaction and pexophagy."
      }
    ]
  },
  {
    "id": "PMC8148155_multi",
    "image": [
      "images/PMC8148155-f1.png",
      "images/PMC8148155-f2.png",
      "images/PMC8148155-f3.png",
      "images/PMC8148155-f4.png",
      "images/PMC8148155-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Oral Supplementation of an Alkylglycerol Mix Comprising Different Alkyl Chains Effectively Modulates Multiple Endogenous Plasmalogen Species in Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Dietary alkylglycerols can modulate endogenous plasmalogen content. Dietary AKGs can bypass the rate-limiting peroxisomal biosynthetic steps (red pathway). Metabolites are shown in red and black and enzymes are shown in violet. AADHAP-R: alkyl/acyl-DHAP-reductase, AAG3P-AT: alkyl/acyl-glycero-3-phosphate acyltransferase, ADHAP-S: alkyl DHAP synthase, AG kinase: alkylglycerol kinase, CoA: coenzyme A, C-PT: choline phosphotransferase, Δ1-desaturase: plasmanylethanolamine desaturase, DHAP: dihydroxyacetone phosphate, DHAP-AT: DHAP acyltransferase, E-PT: ethanolamine phosphotransferase, FAR-1/2: fatty acyl-CoA reductase 1 or 2, ER: endoplasmic reticulum, GPC: glycerophosphocholine, GPE: glycerophosphoethanolamine; PC: phosphatidylcholine, PE: phosphatidylethanolamine, PEMT: phosphatidylethanolamine N-methyltransferase, PH: phosphohydrolase, PLC: phospholipase C.\n\nFigure 2: Figure 2. Effects of alkylglycerol mix administration on alkylphospholipid concentrations in plasma and tissues. Concentrations of alkylphosphatidylethanolamine (PE(O)) and alkylphosphatidylcholine (PC(O)) were normalised to total phosphatidylcholine (PC) concentration in plasma and different tissues of C57BL6 mice (n = 7–8/group) at each time point (offset for clarity). Treatment (solid lines) and vehicle (dashed lines) groups are shown for each tissue. Boxes show the inter-quartile range and whiskers show the range. Outliers (greater than 1.5 times the inter-quartile range from the median) are shown as empty circles. Medians are shown as white dots and are joined together to facilitate visualisation of the pseudo-kinetics. Post-hoc p values for treatment effect from a two-way ANOVA are also shown. Purple stars indicate significance: * p < 0.05, ** p < 0.01 and *** p < 0.001 from a post-hoc test for the mean differences between treatment and vehicle groups at each time point.\n\nFigure 3: Figure 3. Effects of alkylglycerol mix administration on alkenylphospholipid (plasmalogen) concentrations in plasma and tissues. Concentrations of alkenylphosphatidylethanolamine (PE(P)) and alkenylphosphatidylcholine (PC(P)) were normalised to total phosphatidylcholine (PC) concentration in plasma and different tissues of C57BL6 mice (n = 7–8/group) at each time point (offset for clarity). Treatment (solid lines) and vehicle (dashed lines) groups are shown for each tissue. Boxes show the inter-quartile range and whiskers show the range. Outliers (greater than 1.5 times the inter-quartile range from the median) are shown as empty circles. Medians are shown as white dots and are joined together to facilitate visualisation of the pseudo-kinetics. Post-hoc p-values for treatment effect from a two-way ANOVA are also shown. Purple stars indicate significance: * p < 0.05, ** p < 0.01 and *** p < 0.001 from a post-hoc test for the mean differences between treatment and vehicle groups at each time point.\n\nFigure 4: Figure 4. Heatmap showing the effects of alkylglycerol mix administration on plasmalogen species in plasma and tissues. Plasmalogen concentration data are presented as Z scores calculated for all animals in the study (mean-centered and scaled to unit variance per lipid) (by row). W: weeks of treatment, AKG: alkylglycerol mix, PC(P): alkenylphosphatidylcholine; PE(P), alkenylphosphatidylethanolamine.\n\nFigure 5: Figure 5. Effects of alkylglycerol mix administration on endogenous plasmalogens with different alkenyl chains. Concentrations of alkenylphosphatidylethanolamine (PE(P)) with different alkenyl chains were normalised to total phosphatidylcholine (PC) concentration in plasma and different tissues of C57BL6 mice at the 12-week time point. Data are presented as mean ± SEM (n = 8/group). Treatment (darker colours) and vehicle (lighter colours) groups are shown for each tissue. The mean differences between two dietary groups (vehicle and treatment) were analysed using Student’s t-test; * indicates p < 0.05, ** indicates p < 0.01 and *** indicates p < 0.001 relative to the vehicle group."
      }
    ]
  },
  {
    "id": "PMC8201181_multi",
    "image": [
      "images/PMC8201181-f1.png",
      "images/PMC8201181-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Peroxisomal ABC Transporters: An Update\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomal ABC transporters and their involvement in lipid metabolism. Peroxisomal ABC transporters are represented as homo or heterotetramers with their preferential substrates and their involvement in metabolic routes, including several enzymatic steps, catalyzed by acyl-CoA oxidase 1 and 2 (ACOX1 and ACOX2), D- and L-bifunctional protein (D-BP and L-BP), acetyl-CoA Acyltransferase 1 (3-ketoacyl-CoA thiolase, ACAA1), sterol carrier protein 2 (SCPX thiolase, SCP2), alpha-methylacyl-CoA racemase (AMACR), bile acid-CoA:amino acid N-acyltransferase (BAAT), and phytanoyl-CoA hydroxylase (PHYH).\n\nFigure 2: Figure 2. Structural model of human ABCD1 (reprinted from [17]). (A) Ribbon representation of the ABCD1 monomer. TMD helices are numbered from 1 to 6 and rainbow colored from dark blue to red. NBD is in light grey, and intracellular loops (ICL) 1 and 2 are indicated. (B) Ribbon representation of the ABCD1 homodimer with the two subunits respectively colored in dark blue and yellow."
      }
    ]
  },
  {
    "id": "PMC8204421_multi",
    "image": [
      "images/PMC8204421-f1.png",
      "images/PMC8204421-f2.png",
      "images/PMC8204421-f3.png",
      "images/PMC8204421-f4.png",
      "images/PMC8204421-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Parkinson’s disease–associated VPS35 mutant reduces mitochondrial membrane potential and impairs PINK1/Parkin-mediated mitophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generation of heterozygous VPS35D620N SH-SY5Y cells. a Schematic representation of cloning strategy for the generation of nucleotide exchange in the VPS35 locus that leads to the D620N mutation using CRISPR-Cas9 technology. Partial sequence of endogenous target on exon 15 is shown (upper sequence). The 20-nt guide sequence is depicted by the burgundy line with the blue arrowhead pointing towards the predicted Cas9-cleavage site. GAT sequence that encodes the aspartic acid residue at position 620 is highlighted in red. Lower sequence shows the design of the repair template used to create the mutation. The substitution G > A is shown in red. Silent substitutions to create an EcoRI restriction site are shown in green. b Representative agarose gel showing PCR products of the target VPS35 region obtained from different CRISPR-clones. PCR products were subjected to EcoRI digestion before loading on an agarose gel. Upper bands show noncleaved bands of the PCR amplicon. Arrowhead indicates an example of a successfully edited clone (VPS35D620N clone 1) that was partially cleaved by EcoRI. c Sanger chromatograms of the region surrounding the CRISPR-edit of WT (upper panel), VPS35 D620N clone 1 (middle panel) and VPS35 D620N clone 2 (lower panel). Red arrowhead indicates successful integration of the PD-associated mutation G > A. Black arrowheads indicate silent substitutions to create the EcoRI restriction site. Note that double peaks are shown for the edited nucleotides as one allele remains unaltered. d Representative immunoblots of protein extracts from WT and VPS35D620N (clone 1 and clone 2) cells. Blots were stained for VPS35 and β-actin (total protein loading control)\n\nFigure 2: Figure 2. CCCP-induced PINK1/Parkin recruitment is impaired in VPS35D620N cells. a Representative immunoblots for PINK1 in WT and VPS35D620N (clone 1 and clone 2) cells treated with DMSO, 10 μM or 20 μM CCCP for 24 h. b Quantification of PINK1 levels from immunoblots in (a). Shown are relative PINK1 levels after 10 μM or 20 μM CCCP stimulation for 24 h compared to WT cells. Note that PINK1 levels were not quantifiable when treated with DMSO and thus comparisons were made within each treatment condition. Each red dot depicts a separate experiment. Statistical analyses were performed by one-way ANOVA followed by Tukey’s post-hoc test. c Representative immunoblots for VPS35, PINK1, Parkin, TOM20 (mitochondrial loading control) and β-actin (total protein loading control) using protein extracts derived from whole cell, crude mitochondrial fractions or cytosolic fraction from WT and VPS35D620N cells treated with either DMSO or 10 μM CCCP for 6 h. d Quantification of PINK1, Parkin and VPS35 in the mitochondrial fraction from the immunoblots in (c). Shown are relative levels compared to the WT cells treated with CCCP. Each red dot depicts a separate experiment. Statistical analyses were performed by two-way ANOVA followed by Tukey’s post-hoc test. e Representative fluorescence images of cells transiently overexpressing EGFP-Parkin (upper panels: white, lower panels: green), which were also stained for the mitochondrial protein TOM20 (lower panels: magenta). WT cells with EGFP-Parkin translocated onto mitochondria are shown in the left panels and VPS35D620N cells showing a diffuse cytosolic distribution of EGFP-Parkin are shown in the middle (clone 1) and right (clone 2) panels. Scale bar, 10 μm. f Quantification of WT and VPS35D620N (clone 1 and clone 2) cells with EGFP-Parkin translocation to mitochondria, as shown in (e), after 10 μM CCCP stimulation for 24 h, represented as fraction (%) of all counted cells. Red dots represent the means of four different experiments in which at least 50 cells were counted. Data were analyzed using a beta regression. *P < 0.05, **P < 0.01, ***P < 0.005, ****P < 0.001\n\nFigure 3: Figure 3. PINK1 does not localize to mitochondria upon CCCP treatment in VPS35D620N cells. a Representative fluorescence images of WT or VPS35D620N (clone 1) cells treated with 10 μM or 20 μM CCCP for 24 h. From left to right: endogenous TOM20 staining; endogenous PINK1 staining; overlay image including DAPI staining for nuclei in which cells with co-localization (white) of TOM20 (magenta) and PINK1 (green) are outlined; zoom-in of highlighted area in overlay image. Scale bar, 10 μm, or 4 μm for zoomed images. b Quantification of co-localization of endogenous TOM20 and PINK1 of WT and VPS35D620N (clones 1 and 2) cells treated with 10 μM or 20 μM CCCP for 24 h. Each dot represents the Pearson coefficient calculated for one cell. Red lines show the median Pearson coefficient per cell line. Statistical analyses were performed using the Kruskal-Wallis test followed by a pairwise Mann-Whitney U-test with Benjamini-Hochberg multiple testing correction. ***P < 0.005, ****P < 0.001\n\nFigure 4: Figure 4. VPS35D620N cells display impaired mitophagy upon CCCP treatment. a Representative fluorescence images of WT (left panels) or VPS35D620N (right panels) cells stably expressing COX8-EGFP-mCherry treated with DMSO (upper panels) or 10 μM CCCP (middle panels) for 24 h. The signal from the yellow particles originates from EGFP and mCherry and highlights cytoplasmic mitochondria. The red particles show quenched EGFP signal and normal mCherry signal, reflecting mitochondria transported into an acidic compartment (mitophagolysosome). Lower panels show zoomed-in images from the highlighted area in the middle panels. Scale bar, 10 μm, or 4 μm for zoomed images. b Quantification of yellow and red particles in (a) in WT and VPS35D620N cells treated with DMSO or 10 μM CCCP. Each dot represents the proportion of total yellow and red particles for one cell. Red lines show the median proportion per cell line per condition. Statistical analysis was performed using a beta regression. c Representative confocal images of WT (left panels) or VPS35D620N (clone 1, right panels) cells transiently overexpressing EGFP-LC3 (upper panel: white, lower panel: green) and stained for the mitochondrial protein TOM20 (middle panel: white, lower panel: magenta) treated with 10 μM CCCP for 6 h. Scale bar, 10 μm. d Quantification of EGFP-LC3 puncta colocalized with mitochondria in WT and VPS35D620N (clone 1 and 2) cells treated with 10 μM CCCP. Each dot represents one cell. Red lines show the median amount of EGFP-LC3 on mitochondria per cell line. Data analyzed using one-way ANOVA. ****P < 0.001\n\nFigure 5: Figure 5. PINK1 accumulation is unaltered in VPS35D620N cells as a result of depolarization via antimycin A and oligomycin. a Representative immunoblots of protein extracts from WT and VPS35D620N (clone 1 and clone 2) cells treated with DMSO, 1 μM antimycin A, 1 μM oligomycin, or a combination of both drugs for 24 h. Blots were stained with PINK1, Parkin and β-actin (total protein loading control) antibodies. b Quantification of PINK1 and Parkin levels from immunoblot analysis in (a). Shown are relative PINK1 and Parkin levels after 1 μM oligomycin or 1 μM antimycin A and 1 μm oligomycin stimulation for 24 h compared to the WT cells. Each red dot depicts a separate experiment. Statistical analyses were performed by one-way ANOVA followed by Tukey’s post-hoc test. c Representative fluorescence images of WT or VPS35D620N (clone 1 and 2) cells treated with 1 μM antimycin A and 1 μM oligomycin. From top to bottom: endogenous TOM20 staining; endogenous PINK1 staining; overlay image of TOM20 (magenta), PINK1 (green) and DAPI staining for nuclei (blue); zoom in of highlighted area in overlay image. Scale bar, 10 μm, or 4 μm for zoomed images. d Quantification of co-localization of endogenous TOM20 and PINK1 in WT and VPS35D620N (clones 1 and 2) cells treated with 1 μM antimycin A and 1 μM oligomycin, as shown in (c). Each dot represents the Pearson coefficient calculated for one cell. Red lines show the median Pearson coefficient per cell line. Statistical analysis was performed using a Kruskal-Wallis test followed by a pairwise Mann-Whitney U-test with Benjamini-Hochberg multiple testing correction. e Representative fluorescence images of WT (left panels) or VPS35D620N (right panels) cells that stably express COX8-EGFP-mCherry treated with 1 μM antimycin A and 1 μM oligomycin for 24 h. The signal from the yellow particles originates from EGFP and mCherry and highlights cytoplasmic mitochondria. The red particles show quenched EGFP signal and normal mCherry signal, reflecting mitochondria transported into an acidic compartment (mitophagolysosome). Scale bar, 10 μm. f Quantification of yellow and red particles in WT and VPS35 D620N cells in (e). Each dot represents the proportion of total yellow and red particles for one cell. Red lines show the median proportion per cell line per condition. Statistical analysis was performed using a beta regression. n.s. non-significant, *P < 0.05, **P < 0.01"
      }
    ]
  },
  {
    "id": "PMC8204421_multi_2",
    "image": [
      "images/PMC8204421-f6.png",
      "images/PMC8204421-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Parkinson’s disease–associated VPS35 mutant reduces mitochondrial membrane potential and impairs PINK1/Parkin-mediated mitophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. VPS35D620N cells are less susceptible to CCCP-induced mitochondrial depolarization. a Measurements of mitochondrial membrane potential of WT and VPS35D620N (clone 1 and 2) cells by TMRM fluorescence at basal level and at 1, 3, 10 and 20 min after treatment with 10 μM CCCP. b Basal TMRM levels from boxed area highlighted in (a). c TMRM fluorescence was measured 1 min after treatment with 1, 5, 10, 20 or 50 μM CCCP. Shown data are relative to basal conditions of each cell line. Slopes were determined using a simple linear regression. d TMRM fluorescence was measured 24 h after treatment with 10 μM CCCP or 1 μM antimycin A and 1 μM oligomycin. Shown data are relative to basal conditions of each cell line. Statistical analyses were performed using two-way ANOVA followed by Tukey’s post-hoc test. e Representative immunoblots of protein extracts from WT and VPS35D620N (clone 1 and clone 2) cells at steady state. Blots were stained with ATPIF1 and β-actin (total protein loading control) antibodies. f Quantification of ATPIF1 levels from immunoblots in (e). Each red dot depicts a separate experiment. Statistical analyses were performed by one-way ANOVA followed by Tukey’s post-hoc test. *P < 0.05, **P < 0.01, ***P < 0.005, ****P < 0.001\n\nFigure 7: Figure 7. Mitochondria of VPS35D620N cells appear damaged under basal conditions and do not respond to CCCP. a, b Representative TEM micrographs of WT and VPS35D620N (clones 1 and 2) cells treated with DMSO (a) or 10 μM CCCP for 6 h (b). Mitochondria are highlighted in red. DGC, degradative compartment; G, Golgi apparatus; PM, plasma membrane. Scale bar, 1 μm. c Representative examples of the mitochondria categories I–V. d Quantification of the mitochondrial profile of WT or VPS35D620N (clones 1 and 2) cells treated with DMSO or 10 μM CCCP for 6 h. Statistical analyses were performed by two-way ANOVA followed by Tukey’s post-hoc test. n.s. non-significant, ****P < 0.001"
      }
    ]
  },
  {
    "id": "PMC8226985_multi",
    "image": [
      "images/PMC8226985-f1.png",
      "images/PMC8226985-f2.png",
      "images/PMC8226985-f1-2.png",
      "images/PMC8226985-f2-2.png",
      "images/PMC8226985-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"LC-MS Based Platform Simplifies Access to Metabolomics for Peroxisomal Disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Heatmap illustrating clustering of Zellweger syndrome spectrum patients (ZSS) and controls. Serum from patients analyzed using the Biocrates AbsoluteIDQ p180 kit. Only the 65 components with highest p-value by Student’s t-test are shown. Euclidean distance and Ward clustering were used. Normalized data was used and colormaps were auto scaled. n = 28 (Controls), 17 (ZSS/PEX1). C: Acyl-Carnitine; lysoPC: lysophosphatidylcholine; PC aa: phosphatidylcholines with 2 acyl-linkages; PC ae: phosphatidylcholine with one acyl and one ether linkage; SM: sphingomyelin.\n\nFigure 2: Figure 2. Heatmap illustrating clustering of X-linked adrenoleukodystrophy (X-ALD) patients and controls. Serum from patients analyzed using the Biocrates AbsoluteIDQ p180 kit. Only the 65 components with highest p-value by Student’s t-test are shown. Euclidean distance and Ward clustering were used. Normalized data was used and colormaps were auto scaled. n = 36 (X-ALD/ABCD1), 28 controls. C: Acyl-Carnitine; lysoPC: lysophosphatidylcholine; PC aa: phosphatidylcholines with 2 acyl-linkages; PC ae: phosphatidylcholine with one acyl and one ether linkage; SM: sphingomyelin.\n\nFigure 1: Figure 1. Volcano-plot showing metabolic changes of Zellweger syndrome spectrum patients (ZSS/PEX1) in serum compared to control group. Components with a raw p-value < 0.05 and log2 fold change (log2FC) > 1.0 are displayed in color. lysoPC: lysophosphatidylcholine; PC aa: phosphatidylcholines with two acyl-linkages; PC ae: phosphatidylcholine with one acyl and one ether linkage; SM: sphingomyelin.\n\nFigure 2: Figure 2. (A) Total sum of polyunsaturated acyl-ethyl-phosphatidylcholines (PC ae/plasmalogen candidates) is lower in Zellweger syndrome spectrum patients (ZSS, PEX1) and higher in X-linked adrenoleukodystrophy (X-ALD, ABCD1) patients than in controls. (B) Unsaturated (very) long chain PC ae (total C > 42) are enriched compared to total polyunsaturated PC ae in ZSS and X-ALD patients. Mean ± SEM, n = 36 (X-ALD/ABCD1), 28 (Controls), 17 (ZSS/PEX1). ** p < 0.01, *** p < 0.001 after one-way ANOVA multiple comparisons analysis, Tukey correction.\n\nFigure 3: Figure 3. Phospholipids indicate differential phenotype between Zellweger syndrome spectrum patients (ZSS) and X-linked adrenoleukodystrophy (X-ALD) patients, as well as controls. Mean ± SEM, n = 36 (X-ALD/ABCD1), 28 (Controls), 17 (ZSS/PEX1). ns: not significant, ** p < 0.01, *** p < 0.001 after one-way ANOVA multiple comparisons analysis, Tukey correction. lysoPC: lysophosphatidylcholine; PC aa: phosphatidylcholines with two acyl-linkages; PC ae: phosphatidylcholine with one acyl and one ether linkage; SM: sphingomyelin."
      }
    ]
  },
  {
    "id": "PMC8231983_multi",
    "image": [
      "images/PMC8231983-f1.png",
      "images/PMC8231983-f2.png",
      "images/PMC8231983-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Therapy Development by Genome Editing of Hematopoietic Stem Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Overview of exemplary hereditary disorders potentially curable by editing of HSCs. Genes associated with each disease are indicated in parentheses. The cell types given indicate where protein expression or phenotypic correction are most apparent. Note that combined immunodeficiencies affect B cell function even when presenting with a B+ phenotype. Monocytes and macrophages (MΦ) may also act on cells and for disease correction outside the hematopoietic system (not shown). RBC—red blood cell, NK cell—natural killer cell.\n\nFigure 2: Figure 2. Structure, function and HSC-based application of common gene-editing platforms. ZFNs, TALENs and CRISPR/Cas9 are chimeric proteins comprising customizable sequence-specific DNA binding domain (e.g., zinc finger—ZF, transcription activator-like effector proteins—TALEs or single guide RNA—sgRNA) and a nonspecific nuclease that mediates DNA cleavage (e.g., FokI nuclease in the context of ZFNs and TALENs and Cas9 in the case of CRISPR/Cas9). DNA double-strand breaks generated by ZFNs, TALENs and CRISPR/Cas9 are mainly repaired via two endogenous pathways: (1) error-prone non-homologous end joining (NHEJ), which occurs throughout the cell cycle and corrects breaks through ligation of DNA ends, or (2) by precise homology-directed repair (HDR), in the presence of donor template provided, e.g., as synthetic single-stranded oligodeoxynucleotides (ssODNs), insertion-defective lentiviral vector (IDLV) or adeno-associated virus 6 vector (AAV6) components,. Base editors are chimeric proteins composed of a mutated nuclease, such as Cas9 nickase (nCas9), a catalytic domain capable of deaminating a cytidine or adenine base to induce transition mutations, and a uracil glycosylase inhibitor to prevent base excision repair of the transition event. Prime editors are chimeric proteins exploiting an extended gRNA, termed prime editing guide RNA (pegRNA), and a nCas9 fused to a reverse transcriptase, which nick the DNA to allow pegRNA binding of flanking gRNA to serve as primer of pegRNA-directed reverse transcription of the desired sequence change.\n\nFigure 3: Figure 3. Ex vivo vs. in vivo HSC gene-editing. Steps shown for Ex vivo editing are widely applied for gene editing in in vivo animal models and now also in clinical trials for gene editing. Findings for therapy by gene addition indicate that gene editing, too, might benefit from selective HSC depletion by delivery of antibody-drug conjugates [55] and for suitable disorders, such as FA, from engraftment of corrected cells without conditioning [14]. Steps shown for In vivo editing are in part extrapolated for HSC-targeted approaches of gene addition [56,57,58] and in part based on the latest developments and concepts in the delivery of gene editing components and mRNAs [59,60,61,62]."
      }
    ]
  },
  {
    "id": "PMC8248144_multi",
    "image": [
      "images/PMC8248144-f1.png",
      "images/PMC8248144-f2.png",
      "images/PMC8248144-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Lipid alterations in human frontal cortex in ALS‐FTLD‐TDP43 proteinopathy spectrum are partly related to peroxisome impairment\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. mRNA expression levels of peroxisome‐related genes in frontal cortex area 8 in controls, sALS, sFTLD‐TDP and c9FTLD cases assessed with TaqMan RT‐qPCR assays. (A) Genes implicated in peroxisome biogenesis. (B) Genes coding for redox mechanisms. (C) Genes involved in peroxisomal primary bile acid biosynthesis. (D) Genes related with peroxisome substrate transport. (E) Genes involved in peroxisomal β‐oxidation. Genes linked to plasmalogens biosynthesis (F) and acylcarnitine biosynthesis (G). Data are expressed as the mean values±SEM. The significance level was set at *p < 0.05, **p < 0.01 and ***p < 0.001 versus control group; # p < 0.05, ## p < 0.01 and ### p < 0.001 versus sALS; and $ p < 0.05, $$ p < 0.01 and $$$ p < 0.001 versus sFTLD‐TDP\n\nFigure 2: Figure 2. mRNA expression levels of genes linked to fatty acid metabolism in frontal cortex area 8 in controls, sALS, sFTLD‐TDP and c9FTLD cases assessed with TaqMan RT‐qPCR assays. Data are expressed as the mean values±SEM. The significance level was set at *p < 0.05, **p < 0.01 and ***p < 0.001 versus control group; # p < 0.05, ## p < 0.01 and ### p < 0.001 versus sALS; and $ p < 0.05, $$ p < 0.01 and $$$ p < 0.001 versus sFTLD‐TDP\n\nFigure 3: Figure 3. Multivariate statistics and learning methods reveal a specific lipidome shared by TDP‐43 proteinopathies. (A) Principal component analysis (PCA) 2D plot of samples lipidome. (B–C) Heatmap representation of hierarchical clustering of individual samples according to the top 25 statistically significantly different lipid species between (B) neurological disorders versus controls and (C) among groups of TDP‐43 proteinopathies. (D–E) Heatmap representation of hierarchical clustering of groups according to the identified significantly different lipid species (D) among groups of TDP‐43 proteinopathies and (E) between neurological disorders and controls"
      }
    ]
  },
  {
    "id": "PMC8254661_multi",
    "image": [
      "images/PMC8254661-f1.png",
      "images/PMC8254661-f2.png",
      "images/PMC8254661-f3.png",
      "images/PMC8254661-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Asymptomatic retinal dysfunction in alpha-methylacyl-CoA racemase deficiency\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigree of the three affected siblings.\n\nFigure 2: Figure 2. Sibling 1. A: The appearance of the right eye retina is normal. B: The slit-lamp examination of the right eye shows fine white opacities; these were in both eyes and not visually significant. C: The appearance of the left eye retina is normal. D, E: Macular spectral-domain optical coherence tomography (SD-OCT) of the right and left eyes reveals subtle findings, which are shown with magnification in G: The hyporeflective band (outer segments; OS) normally seen in the parafoveal area between the hyper-reflective layers associated with the inner/outer segment junction (IS/OS) and the RPE/Bruch’s membrane (RPE/BM) complex is not seen; in addition, the RPE/BM layer has a blurred rather than a sharp appearance. F: Short-wave autofluorescence of the right eye is normal. G: Enlargement of right eye SD-OCT with control. H: Short-wave autofluorescence of the left eye is normal.\n\nFigure 3: Figure 3. Siblings 1, 2, 3, and control. A, B, C: Pattern electroretinograms of the right eyes of siblings 1, 2, and 3 show a decreased P50 amplitude (and a decreased downstream N95 amplitude), indicative of macular photoreceptor dysfunction. The left eyes were similar. D: The right eye of a control subject.\n\nFigure 4: Figure 4. Sibling 2. Full-field electroretinography tracings (upper scotopic, bottom photopic) show normal scotopic (rod) function and mildly decreased photopic amplitudes (cone function). Rectangular blocks outline the upper and lower limits of normal values. Stimuli (DA, dark-adopted; LA, light-adapted) were as follows: upper left DA flash 0.01 cd·s·m2, upper right DA flash 3.0 cd·s·m2, lower left LA flash 3.0 cd·s·m2, and lower right LA 0.0 cd·s·m2, flicker at 30 Hz."
      }
    ]
  },
  {
    "id": "PMC8273280_multi",
    "image": [
      "images/PMC8273280-f1.png",
      "images/PMC8273280-f2.png",
      "images/PMC8273280-f3.png",
      "images/PMC8273280-f4.png",
      "images/PMC8273280-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Nicotinamide Riboside Vitamin B3 Mitigated C26 Adenocarcinoma–Induced Cancer Cachexia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Dietary intake of NR as pellet diet to mitigate C26 adenocarcinoma–induced cancer cachexia. (A) Schematic protocol for experiment Balb/c mice were administered with 1 × 107 cells/ml on side of abdomen. Right picture shows representational tumors according to the groups. Tumor growth did not differ according to the groups. (B) Daily measurement of body weight according to the groups. Body weights after 2 weeks were significantly decreased in Group 2 compared to Group 3 and Group 4. (C) Representational gross morphology of thigh including gastrocnemius muscle. Significant atrophy was noted in Group 2 (p < 0.01). Using imaging analysis, individual muscle mass of leg was measured and averaged according to the groups. The mean size and volume of resected C26 adenocarcinoma xenograft after 3 weeks. (D) Mean tumor volume and tumor masses according to the groups. Though different in body weights and general condition, NR administration did not affect either tumor volume or tumor masses. Though omitted, the mean amounts of daily food intake were not differed according to the groups, suggesting that changes in either appetite or food consumption was not differed according to the groups.\n\nFigure 2: Figure 2. Mean sera levels of cachexic cytokines, TNF-α and IL-6 according to the groups (A) TNF-α and (B) IL-6. TNF-α and IL-6 were significantly increased in Group 2, cancer cachexia group. Their levels were significantly decreased in the group treated with NR administration.\n\nFigure 3: Figure 3. MAPKs, NAMPT, and SIRT1 changes according to the group. (A) C26-induced cancer cachexia was associated either ERK and JNK activation, then NR administration significantly inactivated these cachexia-associated MAPKs. (B) NAMPT1 was significantly decreased in cancer cachexia group, suggesting incomplete conversion of NAD+ in cancer cachexia, whereas NR administration maintained NAMPT1 expression. (C) SIRT1 was significantly increased in cancer cachexia group, but not in the NR-treated group, suggesting that NR administration did not affect SIRT1-mediated muscle atrophy.\n\nFigure 4: Figure 4. Changes of muscle-specific UPS ligase atrogin-1 and MuRF-1, Pax 7, PCG-1α, and mitofucin-2. (A) Western blot for atrogin-1 and MuRF-1 according to the groups (I) and UPS ligase according to the groups blotted with ligase (II). (B) Western blot for Pax7 and (C) Western blot for PCG-1α (D) RT-PCR and Western blot for mitofucin-2.\n\nFigure 5: Figure 5. Changes of fat status according to the groups. (A) Epididymal fat mass according to the groups. (B) Western blot for ATGL. (C) Western blot for apoptotic executors according to the groups. (D) Western blot for p-AMPKα, PCG-1α, and Mfn-2."
      }
    ]
  },
  {
    "id": "PMC8299108_multi",
    "image": [
      "images/PMC8299108-f1.png",
      "images/PMC8299108-f2.png",
      "images/PMC8299108-f3.png",
      "images/PMC8299108-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Conserved and Unique Roles of Chaperone-Dependent E3 Ubiquitin Ligase CHIP in Plants\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Amino acid sequence alignment of carboxy-terminal Hsp70-interacting protein (CHIP) ubiquitin E3 ligase proteins from human and plants. The accession numbers of the CHIP proteins used in the alignment are: HsCHIP from Homo sapiens (AAD33400); CrCHIP from Chlamydomonas reinhardtii (Cre.11g479650.t1.2); SmCHIP from Selaginella moellendorffii (Selaginella74711); PpCHIP1 and PpCHIP2 from Physcomitrium patens (Pp3c14_2850V3.7 and Pp3c10_2570V3.5, respectively); OsCHIP from Oryza sativa (LOC_Os05g01460.1); SlCHIP from Solanum lycopersicum (Solyc06g083150.2.1); and AtCHIP from Arabidopsis thaliana (AT3G07370.1). Identical amino acid residues are indicated in green. Highly similar amino acid residues are indicated in pink. The N-terminal tetratricopeptide repeat (TPR) motifs and the C-terminal B-box domain are also indicated.\n\nFigure 2: Figure 2. CHIP-mediated ubiquitination and degradation of misfolded proteins. Heat shock protein (Hsp) 70 and Hsp90 recognize misfolded proteins and can switch their role as molecular chaperones from promoting protein folding/maturation to facilitate protein degradation upon binding to the N-terminal TPR domain of CHIP. Upon Hsp70 or Hsp90, CHIP recruits E2 enzymes of the Ubc4/H5 family to ubiquitinate misfolded proteins, and targets their degradation by the 26S proteasome system.\n\nFigure 3: Figure 3. Roles of CHIP in chloroplast protein quality control (PQC). A majority of chloroplast proteins are nuclear-encoded and synthesized as precursor proteins (pre-proteins) in the cytosol. Import of these precursors proteins into chloroplasts is through the joint action of molecular machines named translocon at the outer envelope membrane (OM) of chloroplast (TOC), and translocon at the inner envelope membrane (OIM) of chloroplast (TIC). CHIP targets the degradation of misfolded and accumulated chloroplast precursor proteins such as light-harvesting complex (LHC) and Rubisco small (RbcS) subunits, which can aggregate and interfere with the chloroplast protein import. CHIP can also target the degradation of accumulated and misfolded ClpP and filamentation temperature sensitive H (FtsH) protease subunit pre-proteins to help maintain the balance among different subunits for assembly into active protease complexes. ClpP and FtsH target the degradation of misfolded, physiologically, and stress-damaged proteins insides the chloroplasts.\n\nFigure 4: Figure 4. Regulation of protein phosphatase 2A (PP2A) by CHIP in plant stress responses. CHIP interacts with and monoubiquitinates the A1 and A3 subunits of PP2A to stimulate its activity. PP2A has regulatory roles in abscisic acid (ABA) signaling and affects ABA responses such as stomatal closure through an association with the sucrose non-fermenting-1-related protein kinase 2- (SnRK2-) type kinases. SnRK2 is inactivated by the interacting 2C-type protein phosphatases (PP2C), and this action of PP2C is inhibited by PYR/PVL ABA receptors in the presence of ABA. PP2A also regulates signaling of other phytohormones such as jasmonic acid and ethylene and affects responses to other stresses such as wounding, cold, and salt stresses."
      }
    ]
  },
  {
    "id": "PMC8313121_multi",
    "image": [
      "images/PMC8313121-f1.png",
      "images/PMC8313121-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Neuromuscular and Neuroendocrinological Features Associated With ZC4H2-Related Arthrogryposis Multiplex Congenita in a Sicilian Family: A Case Report\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Brain MRI of the patient, performed at the age of 8 months. (A,B) Axial T2-weighted images: enlarged posterior horn of lateral ventricles with periventricular white matter thinning (A) and central tegmental tracts hyperintensity (white arrows). (C) Sagittal T1-weighted image and (D) Sagittal T2-DRIVE: Thinning of the corpus callosum and mild pons hypoplasia. No abnormalities recorded in the hypothalamic-pituitary axis.\n\nFigure 2: Figure 2. Muscle biopsy performed at the age of 9 months. (A) Modified Gomori Trichrome staining showing round and small muscle fibers separated by increased connective tissue and containing several cytoplasmic vacuoles. (B) Non-specific esterase (NSE) staining displaying swelled NMJs."
      }
    ]
  },
  {
    "id": "PMC8318916_multi",
    "image": [
      "images/PMC8318916-f1.png",
      "images/PMC8318916-f2.png",
      "images/PMC8318916-f3.png",
      "images/PMC8318916-f4.png",
      "images/PMC8318916-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Roles of the ubiquitin ligase CUL4B and ADP-ribosyltransferase TiPARP in TCDD-induced nuclear export and proteasomal degradation of the transcription factor AHR\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Loss of CUL4B increases AHR protein levels and AHR transcriptional activity in MEF cells.A, WT and MEFCul4b-null cells were treated with solvent dioxane or 0.3, 1, and 10 nM TCDD for 6 h. Left panels, cell homogenates were used for Western blotting (WB) analysis with antibodies against AHR, CUL4B, and β-actin; right bar graph shows densitometry analysis of AHR protein levels from n = 5 experiments using TCDD (1 nM) with 1 or 2 replicates per treatment group for each experiment (p ≤ 0.0001, T versus C for both WT MEF and MEFCul4b-null; p = 0.0004, T (WT MEF) versus T MEFCul4b-null). B, WT MEF and MEFCul4b-null cells treated with TCDD (0.3 nM) for 0, 2, 4, 6, and 15 h were used to prepare homogenates for WB analysis with antibodies indicated in the figure (left panels) or to extract RNA and analyze Cyp1a1 mRNA levels (an index of AHR transcriptional activity) by RT-qPCR (right bar graph); WT versus MEFCul4b-null: p = 0.0024 (T 2 h), p = 0.0005 (T 4 h), p < 0.0001 (T 6 h), p < 0.0001 (T 15 h). C, WB using homogenates of WT MEF and MEFCul4b-null cells (TCDD, 10 nM) with antibodies against ARNT and β-actin. Results are representative of n = 2 independent experiments. D, representative results for WB using homogenates of WT MEF and MEFCul4b-null cells treated with TCDD (1 nM, 6 h) ± MG132 (50 μM). For bar graphs in panels A and B, one-way ANOVA was used to calculate differences among the means and Tukey's honestly significant difference (HSD) test was used as a post hoc test. For this and other figures, bar graphs represent means ± SE with experimental replicates shown as black-filled circles; ∗p ≤ 0.05; ∗∗p ≤ 0.01; ∗∗∗p ≤ 0.001; ∗∗∗∗p ≤ 0.0001. AHR, aryl hydrocarbon receptor; ARNT, aryl hydrocarbon receptor nuclear translocator; C, control (solvent); CUL4B, cullin 4B; MEF, mouse embryonic fibroblast; MEFCul4b-null, MEF cell line in which CUL4B has been knocked out; n.s., not significant; RDU, relative densitometry units; RT-qPCR, real-time quantitative PCR; T, TCDD; T, 2,3,7,8-tetrachlorodibenzo-p-dioxin.\n\nFigure 2: Figure 2. TiPARP leads to TCDD-activated AHR degradation in the absence of CUL4B.A, WB using homogenates of WT MEF and MEFCul4b-null cells transfected with dsRNAs targeting mouse TiPARP (+siTiPARP) or nontargeted control dsRNAs (+scr) and treated with solvent or TCDD (10 nM) for 6 h; antibodies against AHR and β-actin were used. B, RT-qPCR for Cyp1a1 and Tiparp using RNA extracted from WT MEF and MEFCul4b-null cells treated as in panel A (n = 3 independent experiments). C, i, scheme showing the sequence in Tiparp exon 2 targeted by single-guide RNA (sgRNA) used for the CRISPR/Cas9-mediated deletion of Tiparp in MEFCul4b-null cells to abolish TiPARP. ii, panels, WB using homogenates of WT MEF, MEFCul4b-null, and MEFCul4b-null/TiparpK.D. cells treated with solvent or TCDD (1 nM, 6 h) and antibodies for AHR and β-actin. D, RT-qPCR for Cyp1a1 and Cyp1b1 using RNA extracted from WT MEF, MEFCul4b-null, and MEFCul4b-null with TiPARP knocked down cells treated with TCDD (1 nM, 6 h) (n = 3). For bar graphs in panels B and D, one-way ANOVA was used to calculate differences among the means and Tukey's honestly significant difference (HSD) test was used as a post hoc test. +scr, scrambled siRNA; +siTiPARP, silencing TiPARP by siRNA; AHR, aryl hydrocarbon receptor; C, control (solvent); CUL4B, cullin 4B; MEF, mouse embryonic fibroblast; MEFCul4b-null, MEF cell line in which the Cullin 4B gene had been knocked out; n.s., not significant; PAM, protospacer adjacent motif; RDU, relative densitometry units; RT-qPCR, real-time quantitative PCR; T, TCDD, T, 2,3,7,8-tetrachlorodibenzo-p-dioxin; TiPARP, TCDD-inducible poly(ADP-ribose) polymerase; WB, Western blotting.\n\nFigure 3: Figure 3. Effects of loss of CUL4B and TiPARP on viral induced Infb1 mRNA.Left bar graph, RT-qPCR of Infb1 mRNA using RNA extracted from WT MEF, MEFCul4b-null, and MEFCul4b-null/TiparpK.D. transfected with 5'-triphosphate RNA (+3pRNA) or control RNA (−3pRNA) and treated with solvent or TCDD (1 nM, 24 h). Right bar graph, RT-qPCR analysis of Cyp1a1 mRNA in WT MEF cells transfected with ±3pRNA and treated with the solvent or TCDD (1 nM, 24 h). Bar graphs represent the means ± SEM (n = 3). One-way ANOVA was used to calculate differences among the means, and Tukey's honestly significant difference (HSD) test was used as a post hoc test. C, control (solvent); CUL4B, cullin 4B; Infb1, interferon beta 1; MEF, mouse embryonic fibroblast; MEFCul4b-null, MEF cell line in which the Cullin 4B gene had been knocked out; n.s., not significant; RDU, relative densitometry units; RT-qPCR, real-time quantitative PCR; T, TCDD, T, 2,3,7,8-tetrachlorodibenzo-p-dioxin; TiPARP, TCDD-inducible poly(ADP-ribose) polymerase.\n\nFigure 4: Figure 4. Inhibition of the nuclear export of the TCDD-activated AHR by LMB leads to inhibition of AHR degradation and AHR nuclear accumulation; loss of CUL4B and TiPARP leads to TCDD-activated AHR accumulation in the nucleus.A, WB using nuclear- and cytoplasmic-enriched subcellular fractions of WT MEF cells treated with the solvent or TCDD (1 nM) with or without LMB (25, 50, and 100 nM) for 6 h. Antibodies against AHR, histone 3 (H3, nuclear marker), and α/β tubulin (cytoplasmic marker) were used. B, left panels, representative images of immunofluorescence analysis in WT MEF cells treated with the solvent or TCDD (1 nM, 6 h) with or without LMB (50 nM, overnight) using an AHR antibody (FITC, green). DAPI, nuclear marker (blue). Merge, visualization of both AHR and nuclear signals. Right bar graph, means ± SEM (n = 15 cells per treatment group) of AHR fluorescence signal (green). The white scale bar represents 20 μm. C, WB using nuclear- and cytoplasmic-enriched subcellular fractions of WT MEF, MEFCul4b-null, and MEFCul4b-null/TiparpK.D. cells treated with the solvent or TCDD (1 nM, 6 h). Antibodies against AHR, histone 3 (H3, nuclear marker), and α/β tubulin (cytoplasmic marker) were used. D, left panels, representative images of immunofluorescence analysis in MEFCul4b-null/TiparpK.D. treated with the solvent or TCDD (1 nM, 6 h) with or without LMB (50 nM, overnight) using an AHR antibody (FITC, green). DAPI, nuclear marker (blue). Merge, visualization of both AHR and nuclear signals. Right bar graph, means ± SEM (n = 15 cells per treatment group) of AHR fluorescence signal (green). One-way ANOVA was used to calculate differences among the means, and Tukey's honestly significant difference (HSD) test was used as a post hoc test. The white scale bar represents 20 μm. AHR, aryl hydrocarbon receptor; C, control (solvent); CUL4B, cullin 4B; DAPI, 4′,6-diamidino-2-phenylindole; LMB, leptomycin B; MEF, mouse embryonic fibroblast; MEFCul4b-null, MEF cell line in which the Cullin 4B gene had been knocked out; n.s., not significant; RDU, relative densitometry units; T, TCDD, T, 2,3,7,8-tetrachlorodibenzo-p-dioxin; WB, Western blotting.\n\nFigure 5: Figure 5. TiPARP is a major factor promoting AHR nuclear export and degradation after TCDD treatment.A, i, WB using homogenates of WT MEF and MEFTiparpK.D. treated with the solvent (C) or TCDD (1 nM, 6 h). Antibodies against AHR and β-actin were used. The bar graph represents densitometry analysis of WB bands (means ± SEM). ii, representative images of immunofluorescence analysis in MEFTiparpK.D. treated with the solvent or TCDD (1 nM, 6 h) using an AHR antibody (FITC, green). DAPI, nuclear marker (blue). Merge, visualization of both AHR and nuclear signals. The bar graph represents the means ± SEM (n = 15 cells per treatment group) of AHR fluorescence signal (green). The white scale bar represents 20 μm. B, i, representative WB using homogenates of MEFCul4b-null/TiparpK.D. transfected with CUL4B-HA construct (0.5 or 5 μg) and treated with the solvent or TCDD (1 nM, 6 h); antibodies against AHR and β-actin were used. Lower panels, WB using homogenates of WT MEF, MEFCul4b-null, and MEFCul4b-null/TiparpK.D. transfected with the CUL4B-HA construct (0.5 or 5 μg) and treated as above; antibodies against CUL4B and β-actin were used. ii, WB using nuclear- and cytoplasmic-enriched fractions of MEFCul4b-null/TiparpK.D. transfected and treated as described in panel Bi. Antibodies against AHR, CUL4B, and H3 were used. AHR, aryl hydrocarbon receptor; C, control (solvent); CUL4B, cullin 4B; DAPI, 4′,6-diamidino-2-phenylindole; MEF, mouse embryonic fibroblast; MEFCul4b-null, MEF cell line in which the Cullin 4B gene had been knocked out; n.s., not significant; RDU, relative densitometry units; T, TCDD, T, 2,3,7,8-tetrachlorodibenzo-p-dioxin; TiPARP, TCDD-inducible poly(ADP-ribose) polymerase; WB, Western blotting."
      }
    ]
  },
  {
    "id": "PMC8342883_multi",
    "image": [
      "images/PMC8342883-f1.png",
      "images/PMC8342883-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Two Novel HSD17B4 Heterozygous Mutations in Association With D-Bifunctional Protein Deficiency: A Case Report and Literature Review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The patient with severe hypotonia and facial dysmorphism.\n\nFigure 2: Figure 2. Heterozygous mutations of HSD17B4 in the family. (A) Pedigree of family with D-bifunctional protein (DBP) deficiency. X, variant; N, normal. (B) Sanger sequencing validation of HSD17B4 variants identified by exome sequencing. For the mutated gene c.972+1G>T, the sequencing validation is reversed, and the complementary chain of G>T is C>A. Genomic DNA was amplified for sequencing with primers flanking intron 12 and exon 10. Arrow indicates heterozygous mutations. Red X, c.972+1G>T at chr5:119496647–119496647. Blue X, c.727T>A (p.W243R) at chr5:119492112–119492112."
      }
    ]
  },
  {
    "id": "PMC8393694_multi",
    "image": [
      "images/PMC8393694-f1.png",
      "images/PMC8393694-f2.png",
      "images/PMC8393694-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The Targeting of Native Proteins to the Endoplasmic Reticulum-Associated Degradation (ERAD) Pathway: An Expanding Repertoire of Regulated Substrates\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The endoplasmic reticulum-associated degradation (ERAD) pathway consists of four steps. The degradation pathway for a generic integral membrane protein in the ER is shown, and misfolded regions in the lumen, membrane, and cytosol are represented within the polypeptide chain as condensed regions. Recognition: Integral membrane proteins enter the ER concomitant with protein translation on ER-associated ribosomes and with the assistance of the Sec61 translocon. A misfold region in a nascent polypeptide is recognized by cytosolic or lumenal chaperones. Ubiquitination: The ubiquitination machinery—and more specifically an E3 ubiquitin ligases, often along with an E2 ubiquitin conjugating enzyme (not shown)—is next recruited to the misfolded protein, which is then conjugated with a polyubiquitin chain. The chain most commonly contains Lys-48 isopeptide linkages, and a minimum of four ubiquitins is required for proteasome-dependent degradation [14]. Retrotranslocation: The ubiquitinated protein is retrotranslocated through an ER-integrated retrotranslocon. Retrotranslocation requires ATP-dependent extraction mediated by the Cdc48 (in yeast) or p97 (in mammals) complex. The Cdc48/p97 complex also consists of two associated factors, Npl4 and Ufd1, which aid in ubiquitinated substrate capture. Degradation: During and/or after retrotranslocation, the misfolded ubiquitination substrate is degraded by the 26S proteasome into short peptide fragments.\n\nFigure 2: Figure 2. The biosynthetic pathway that leads to the generation of ergosterol (in yeast and fungi) and cholesterol (in higher organisms). The ergosterol and cholesterol biosynthetic pathways are catalyzed by a cascade of enzymes, including those shown as well as others that were not highlighted in the text. Select examples of feedback loops are also shown. Key enzymes regulated by ERAD in yeast (ergosterol biosynthetic pathway, in blue) and mammals (cholesterol biosynthetic pathway, in orange) are also noted. Two factors (ApoB and ACAT2) that act after cholesterol synthesis in mammals are also highlighted. Where studied, select examples of proteins that facilitate substrate degradation by the ERAD pathway and that act on specific enzymes in these pathways are displayed in bold.\n\nFigure 3: Figure 3. Early steps during apolipoprotein B (ApoB) biosynthesis. (A) Under lipid-rich conditions, cholesterol (C), cholesterol esters (CE), phospholipids (PL), and triacylglycerides (TAG) from the ER membrane and from ER lumenal lipid droplets assemble onto ApoB with the assistance of the MTP complex as it is co-translationally translocated through Sec61. (B) Under lipid-poor conditions, co-translational translocation through Sec61 slows but translation continues, depositing large polypeptide segments of ApoB in the cytoplasm. The depicted chaperones, as well as the gp78 ubiquitin ligase, associate with and facilitate ApoB targeting the proteasome."
      }
    ]
  },
  {
    "id": "PMC8395492_multi",
    "image": [
      "images/PMC8395492-f1.png",
      "images/PMC8395492-f2.png",
      "images/PMC8395492-f3.png",
      "images/PMC8395492-f4.png",
      "images/PMC8395492-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Glycosphingolipids with Very Long-Chain Fatty Acids Accumulate in Fibroblasts from Adrenoleukodystrophy Patients\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Structures of glycosphingolipids and sphingomyelin analyzed in this study. Hex; hexsosylceramide, HexNAc; N-acetylhexosamine, NeuAC; N-acetylneuraminic acid, and R; alkyl chain group.\n\nFigure 2: Figure 2. Amounts of Hex2Cer (LacCer) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific LacCer species as pmol/mg protein, calculated using the concentration of N-C18:0-CD3-Gb3 as an internal standard. Each species was quantified and classified according to the number of carbon atoms and double bonds, e.g., the C18:1 fatty acid species contains 17 carbon atoms and 1 double bond in the R (alkyl chain) group. * p < 0.05, ** p < 0.01, and *** p < 0.001.\n\nFigure 3: Figure 3. Amounts of NueAC-Hex2Cer (GM3) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific GM3 species as pmol/mg protein, calculated using the concentration of N-C18:0-CD3-Gb3 as an internal standard. Each species was quantified and classified according to the number of carbon atoms and double bonds, e.g., the C18:1 fatty acid species contains 17 carbon atoms and 1 double bond in the R (alkyl chain) group. * p < 0.05, ** p < 0.01, *** p < 0.001, and **** p < 0.0001.\n\nFigure 4: Figure 4. Amounts of NeuAc-HexNAc-Hex2Cer (GM2) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific GM2 species as pmol/mg protein, calculated using the concentration of N-C18:0-CD3-Gb3 as an internal standard. Each species was quantified and classified according to the number of carbon atoms and double bonds, e.g., the C18:1 fatty acid species contains 17 carbon atoms and 1 double bond in the R (alkyl chain) group. * p < 0.05.\n\nFigure 5: Figure 5. Amounts of NeuAc-HexNAc-Hex3Cer (GM1) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific GM1 species as pmol/mg protein, calculated using the concentration of N-C18:0-CD3-Gb3 as an internal standard. Each species was quantified and classified according to the number of carbon atoms and double bonds, e.g., the C16:1 fatty acid species contains 15 carbon atoms and 1 double bond in the R (alkyl chain) group."
      }
    ]
  },
  {
    "id": "PMC8395492_multi_2",
    "image": [
      "images/PMC8395492-f6.png",
      "images/PMC8395492-f7.png",
      "images/PMC8395492-f8.png",
      "images/PMC8395492-f9.png",
      "images/PMC8395492-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Glycosphingolipids with Very Long-Chain Fatty Acids Accumulate in Fibroblasts from Adrenoleukodystrophy Patients\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Amounts of NeuAc2-Hex2Cer (GD3) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific GD3 species as pmol/mg protein, calculated using the concentration of N-C18:0-CD3-Gb3 as an internal standard. Each species was quantified and classified according to the number of carbon atoms and double bonds, e.g., the C16:1 fatty acid species contains 15 carbon atoms and 1 double bond in the R (alkyl chain) group.\n\nFigure 7: Figure 7. Amounts of Hex3Cer (Gb3) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific Gb3 species as pmol/mg protein, calculated using the concentration of N-C18:0-CD3-Gb3 as an internal standard. Each species was quantified and classified according to the number of carbon atoms and double bonds, e.g., the C18:1 fatty acid species contains 17 carbon atoms and 1 double bond in the R (alkyl chain) group. * p < 0.05, ** p < 0.01, *** p < 0.001, and **** p < 0.0001.\n\nFigure 8: Figure 8. Amounts of HexNAc-Hex3Cer (Gb4) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific Gb4 species as pmol/mg protein, calculated using the concentration of N-C18:0-CD3-Gb3 as an internal standard. Each species was quantified and classified according to the number of carbon atoms and double bonds, e.g., the C18:1 fatty acid species contains 17 carbon atoms and 1 double bond in the R (alkyl chain) group. * p < 0.05 and ** p < 0.01.\n\nFigure 9: Figure 9. Fragmentation patterns of GalCer (A) and SM (B) in positive ion mode. Both GalCer and SM generate a product ion with 264 m/z. MRM traces for transitions from m/z 728.6 to 548.4 for GalCer d18:1/C18:0 and from m/z 729.6 to 184 for SM d18:1/C18:1. Assignment of LC–MS/MS spectra at 730 m/z for a mixture of GalCer d18:1/C18:0 and SM d18:1/C18:1 with collision energy (CE) of 30 V (C) and 70 V (D).\n\nFigure 10: Figure 10. Retention times of GalCer d18:1/C18:0 and SM d18:1/C18:1."
      }
    ]
  },
  {
    "id": "PMC8395492_multi_3",
    "image": [
      "images/PMC8395492-f11.png",
      "images/PMC8395492-f12.png",
      "images/PMC8395492-f13.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Glycosphingolipids with Very Long-Chain Fatty Acids Accumulate in Fibroblasts from Adrenoleukodystrophy Patients\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Amounts of HexCer species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amount of each specific HexCer species as pmol/mg protein, calculated using the concentration of N-C16:0-CD3-glucosylceramide as an internal standard. Each species was quantified and classified according to the total number of carbon atoms and double bonds in the ceramide moiety, e.g., the C34:1 species contains 33 carbon atoms and 1 double bond in the fatty acid and long-chain base moiety. * p < 0.05 and *** p < 0.001.\n\nFigure 12: Figure 12. Amounts of sphingomyelin (SM) species in fibroblasts from X-ALD patients. The Y-axis of each graph shows the amounts of specific SM species as pmol/mg protein, calculated using the concentration of N-C16:0-D31-D-erythro-sphingosylphosphorylcholine as an internal standard. Each species was quantified and classified according to the total number of carbon atoms and double bonds in the ceramide moiety, e.g., the C34:1 species contains 33 carbon atoms and 1 double bond in the fatty acid and long-chain base moiety. * p < 0.05 and ** p < 0.01.\n\nFigure 13: Figure 13. Quantity of each glycosphingolipid (GSL) and sphingomyelin (SM) species in X-ALD fibroblasts and comparison of the amounts of each GSL and SM species among groups. LacCer, GM3, GM2, GD3, GB3, and Gb4 are shown in (A), and HexCer and SM are shown in (B). The mean quantity of each species in fibroblasts from X-ALD patients is represented as pmol/mg protein with a color code. Each pmol/mg protein value was calculated using the concentration of N-C18:0-CD3-Gb3 for LacCer, GM3, GM2, GD3, GB3, and Gb4 (A), N-C16:0-CD3-glucosylceramide for HexCer, and N-C16:0-D31-D-erythro-sphingosylphosphorylcholine for SM (B) as an internal standard. Each GSL and SM species that was significantly more abundant in CCALD or AMN samples relative to control samples is indicated as * and #, respectively. Each GSL and SM species that was significantly more abundant in CCALD samples relative to AMN samples is indicated as $."
      }
    ]
  },
  {
    "id": "PMC8395936_multi",
    "image": [
      "images/PMC8395936-f1.png",
      "images/PMC8395936-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Advanced Diagnostic System and Introduction of Newborn Screening of Adrenoleukodystrophy and Peroxisomal Disorders in Japan\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Diagnostic flowchart for adrenoleukodystrophy and peroxisomal disorders at Gifu University [8]. * collaborated with Hamamatsu University School of Medicine [7].\n\nFigure 2: Figure 2. Follow-up flowchart for patients with pre-symptomatic adrenoleukodystrophy [8]. * start MRI follow-up at 12 to 18 months of age [13]."
      }
    ]
  },
  {
    "id": "PMC8396561_multi",
    "image": [
      "images/PMC8396561-f1.png",
      "images/PMC8396561-f2.png",
      "images/PMC8396561-f3.png",
      "images/PMC8396561-f4.png",
      "images/PMC8396561-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mechanisms Mediating the Regulation of Peroxisomal Fatty Acid Beta-Oxidation by PPARα\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomal β-oxidation pathways, including different enzymes and transporters. Saturated or unsaturated very-long-chain fatty acids (sVLCFA or uVLCFA) are imported by the solute ABC-transporters ABCD1 and ABCD2, respectively, into peroxisome, where they are transformed into their acyl-CoAs by one of the peroxisomal acyl-CoA synthetases (ACSVL5 for uVLCFA, and ACSVL1 for uVLCFA). The long-chain dicarboxylic acids (LCDCA), originating from the endoplasmic reticulum ω-oxidation, are imported by ABCD3 and activated to their acyl-CoA thioesters (DCAcyl-CoA) by an unknown acyl-CoA synthetase (ACSL?). The reactions that are catalyzed by ACSVL and ACSL use CoASH and hydrolyze ATP to AMP and pyrophosphate to activate VLCFA or LCDCA molecules, giving acyl-CoA. Acyl-CoA oxidase 1 (ACOX1) is the first flavoenzyme in the straight-chain β-oxidation system, oxidizing sVLCFA, uVLCFA, or LCDCA to their enoyl-CoA derivatives. The second enzyme metabolizing sVLCFA and uVLCFA is the D-bifunctional protein (also called MFP2 or HSD4B17), while the dicarboxylic enoyl-CoA are taken by the L-bifunctional enzyme (also called MFP1 or EHHADH). The thiolytic cleavage is catalyzed by one of the two peroxisomal thiolases (TH: thiolase/ACAA1/2 or SCPx: sterol carrier protein-x). After several rounds of β-oxidation, the peroxisomal system gives shortened acyl-CoA derivatives as hexanoyl- or octanoyl-CoA, and one molecule of acetyl-CoA/round. Both shortened acyl-CoA and acetyl-CoA can be hydrolyzed by acyl-CoA thioesterases 3 or 4 (ACOT3/4) to CoASH, while free fatty acid and acetate are exported by the pore-forming protein PXMP2 (or PMP22) to the cytosol. However, acetyl-CoA and acyl-CoA derivatives can also be transformed to acetyl-carnitine or acyl-carnitine by carnitine acetyl- and carnitine octanoyl transferases (CRAT and CROT), respectively, and then exported by PXMP2 to the cytosol. β-oxidation of DCAcyl-CoAs leads to the production of succinyl-CoA, hydrolyzed to succinate and CoASH by ACOT4, and shipped outside by peroxisome PXMP2. Bile acid intermediates, dihydroxycholestanoic acid (DHCA) and trihydroxycholestanoic acid (THCA), imported by ABCD3 transporter, are beta-oxidized by ACOX2, DBP and SCPx enzymes, leading to the formation of choloyl-CoA and chenodeoxycholoyl-CoA, which are conjugated to glycine or taurine by the bile acid-CoA: amino acid N- acyltransferase (BAAT) and then exported by PXMP2. D/THC-CoA indicate DHCA and THCA co-enzyme A thioesters.\n\nFigure 2: Figure 2. Sequence logo and consensus matrix of the PPARα/RXRα PPRE consensus sequence from MA1148.1 Jaspar matrix [38]. (A) Sequence logo of the MA1148.1 Jaspar matrix, presenting the conservation of nucleotides from multiple alignments of 1000 PPARα/RXRα PPRE sequences. Adenosine (A), cytidine (C), guanosine (G), and thymidine (T) nucleotides are respectively green-, blue-, yellow-, and red-colored, and the relative size of the letters represents their frequency in the consensus. The total height of a logo position corresponds to the degree of conservation in the corresponding multiple sequence alignment. (B) A table representing the percentage of the four bases for each position of the consensus. The color gradient code highlights the percentage of conservation of bases from blue to red for the whole table.\n\nFigure 3: Figure 3. Multiple alignments of PPRE sequences, identified in peroxisomal gene promoters, and experimentally proved to be regulated through PPARα binding. Adenosine (A), cytidine (C), guanosine (G) and thymidine (T) nucleotides are respectively green-, blue-, yellow- and red-colored.\n\nFigure 4: Figure 4. Schematic view of PPARα structure and domain function, with phosphorylation and cofactor binding sites. From the left N-terminus to the right C-terminus of the PPARα protein, (A) domain structure of the PPARα protein with the ligand-independent activation function-1 (AF-1) domain or A/B domain shown in purple, the DNA-binding domain (DBD) or C domain shown in blue with two zinc finger-like motifs, the hinge region (HR) or D domain shown in white, and the ligand-binding domain (LBD) or E domain together with the activation function 2 (AF-2) or F domain shown in green. Phosphorylation sites are labeled with yellow stars (6, 12, 21, 179, 230) amino acids, the corepressor site is marked with a red half-sphere, and the coactivator binding site is shown with a green ring. The panels on top show the number of amino acid residues. (B) Structural function of A/B, C, D, and E/F domains, respectively.\n\nFigure 5: Figure 5. Diagram of different types and classes of PPARα ligands. The natural ligands type encompasses endogenous natural ligands (fatty acids [28,80,81,82], eicosanoids [31,83,84,85], phospholipids [75,86], fatty-acid amide [87] and endocannabinoid-like molecules [77], and exogenous natural ligands [30,88] (polyphenol flavonoids, isoflavonoids, monoterpenes, sesquiterpenes, diterpenes, triterpenes and steroids, carotenoids, coumarins, ligans, and tannins). The synthetic ligands type includes various classes of synthetic agonists [28,31,62,67,69,88,89,90,91] with various activation and binding modes (single [88,92], dual [28,91,93,94] and pan agonists [28,92]), and synthetic antagonists [89,90,95]. Abbreviations: 8-HEPE: 8-hydroxyeicosapentaenoic acid, 12-HETE: 12-hydroxyeicosatetraenoic acid, 8S-HETE: 8 (S)-hydroxyeicosatetraenoic acids, 16:0/18:1-GPC: phosphatidylcholine(1-palmitoyl-2-oleoyl-sn-glycerol-3-phosphocholine), EPA: eicosapentaenoic acid (20:5), ETYA: eicosatetraynoic acid, HEX: hexadecanamide, HMB: 3-hydroxy-(2,2)-dimethyl butyrate, OCT:9-octadecenamide, OEA: oleoyl-ethanolamide, OxPAPC: oxidized 1-palmitoyl-2-arachidonoyl-sn-glycero-3-phosphocholine, PEA: palmitoyl-ethanolamine."
      }
    ]
  },
  {
    "id": "PMC8396561_multi_2",
    "image": [
      "images/PMC8396561-f6.png",
      "images/PMC8396561-f7.png",
      "images/PMC8396561-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Mechanisms Mediating the Regulation of Peroxisomal Fatty Acid Beta-Oxidation by PPARα\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Scheme of heterodimer PPARα/RXRα, located on a PPRE DNA region. The graphic displays two parts: part (A), the silent state, and part (B), the active state. Part (A). In the absence of the ligand, PPARα interacts with transcriptional corepressors (NCoR, SMRT, NRTR-P-1) by recognizing the AF2 region. The same process is at the RXR, where AF2 interacts with RIP140 as RXRα corepressor [169]. Due to the chromatin condensed state, the heterodimer cannot bind the PPRE properly. Part (B). In the presence of a PPARα ligand, either a long-chain or very-long-chain polyunsaturated fatty acid, leukotriene LTB4, fibrate or other chemicals [170], and a 9-cis retinoic acid as RXRα ligand, an exchange corepressor/coactivator is made by NCoEX, which suppresses the repressive of corepressor state by ubiquitinylation-inducing degradation by the proteasome system. The fixation of a ligand induces an allosteric LBD conformational change of AF2, allowing the recruitment of coactivators, either NCoR1, p300/CBP, or SRC1 for PPARα, and p120 and NCoPR for RXRα [171]. The CBP-dependent HAT activity induces the remodeling of chromatin and allows the PPARα/RXRα heterodimer to bind to PPRE correctly, then activates the Pol II transcription complex and triggers the transcription of lipid metabolism-encoding genes. Some post-translational modifications of PPARα regulate its activity [172,173]. For instance, phosphorylation stimulates PPARα transcriptional activity [174]. The HNF4α transcription factor recognizes a similar response element as the PPRE and interplay with PPARα [175]. A comparable mechanism has been reported with the Coup-TF transcription factor. While several works consider PGC-1α [176] as an important coregulator of PPARα, it seems to be more specific for PPAR γ. The 15(S)-HETE, 15-hydroxyicosatetraenoic acid, family of arachidonic acid metabolites; 9-cisRA, retinoic acid cis conformation in carbon 9; AF1, activating domain 1; AF2, activating domain 2; CBP, CREBP binding protein; CoPRs, COPR1 and COPR2 as corepressors of PPAR and RXR, respectively; COUP-TF, chicken ovalbumin upstream promoter transcription factor; CTBP-2, C-terminal binding protein-2; DBD, DNA binding domain; HAT, histone acetyl-transferase; HD, hinge domain; HNF-4α, hepatic nuclear factor 4 α; HDAC, histone de-acetyl transferase; LBD, ligand binding domain; LTB4, leukotrien B4; MBP, mono butyl phthalate; MEHP, mono ethyl hexyl phthalate; NCoA1, nuclear receptor coactivator 1; NCoEX, nuclear receptor corepressor Excit; NCoR1, nuclear receptor corepressor 1; NRTP-1, nuclear repressor transcription factor; p120, protein 120 kDa; p300, protein 300 kDa; Pol II, RNA polymerase class II; PGC-1αPPAR γ co-activator-1α; PPRE, peroxisome proliferator response element; PRIP/RAP250, PPAR interacting-protein methyl transferase; PUFA (LC &VLC), polyunsaturated fatty acids (long-chain or very-long-chain); RIP140 receptor interacting protein corepressor; SMRT, silencing mediator of retinoid and thyroid receptors; SRC1, steroid receptor coactivator-1.\n\nFigure 7: Figure 7. Interaction of PPARα-RXRα heterodimer with corepressor complex (A) or coactivator complex (B). (A) The corepressor complex, including Sin 3, NCoR/SMRT, and HDAC proteins, is recruited to an unliganded PPARα-RXRα heterodimer, so there is no transcription of the PPARα-target genes. (B) in the presence of PPARα-ligand, the PPARα-RXRα heterodimer exhibits a conformational change, leading to the dissociation of the corepressor complex, the recruitment of coactivator proteins, and the binding of PPARα to the peroxisome proliferator response element (PPRE). Different subcomplex modules participate in chromatin remodeling, through the acetylation (SRCs, p300) and the methylation (CARM1) of nucleosomes. Mediator components interact with PPARα and promote the recruitment of the basal transcription factors (TFs) to establish a connection with the RNA polymerase II to transcription of PPARα-target genes.\n\nFigure 8: Figure 8. PPARα-dependent regulation of peroxisomal fatty acid b-oxidation in rat liver through adiponectin signaling. Adiponectin: a hormone produced by adipose tissue that plays a role in lipid and glucose metabolism regulation; AdipoR, adiponectin receptor; APPL1, an adaptor protein containing a PH domain, PTB domain, and leucine zipper motif 1, plays a central role as the main contributing factor in the adiponectin and insulin signaling; AMPK, AMP kinase; PGC1- α, PPAR γ coactivator1α; PPRE, peroxisome proliferator-activated receptor; RNA Pol II, RNA-polymerase II; ACOX1, acyl-CoA oxidase 1; MFP2, multifunctional protein 2; thiolase B, 3-ketoacyl-CoA thiolase B; VLCFA, very-long-chain fatty acid."
      }
    ]
  },
  {
    "id": "PMC8424520_multi",
    "image": [
      "images/PMC8424520-f1.png",
      "images/PMC8424520-f2.png",
      "images/PMC8424520-f3.png",
      "images/PMC8424520-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Feedback repression of PPARα signaling by Let-7 microRNA\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A–D) Fold change of let-7 miRNA precursors in PPARα-activated Ppara+/+ and PparaΔHep mouse livers measured by qRT-PCR. Individual let-7 miRNA precursor expression in livers treated with Wy-14,643 (A) or overnight fasting (C). Precursor abundance ratios in mice treated with Wy-14,643 (B) or overnight fasting (D). Data are normalized to Actb expression and presented as mean ± SEM (n = 4 mice per group; *p < 0.05, #p < 0.01, §p < 0.001) (E) Time course of mature let-7 miRNA abundance in wild-type mouse liver after Wy-14,643 administration measured by qRT-PCR. Data are normalized to U6 expression and presented as mean ± SEM (n = 4 mice per group; *p < 0.05, **p < 0.01, ***p < 0.001)\n\nFigure 2: Figure 2. (A) let7b/c2+/+ and let7b/c2ΔHep mice after HFD feeding for 8 weeks. (B) Body weight alterations of let7b/c2+/+ and let7b/c2ΔHep mice during HFD feeding. (C) Oil red O and H&E staining of let7b/c2+/+ and let7b/c2ΔHep liver sections after HFD feeding. Bars, 100 μM. (D–F) Tissue weight ratio of lean (D), fat (E), and liver (F) to total body weight for let7b/c2+/+ and let7b/c2ΔHep mice after HFD feeding. (G) Biochemical analysis for serum triglycerides (TGs) in let7b/c2+/+ and let7b/c2ΔHep mice after HFD feeding. (H) EGFP fluorescence in mouse primary hepatocytes infected with either EGFP or let-7 sponge AAV vectors after 5 days in culture. Bars, 300 μm. (I) Body weight alterations in wild-type mice infected with EGFP or let-7 sponge expressing AAV and then placed on HFD for 8 weeks. (J–L) Tissue weight ratio of lean (J), fat (K), and liver (L) to total body weight for wild-type mice infected with EGFP or let-7 sponge expressing AAV then placed on HFD for 8 weeks. (M) Biochemical analyses for serum TG concentration in EGFP and let-7 sponge AAV-infected mice after HFD feeding. Data are presented as mean ± SEM (n = 4–5 mice per group; *p < 0.05, **p < 0.01)\n\nFigure 3: Figure 3. (A) Heatmap of PPARα target genes identified by differential gene expression analysis of RNA-seq data from let7b/c2+/+ and let7b/c2ΔHep livers after HFD feeding. (B and C) mRNA analysis by qRT-PCR of PPARα target genes involved in fatty acid oxidation and cell proliferation (B) and lipid accumulation and glucose metabolism (C) in HFD-fed let7b/c2+/+ and let7b/c2ΔHep livers. (D) Western blot analysis for PPARα target genes in HFD-fed let7b/c2+/+ and let7b/c2ΔHep liver lysates. (E) Western blot analysis of PPARα and RXRα protein expression in nuclear fractions isolated from let7b/c2+/+ and let7b/c2ΔHep hepatocytes. (F–H) Western blot analysis of RXRα and the densiometric quantification in whole-liver lysates from let7b/c2ΔHep- mice (F), let-7 sponge expressing AAVinflected mice (G), and pre-let-7c-1--AAVinfected mice (H). Data are presented as mean ± SEM (n = 4–5 mice per group; *p < 0.05, **p < 0.01, ***p < 0.001\n\nFigure 4: Figure 4. (A) Predicted let-7 miRNA binding sites in Rnf8 mRNA. (B–F) Western blot analysis and densitometric quantification of RNF8 protein (B, D, and F) and qRT-PCR of Rnf8 mRNA (C and E) in let7b/c2+/+ and let7b/c2ΔHep (B and C); EGFP and let-7 sponge AAV-transduced (D and E); EGFP and pre-let-7c-1 AAV-transduced (F) livers treated with HFD feeding. (G) 3′ UTR reporter assays in HepG2 cells transfected with Rnf8 wild-type or mutant 3′ UTR reporter constructs and a let-7c mimic expression vector. (H and I) Western blot analysis (H) and densitometric quantification (I) of RXRα expression in Rxra- and Rnf8-transfected Hepa-1 cells. (J and K) Fold change of Rnf8 (J) and Rxra (K) mRNA by qRT-PCR analysis in Rxra- and Rnf8-transfected Hepa-1 cells. (L) Western blot analysis and the densitometric quantification of RXRα in Rxra- and Rnf8-transfected Hepa-1 cells treated with the proteasome inhibitor MG-132. (M) Ubiquitination assays for Rxra- and Rnf8-transfected and MG-132-treated Hepa-1 cells. RXRα was immunoprecipitated and polyubiquitin detected by anti-ubiquitin antibody. RXRα expression was confirmed in whole-cell lysate as input. (N) Scheme of 3-step inhibition for PPARα/RXRα pathway that the current study demonstrates."
      }
    ]
  },
  {
    "id": "PMC8429733_multi",
    "image": [
      "images/PMC8429733-f1.png",
      "images/PMC8429733-f2.png",
      "images/PMC8429733-f3.png",
      "images/PMC8429733-f4.png",
      "images/PMC8429733-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Oral intake of rice overexpressing ubiquitin ligase inhibitory pentapeptide prevents atrophy in denervated skeletal muscle\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Chromatograms show apical to basolateral transepithelial transport of 1 mM Asp-Gly-pTyr-Met-Pro (a) and Asp-Gly-Tyr-Met-Pro (b) in Caco-2 cell monolayers over 60 min. Samples from the basolateral side at 15, 30, 45, and 60 min were analyzed using LC–TOF/MS with [M + H]+ at m/z 662.1625 for Asp-Gly-pTyr-Met-Pro and 582.2228 for Asp-Gly-Tyr-Met-Pro. (c) Dephosphorylation of Asp-Gly-pTyr-Met-Pro monitored in basolateral solution after 60 min of transport by extracting ions with m/z 582.2228 corresponding to Asp-Gly-Tyr-Met-Pro ions.\n\nFigure 2: Figure 2. Effects of 10 mM Gly-Sar on transport of 1 mM Asp-Gly-pTyr-Met-Pro (a) and Asp-Gly-Tyr-Met-Pro (b) across Caco-2 cell monolayers for 60 min. Basolateral peptide concentrations were determined after 60 min by LC–TOF/MS. Effects of cytochalasin D on transport of 1 mM Asp-Gly-pTyr-Met-Pro (c) and Asp-Gly-Tyr-Met-Pro (d) across Caco-2 cell monolayers for 60 min. Caco-2 cell monolayers were incubated with or without cytochalasin D (0.5 μg/mL) for 30 min. Basolateral peptide concentrations were determined by LC–TOF/MS. Values are expressed as means ± SEM, n = 4–6. *P < 0.05, **P < 0.01. NS, not significant.\n\nFigure 3: Figure 3. a Absorption of Asp-Gly-Tyr-Met-Pro in 8-week-old Sprague-Dawley rats. Stacked intensity-time chromatograms of Asp-Gly-Tyr-Met-Pro with [M + H]+ of m/z 582.2228 and 50 pmol/mL of labeled internal standard (IS) Asp-Gly(13C2; 15N)-Tyr-Met-Pro ([M + H]+: m/z 585.2228) (insert) created by sampling plasma at 0, 15, 30, 45, and 60 min from tail veins of rats dosed with 100 mg/kg BW Asp-Gly-Tyr-Met-Pro. b Time course of appearance of Asp-Gly-Tyr-Met-Pro in plasma of rats orally administered with 100 mg/kg BW determined by LC–TOF/MS. Data are expressed as means ± SEM (n = 5). c, d Extracted ions corresponding to those of possible metabolites, Gly-Tyr-Met-Pro ([M + H]+: m/z 467.1959) and Met-Pro ([M + H]+: m/z 247.1111) were detected in rat plasma at 30 min after administration.\n\nFigure 4: Figure 4. Chromatograms of chymotrypsin-digested glutelin-derived peptides from nontransgenic (non-Tg; a) or Cblin-enriched (CbR; b) rice, and synthetic standard peptide Gln-Asp-Gly-Tyr-Met-Pro-Trp (c). Fraction at 27.0 min was collected and further analyzed by LC–TOF/MS while monitoring [M + 2H]2+ of m/z 448.6840 for Gln-Asp-Gly-Tyr-Met-Pro-Trp (d–f). Arrows indicate MS signals corresponding to RT (21.4 min, upper panel) and m/z ([M + 2H]2+: m/z 448.6840, lower panel) of standard Gln-Asp-Gly-Tyr-Met-Pro-Trp. AU, arbitrary units; ND, not detected.\n\nFigure 5: Figure 5. Body weight (a) and food consumption (b) during experimental period in mice fed with diets containing non-transgenic (non-Tg; unfilled circles) or Cblin-supplemented (CbR; filled circles) rice. Results are shown as means ± SEM (n = 5–6 per group). Expression of IRS1 protein (c) and Mafbx (d) and Murf1 (e) genes associated with muscle atrophy in sciatic denervated or sham-operated gastrocnemius muscles of mice fed with diets containing non-Tg or CbR. Results are shown as means ± SEM (n = 5−6 per group). *P < 0.05 (S vs. D). †P < 0.01 (non-Tg vs. CbR). D, denervated; S, sham-operated."
      }
    ]
  },
  {
    "id": "PMC8439061_multi",
    "image": [
      "images/PMC8439061-f1.png",
      "images/PMC8439061-f2.png",
      "images/PMC8439061-f3.png",
      "images/PMC8439061-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Cholbam® and Zellweger spectrum disorders: treatment implementation and management\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Disrupted bile acid synthesis in patients with ZSD and CA mechanism of action. CA, cholic acid; CDCA, chenodeoxycholic acid; CYP7A1, cytochrome P450 7A; LRH-1, liver receptor homolog 1; SHP-1, small heterodimeric partner 1. A Disrupted bile acid synthesis in patients with ZSD. In the absence of functional peroxisomes, there is a deficiency of primary C24-bile acids, which subsequently results in the disruption of the negative feedback loop (dotted lines) that maintains bile acid homeostasis under normal physiological conditions. Increased transcription of CYP7A1 causes a build-up of C27-bile acid intermediates, which have been shown to be cytotoxic. Additionally, deficiency in primary bile acids causes impaired bile flow and cholestasis, as well as reduced absorption of dietary fats and fat-soluble vitamins. B CA mechanism of action in patients with ZSD. Introduction of exogenous CA restores levels of the primary bile acids, improves bile flow and absorption, and reactivates the negative feedback loop, which, via repression of CYP7A1, reduces levels of the C27-bile acid intermediates. Adapted from Gonzales et al. [13], with permission from Elsevier\n\nFigure 2: Figure 2. Klouwer et al. [20]: impact of cholic acid therapy on bile acid levels, and liver chemistry. A, B Tukey box plots showing the effect of oral cholic acid (CA) on plasma 3α,7α- dihydroxycholestanoic acid (DHCA) and 3α,7α,12α-trihydroxycholestanoic acid (THCA) after 1, 3, 9, 15 and 21 months of treatment. The control reference range for THCA is < 0.05–0.1 μmol/L and levels of DHCA are undetectable (< 0.05 μmol/L) in control individuals. C, D Tukey box plots showing the levels of plasma DHCA and THCA at baseline, study end (after 9 or 21 months of CA treatment) and at follow-up (6–12 months after discontinuation of CA). Only the levels of patients for which follow-up values were available are shown (n = 16). E, F Graphs showing the individual courses of alanine transaminase (ALT) and aspartate transaminase (AST) levels during oral CA treatment (n = 22). The patients with liver cirrhosis are depicted in red. The upper control reference ranges of ALT (40 U/L) and AST (45 U/L) are indicated by the dotted lines. *P<0.05, **P<0.01, ***P<0.005, ****P<0.001, ns, not significant. Reprinted from Klouwer et al. [20]; with permission from John Wiley and Sons. This is an open access article distributed under the terms of the Creative Commons CC BY license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited\n\nFigure 3: Figure 3. Heubi et al. [19]: impact of cholic acid therapy on bile acid levels, liver chemistry, and height and weight. ALT, alanine transaminase; AST aspartate transaminase; NS, not significant; SED, single enzyme defect; SEM, standard erroor of the mean; ULN, upper limit of normal. A Impact of cholic acid treatment on urinary bile acid excretion patients with Zellweger spectrum disorder (ZSD) (n = 27)—worst-to-best analysis, modified intent-to-treat (mITT) population. B Impact of cholic acid treatment on liver chemistries in patients with ZSD (n = 27)—worst-to-best analysis, mITT population. C Mean height and weight percentiles from pretreatment to post-treatment in the mITT population (N = 70), worst-to-best analysis. Numbers in bars represent absolute percentiles for each group. Reprinted from Heubi et al. [19]. This is an open access article distributed under the terms of the Creative Commons CCBY-NC-ND license, where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal\n\nFigure 4: Figure 4. Heubi et al. [21]: impact of cholic acid therapy on bile acid levels, liver chemistry, and height and weight. ALT, alanine transaminase, AST, aspartate transaminase. A Urinary bile acids at baseline, worst postbaseline response, and best postbaseline response (total population). B Height and body weight: baseline, worst postbaseline response, and best postbaseline response (total population). Change from baseline over time in C serum alanine aminotransferase and D serum aspartate aminotransferase. In panels A, C, and D, numbers within the bars indicate n values. Reprinted from Heubi and Setchell [21]. This is an open access article distributed under the terms of the Creative Commons CCBY-NC-ND license, where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal"
      }
    ]
  },
  {
    "id": "PMC8452888_multi",
    "image": [
      "images/PMC8452888-f1.png",
      "images/PMC8452888-f2.png",
      "images/PMC8452888-f3.png",
      "images/PMC8452888-f4.png",
      "images/PMC8452888-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"PAQR9 regulates hepatic ketogenesis and fatty acid oxidation during fasting by modulating protein stability of PPARα\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Paqr9 expression in the liver is regulated by fasting.A. A volcano plot showing RNA-Seq results of liver fasted for 24 hours from GEO dataset GSE92502. Downregulated or upregulated genes were divided by log2–fold change >1 or < −1 with P-value < 0.01. Red dots for upregulated genes and green dots for downregulated genes. The right panel depicts the top 10 most significantly changed genes (except for those involved in lipid metabolism and oxidation pathways). B.Paqr9 mRNA level in the liver after 48 hours fasting and refeeding or peritoneal injection with 10% glucose solution for 3 hours (n = 3 for control and n = 4 for other groups). C.Paqr9 mRNA level in Hep3B and HepG2 cells under starvation condition for different times. D.Paqr9 mRNA level in Hep3B cells treated with 50 nM rapamycin or 1 mM AICAR for different times. E. PPARγ motif analysis and potential binding sites at the Paqr9 promoter. F. Dual-luciferase reporter assay. Different lengths of putative Paqr9 promoter were cloned into luciferase-containing plasmid and transiently expressed in the Hep3B cells along with PPARγ-expressing plasmid as indicated. Relative luciferase activity was calculated by dividing firefly luciferase activity by renilla activity. G. ChIP-qPCR with different regions of Paqr9 promoter. P1 to P5 were five different segments covering the region of −2,500 bp to the transcription start site (TSS) region. Both input and immunoprecipitation results are shown. The expression of Flag-tagged PPARγ is confirmed by Western blotting (right panel). H.Paqr9 mRNA level in Hep3B with overexpression of PPARγ. The mRNA expression results were relative to β-actin in B and relative to α-tubulin in C, D, and H. All the quantitative data are shown as mean ± S.E.M., ∗ for P < 0.05 and ∗∗∗ for P < 0.001.\n\nFigure 2: Figure 2. Deletion of Paqr9 does not alter metabolic phenotype under normal chow feeding.A. The mRNA level of Paqr9 in different tissues of C57BL/6 mice relative to β-actin (n = 4 for each tissue). B. Generation and identification of the Paqr9−/− mouse. The left panel depicts the scheme of the Paqr9−/− mouse. Note that Paqr9 gene only has one exon. The right panel shows genotyping results using primers denoted by arrows in the left panel. C. Body weight of male wild type (WT) and Paqr9−/− mice at 10 weeks old (n = 6 for each group). D. Body composition of the mice. E. Blood glucose of the mice at feeding or fasting for 16 hours. F. Oxygen consumption and carbon dioxide production of the mice during a 24-hour period. G. Respiratory exchange ratio (RER) of the mice. H. Movement of the mice on the X and Z axes. I. Blood levels of triglyceride (TG), total cholesterol (TC), HDL cholesterol, and LDL cholesterol of the mice. All data were analyzed with Student's t-test. All the quantitative data are shown as mean ± S.E.M.\n\nFigure 3: Figure 3. Deletion of Paqr9 reduces hepatic ketogenesis and fatty acid oxidation in vivo and in vitro.A. Concentration of β-hydroxybutyrate (β-HB) in serum of the male wild type (WT) and Paqr9−/− mice after fasting for 24 hours (n = 6 for WT and n = 7 for Paqr9−/− mice). B. The mRNA levels of ketogenic genes in the liver of the mice, as in A. C. The mRNA levels of ketone degradation genes in the skeletal muscle of the mice, as in A. D. Concentration of β-HB in culture medium of primary hepatocytes isolated from the mice. The cells were treated with 500 μM sodium caprylate for 24 hours before measurement. E. Efficiency of Paqr9 knockdown in Hep3B cells transfected with shRNA-containing plasmids. F. Concentration of β-HB in culture medium of the cells, as in E. G. The mRNA levels of fatty acid β-oxidation genes in the livers of the mice after fasting for 48 hours. H. Representative images of Oil Red O staining of the livers from the mice after fasting for 24-hour fasting. I. Triglyceride level in the livers of the mice under feeding or fasting for 24 hours. J. Representative images of Oil Red O staining of primary hepatocytes isolated from the mice. The hepatocytes were treated with 1 g/L glucose and 500 μM sodium caprylate for 36 hours. All data were analyzed with Student's t-test. All the quantitative data are shown as mean ± S.E.M., ∗ for P < 0.05, ∗∗∗ for P < 0.001, and n. s. for non-significant.\n\nFigure 4: Figure 4. PAQR9 protects PPARα from degradation by reducing PPARα ubiquitination.A. The mRNA levels of representative transcription factors in the liver of the mice after fasting for 24 hours (n = 6 for each group). B. Western blotting to detect transcription factors in the livers of the mice as in A. Quantitation of the data is shown in the right panel. C. Analysis of protein stability of PPARα with PPARα knockdown. Hep3B cells with or without PPARα knockdown were transiently transfected with Flag-tagged PPARα and then treated with CHX (100 μg/mL) for various times, followed by immunoblotting with the antibodies as indicated. Quantitation of the immunoblotting results from three independent experiments is shown in the right panel. D. Analysis of protein stability of PPARα with Paqr9 overexpression. Hep3B cells were transiently transfected with Flag-tagged PPARα and GFP-tagged PAQR9 as indicated and treated with CHX (100 μg/mL) for various times. Quantitation of the immunoblotting from three independent experiments is shown in the right panel. E. Poly-ubiquitination of PPARα in Hep3B cells with Paqr9 knockdown. The cells were pretreated with MG132 (10 μM) for 6 hours, followed by immunoprecipitation and immunoblotting with the antibodies as indicated. F. Poly-ubiquitination of PPARα in Hep3B cells with Paqr9 overexpression. The cells were transiently transfected with Myc-tagged Paqr9 and treated with MG132 (10 μM) for 6 hours, followed by immunoprecipitation (IP) and immunoblotting with the antibodies as indicated. All the quantitative data are shown as mean ± S.E.M., ∗ for P < 0.05 and ∗∗ for P < 0.01.\n\nFigure 5: Figure 5. PAQR9 reduces PPARα ubiquitination by competing with its interaction with HUWE1.A-B. Co-immunoprecipitation assay to analyze interaction of PPARα with PAQR9. HEK293T cells were transfected with the plasmids as indicated, followed by immunoprecipitation (IP) and immunoblotting with the antibodies as indicated. C. Localization of PAQR9 and PPARα in HeLa cells. The cells were transiently transfected with the plasmids as indicated and used in immunofluorescent staining. The nucleus was stained with Hoechst 33,342. The right panel shows plots of signal intensity (y axis) against distance in mm (x axis) to indicate occurrence of overlaps between the red and green channels for PAQR9/PPARα co-expressing cells. D. Co-immunoprecipitation assay to analyze interaction of PPARα and PAQR9 with HUWE1. Hep3B cells were transfected with the plasmids as indicated, followed by IP and immunoblotting. E. The interaction of PPARα with HUWE1 is enhanced by Paqr9 knockdown. Hep3B cells with or without Paqr9 knockdown were transiently transfected with GFP-fused PAQR9, followed by IP and immunoblotting. F. The interaction of PPARα with HUWE1 is reduced by Paqr9 overexpression. Hep3B cells were transiently transfected with different amount of GFP-fused PAQR9, followed by IP and immunoblotting. G. Identification of the region of PPARα that interacts with HUWE1. Different segments of PPARα were overexpressed in Hep3B cells, followed by IP and immunoblotting. H. The interaction of the 174–278aa segment of PPARα with HUWE1 is reduced by Paqr9 overexpression. Hep3B cells were transiently transfected with GFP-fused PAQR9 and Flag-tagged PPARα segment, followed by IP and immunoblotting."
      }
    ]
  },
  {
    "id": "PMC8490386_multi",
    "image": [
      "images/PMC8490386-f1.png",
      "images/PMC8490386-f2.png",
      "images/PMC8490386-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"NBS1 I171V variant underlies individual differences in chromosomal radiosensitivity within human populations\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generation of NBS1 I171V knock-in HCT-116 cells. (a) Structure of human NBS1 protein. NBS1 contains FHA and BRCT1/2 domains at the N terminus and several DNA repair protein-binding regions at the C terminus. FHA and BRCT1/2 domains are involved in the IR-induced nuclear foci with phosphoproteins such as γ-H2AX. NBS1 I171V is located in the BRCT1 domain. (b) Sanger sequencing confirmed NBS1 I171V heterozygosity in ovarian cancer patient 18. (c) Targeting strategy for NBS1 I171V knock-in using the CRISPR/Cas9 system. Blue bases indicate silent mutations. (d–f) Sanger sequencing of NBS1+/+ parental HCT116 cell (d), NBS1+/+-edited HCT116 cell clone 1 (e), NBS1I171V/I171V-edited HCT116 cell clone 1 (f). A single base substitution of the NBS1 I171V variant and a silent Sca I site are indicated by yellow boxes.\n\nFigure 2: Figure 2. Chromosomal radiosensitivity of NBS1 I171V edited HCT116 cell clones. (a) Western blotting analysis data showing expression levels of NBS1 and MRE11 protein in NBS1 I171V edited HCT116 cell clones. Full-length gel is presented in Supplementary Fig. 5. GAPDH antibody was used as a loading control. The intensity of NBS1 and MRE11 bands was normalized to that of GAPDH and shown as a percentage, regarding the score of NBS1+/+ parent cell clones as 100%. (b) RT-PCR data showing mRNA expression levels of MRE11 in NBS1 I171V edited HCT116 cell clones. GAPDH was used as a control. (mean ± SEM; no significant change in each t-test parameter; n = 4) (c) Survival fractions for NBS1 I171V edited HCT116 cell clones for 11 days after irradiation (mean ± SD based on averages from triplicate samples; t-test; n = 3). (d–f) Metafer MN Search images showing the cytokinesis-blocked NBS1 I171V edited HCT116 cells stained with DAPI. Arrowheads indicate MN. BN cell without MN of NBS1+/+ clone 1 (d); BN cell with one MN of NBS1I171V/I171V clone 1 (e); BN cell with three MN of NBS1−/− clone 1 (f). (g) Percentage of IR-induced MN formation in NBS1 I171V edited HCT116 cell clones (mean ± SEM; t-test; n = 3; > 1000 BN cells). (h–j) Representative metaphase after 4 Gy irradiation of NBS1 I171V edited HCT116 cells. Remarkable aberrations are enlarged. Arrows indicate chromosomal breakages. Metaphase without chromosomal breakages of NBS1+/+ clone 1 (h), metaphase with one chromosomal breakage of NBS1I171V/I171V clone 1 (i), and metaphase with two chromosomal breakages of NBS1−/− clone 1 (j). (k) Frequency of IR-induced chromosomal aberration in NBS1 I171V edited HCT116 cell clones (mean ± SEM; t-test; n = 3; > 50 cells).\n\nFigure 3: Figure 3. Radiation-induced chromosomal instability of Nbs1 I171V edited MEF clones. (a) Western blotting analysis data showing the expression levels of Nbs1 protein in Nbs1 I171V edited MEF clones. Full-length gel is presented in Supplementary Fig. 5. The GAPDH antibody was used as a loading control. The intensity of Nbs1 bands was normalized to that of GAPDH and shown as a percentage, regarding the score of Nbs1+/+ clone 1 as 100%. (b–d) Metafer MN Search images showing the cytokinesis-blocked Nbs1 I171V edited MEFs stained with DAPI. Arrowheads indicate MN. Nbs1+/+-BN cell without MN (b), Nbs1I171V/+-BN cell with one MN (c), Nbs1I171V/I171V-BN cell with three MN (d). (e) Percentage of IR-induced MN formation in Nbs1 I171V edited MEF clones (mean ± SEM; t-test; n = 3; > 1000 BN cells). (f, g) Representative metaphase of Nbs1 I171V-edited MEFs after 4 Gy irradiation. Remarkable aberrations are enlarged. Arrows indicate chromosomal breakages. (i) Frequency of IR-induced chromosomal aberrations in Nbs1 I171V edited MEF clones (mean ± SEM; t-test; n = 3; > 50 cells)."
      }
    ]
  },
  {
    "id": "PMC8497303_multi",
    "image": [
      "images/PMC8497303-f1.png",
      "images/PMC8497303-f2.png",
      "images/PMC8497303-f3.png",
      "images/PMC8497303-f4.png",
      "images/PMC8497303-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"W246G Mutant ELOVL4 Impairs Synaptic Plasticity in Parallel and Climbing Fibers and Causes Motor Defects in a Rat Model of SCA34\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Knock-in of the W246G ELOVL4 mutation, physical differences, and ELOVL4 expression in WT, HET, and MUT rats. A Cartoon depicting the overall structure and functional domains of ELOVL4 and the location of the W246G ELOVL4 mutation. B The W246G ELOVL4 mutation does not affect the size of female rats at any age between 2 months and 6 months of age. Male MUT rats are significantly smaller than age-matched WT and HET rats from 3 months of age (females, 2 months: n = 26 WT, 22 HET, 24 MUT; 3 months: n = 17 WT, 13 HET, 17 MUT; 4 months: n = 9 WT, 9 HET, 10 MUT; 6 months: n = 17 WT, 14 HET, 10 MUT. Males, 2 months: n = 5 WT, 8 HET, 4 MUT; 3 months: n = 5 WT, 8 HET, 4 MUT; 4 months: n = 4 WT, 7 HET, 3 MUT; 6 months: n = 7 WT, 10 HET, 4 MUT. Data are shown as mean ± SD. 1-way ANOVA + Bonferroni post-hoc test. *p< 0.05; **p<0.01; ***p<0.001; ****p<0.0001). C Western blot of cerebellum from WT, HET, and MUT rats (n=3 each). D Quantification of ELOVL4 levels (normalized to Actin loading control) showed no differences across genotypes. Analysis performed on samples from 3 different rats of each genotype (data are shown as mean ± SEM. Statistical analysis by 1-way ANOVA with Tukey’s post-hoc test)\n\nFigure 2: Figure 2. The W246G ELOVL4 mutation impaired motor function assessed by rotarod test. (A–D) Female HET and MUT rats showed consistent impairment of motor performance on the rotarod test compared to age-matched WT female rats from 2 to 6 months of age. Distance traveled variable shown. (E) Data from panels (A–D) re-plotted to show performance over time (2 months: n = 26 WT, 22 HET, 24 MUT. 3 months: n = 17 WT, 13 HET, 17 MUT. 4 months: n = 9 WT, 9 HET, 10 MUT. 6 months: n = 17 WT, 14 HET, 10 MUT; data are shown as mean ± SEM. 1-way ANOVA + Bonferroni post-hoc test. *p< 0.05; **p<0.01; ***p<0.001)\n\nFigure 3: Figure 3. Gross cerebellar structure and morphometric analysis. (A–I) Gross cerebellar structure in WT, HET, and MUT rats at postnatal day 45 (P45), 3 months, and 6 months of age is comparable. Scale bar = 1 mm for each row. (J–L) Lamination and cellular distribution in the cerebellar cortex is normal in WT, HET, and MUT rats. Six months of age shown, scale bar = 100 μm. (M–T) Morphometric analysis of cortical layer thickness in WT, HET, and MUT rats indicates no substantial reduction in any cortical layer at 3 months or 6 months, although a significant difference in Purkinje cell layer width between WT and MUT rats was noted in lobule 3 at 6 months (3 months: n = 3–5 animals/genotype. 6 months: n = 4–8 animals/genotype. Data are shown as mean ± SEM. 1-way ANOVA with Tukey’s post-hoc test. *p< 0.05). (U, V) Linear density of Purkinje cells shows no difference among WT, HET, and MUT rats (3 months: n = 5 animals/genotype. 6 months: n = 7 animals/genotype. Data are shown as mean ± SEM. 1-way ANOVA with Tukey’s post-hoc test)\n\nFigure 4: Figure 4. Distribution of ELOVL4 and cell- and synapse-specific markers is normal in WT, HET, and MUT rat cerebellum. (A–C) Distribution of ELOVL4 in the cerebellar cortex of WT, HET, and MUT rats is comparable. Labeling is present in granule cells in the granule cell layer (GCL), Purkinje cells (arrows) in the Purkinje cell layer (PCL), and inhibitory neurons in the molecular layer (ML). (D–F) Purkinje cells identified by labeling for calbindin are organized in a monolayer in the Purkinje cell layer (PCL) and show similar structure in the WT, HET, and MUT cerebellum. (G–I) Distribution of NeuN, a marker for granule cells in the granule cell layer (GCL), is comparable across all genotypes. A small population of NeuN-positive cells is also present in the molecular layer (ML), as appropriate. (J–L) Distribution of Vesicular Glutamate Transporter 1 (VGluT1), a marker for excitatory parallel fiber and mossy fiber synapses, is comparable across all genotypes. (M–O) Distribution of synaptotagmin 2 (Syt2), a marker for inhibitory synapses, is comparable across all genotypes. Scale bars = 200 μm for each row\n\nFigure 5: Figure 5. Distribution of VGluT2 and mGluR1 in WT, HET, and MUT rat cerebellum. (A–C) Distribution of VGluT2, a marker for climbing fiber synapses, is comparable in the cerebellar cortex of WT, HET, and MUT rats. Labeling is present in climbing fiber synapses onto Purkinje cell dendrites in the molecular layer (ML) and in the synaptic glomeruli of the granule cell layer (GCL). PCL, Purkinje cell layer. (D–F) Distribution of mGluR1 is comparable in the WT, HET, and MUT cerebellum. PCL, Purkinje cell layer. Scale bars = 100 μm for panels (A–C); 200 μm for panels (D–F)"
      }
    ]
  },
  {
    "id": "PMC8497303_multi_2",
    "image": [
      "images/PMC8497303-f6.png",
      "images/PMC8497303-f7.png",
      "images/PMC8497303-f8.png",
      "images/PMC8497303-f9.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"W246G Mutant ELOVL4 Impairs Synaptic Plasticity in Parallel and Climbing Fibers and Causes Motor Defects in a Rat Model of SCA34\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The W246G ELOVL4 mutation does not significantly alter levels of synaptic proteins in the WT, HET, and MUT cerebellum. Immunoblots for A VGluT1, B VGluT2, C GluA1, D GluA2, E PSD-95, F Syt 2, and G GAD-65 and GAD-67 are shown along with their quantification (normalized to loading control: Actin or GAPDH). Quantitation was performed on samples obtained from 3 different rats of each genotype (data are shown as mean ± SEM. Statistical analysis by 1-way ANOVA with Tukey’s post-hoc test)\n\nFigure 7: Figure 7. Decreased amplitude and frequency domain shift of spontaneous activity in MUT cerebellar slices. A Representative plots of spontaneous network activity in WT (left panel) and MUT (right panel) cerebellar slices recorded from 61 locations (X axis = time, Y axis = number of events, Z axis = recording electrode #). WT and KI slices show very low activity (upper panels) or high activity (lower panels). Inset shows a picture of the cerebellar slice on the hexagonal multi-electrode array. B No difference in the average frequency of spontaneous network activity in the cerebellum of WT (n=7 slices from 5 rats) and MUT (n=8 slices from 6 rats). Note an increased average frequency of positive spikes and reduced frequency of negative spikes in the MUT cerebellum (shown as mean ± SEM, analysis by Mann-Whitney test. *p<0.05). C Representative traces from spontaneous events of WT (left panel) and MUT (right panel). Note higher amplitude in positive spikes (lower panel) and negative spikes (upper panel) of the WT traces. An extremely large positive spike in WT and a complex spike in MUT are shown in middle panel traces. Scale bars y=20 μV, x=1 ms. D Analysis of spontaneous event amplitudes. Note the decreased amplitude of positive spikes (left panel, *p<0.05, Wilcoxon signed rank test) and decreased amplitude of negative spikes (right panel, ***p<0.001, Wilcoxon signed rank test) in the MUT compared with WT cerebellum. E Resting spontaneous activity in WT and MUT slices. Distribution of interspike interval (ISI) in 5 ms bins from WT (upper; n=7) and MUT (lower; n=8) slices during 10-min recordings. F Cumulative histogram of ISI analysis of events with 2 s or less time between them. Data shown in E re-analyzed using 1-ms bins. MUT slices show-reduced activity at high frequencies (above 20 Hz) compared with WT slices (p<0.0001, Mann-Whitney test). G Cumulative histogram of ISI of spontaneous activity in PF–PC connections in WT (n=4) and MUT slices (n=5) analyzed using 1-ms bins (p<0.0001, Mann-Whitney test)\n\nFigure 8: Figure 8. LTP at PF-Purkinje cell synapse is impaired in MUT rats. A LTP induced in WT rats by stimulation of the PFs in the molecular layer at 1 Hz for 10 min induces LTP in WT rat cerebellar slices (green circles, n = 14 slices from 6 rats), but not in cerebellar slices from MUT rats (red triangles, n = 16 slices from 6 rats). Each data point represents the average of two successive test responses. The vertical gray bar indicates the period of 1-Hz stimulation. Typical traces show EPSPs before (black line) and after (green line for WT, red line for MUT) 1-Hz stimulation in slices from WT (left) and MUT (right) rats (data are shown as mean ± SEM; ***p < 0.001, two-way repeated measures ANOVA with Bonferroni post hoc test [RM ANOVA]). B Baseline and potentiated synaptic strength in PF-PC synapses. Graph depicts amplitude of fEPSP evoked from WT slices (green, n=14 from 6 rats) and MUT slices (red, n=13 from 6 rats) by stepwise increase in the stimulus from 5 to 100 μA. WT slices show increased amplitudes after 1 h LTP (upper left panel, ***p < 0.001, two-way RM ANOVA). MUT slices show no increase in amplitudes after 1-h LTP (upper right panel, ns). Comparison of amplitudes between WT and MUT slices before LTP (lower left panel, *p < 0.05, two-way RM ANOVA) and after LTP (lower right panel, **p < 0.01, two-way RM ANOVA). C Changes in the synaptic responses during the 1-Hz stimulation trains. Normalized fEPSP amplitude in WT slices (green circles, n=14 slices from 6 rats) increased significantly compared with MUT slices (red triangles, n=14 slices from 6 rats). Each data point represents one fEPSP response as recorded every second and normalized to the amplitude of first response (data are shown as mean ± SEM, **p < 0.01, two-way ANOVA, last 100 s). D fEPSP average amplitude of the first response in WT and MUT slices (same data set as panel C; shown as mean ± SEM, ns, Mann-Whitney test). E Ratio of average amplitude of the last five responses (#596–600) divided by the average of the first five responses (#1–5) in WT and MUT slices (data are shown as mean ± SEM, ***p < 0.001, Mann-Whitney test)\n\nFigure 9: Figure 9. LTD at CF-PC synapses is impaired in MUT rats. A Stimulating the CFs in the granule cell layer at 1 Hz for 10 min induces LTD in WT cerebellar slices (green circles, n = 10 slices from 5 rats), but not in cerebellar slices from MUT rats (red triangles, n = 14 slices from 6 rats). Each data point represents the average of two successive test responses. The vertical gray bar indicates the period of 1-Hz stimulation. Representative traces depict fEPSPs before (black line) and after (green line for WT and red line for MUT) application of the 1-Hz LTD protocol in WT and MUT slices (left and right inset, respectively) (data are shown as mean ± SEM; **p < 0.01, ***p < 0.001, two-way repeated measures ANOVA with Bonferroni post hoc test [RM ANOVA]). B Baseline and depressed synaptic strength in CF-PC synapses. Graph depicts amplitude of fEPSP evoked from WT slices (green, n=8 from 5 rats) and MUT slices (red, n=12 from 6 rats) by stepwise increase in the stimulus from 5 to 100 μA. Note the decreased baseline CF synaptic strength and lack of LTD in MUT slices after 1-Hz stimulus. WT slices show decreased amplitudes after 1-h LTD (upper left panel, *p < 0.05, two-way RM ANOVA). MUT slices show no changes in amplitudes after 1-h LTD (upper right panel, ns). Comparison of amplitudes between WT and MUT slices before LTD (lower left panel, ***p < 0.001, two-way RM ANOVA) and after LTD (lower left panel, *p<0.05, two-way RM ANOVA). C Changes in the synaptic responses during the 1-Hz stimulation trains. fEPSP amplitude in WT slices (green circles, n=10 slices from 5 rats) did not change significantly compared with MUT slices (red triangles, n=12 slices from 6 rats). Each data point represents one fEPSP response as recorded every second and normalized to the amplitude of first response (data are shown as mean ± SEM, ns, two-way ANOVA, last 100 s). D Average amplitude of the first fEPSP response in WT and MUT slices (data are shown as mean ± SEM, ns, Mann-Whitney test). E Ratio of average amplitude of the last five fEPSP responses (#596–600) divided by the average of the first five responses (#1–5) in WT and MUT slices (data are shown as mean ± SEM, ns, Mann-Whitney test)"
      }
    ]
  },
  {
    "id": "PMC8534235_multi",
    "image": [
      "images/PMC8534235-f1.png",
      "images/PMC8534235-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The Many Potential Fates of Non-Canonical Protein Substrates Subject to NEDDylation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Canonical and non-canonical NEDD8 substrates. Canonical NEDDylation refers to the post-translational modification of the Cullin family of proteins with NEDD8. NEDD8 is first activated by binding to the E1 NEDD8 activating enzyme, a process which can be blocked by the small molecule MLN4924. NEDD8 is then transferred via E2 and E3 enzymes to the Cullin protein, which in turn activates the CRL allowing it to transfer ubiquitin molecules to its designated substrate, leading to the substrate degradation. Non-canonical NEDDylation occurs when NEDD8 is covalently attached to protein substrates other than Cullin molecules. Following NEDDylation these proteins can adopt different fates, such as increased stability, increased enzymatic activity, changes in subcellular location, and degradation. Examples of substrates subject to these outcomes are listed. The list presented here is by no means exhaustive.\n\nFigure 2: Figure 2. The TCGA Pan-Cancer was used to analyze 11,072 tumor samples for expression levels of UBA1, NEDD8, and UBC. Samples were ranked based upon UBA1 expression and visualized using Xena. (A) Visualization of total samples analyzed. (B) Visualization of 63 samples with the lowest level of UBA1 expression."
      }
    ]
  },
  {
    "id": "PMC8534408_multi",
    "image": [
      "images/PMC8534408-f1.png",
      "images/PMC8534408-f2.png",
      "images/PMC8534408-f3.png",
      "images/PMC8534408-f4.png",
      "images/PMC8534408-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The SZT2 Interactome Unravels New Functions of the KICSTOR Complex\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Establishment of the SZT2 interactome. (A) Graphical representation of workflow and choice of conditions. Published SZT2 binding partners associate with the protein independently of the physiological conditions, and we assume other interactors might also do so. In addition, SZT2 might bind to certain components under specific physiological conditions, e.g., starved (STA) and stimulated (STI). (B) Methodological workflow to decipher the SZT2 interactome under catabolic and anabolic conditions via affinity purification coupled to mass spectrometry. Image created with BioRender.com. (C) Quality control of the affinity purification fractions. An aliquot of specific fractions collected along the purification protocol was analyzed by Western blotting against HA; L, Lysate; FT, Flow through; E, Eluate; and B, Beads. (D) Lysates of a representative starved (STA) or starved and stimulated (STI) biological replicate were run on SDS-PAGE and analyzed by immunoblotting.\n\nFigure 2: Figure 2. Characterization of the SZT2 interactome. (A) Principal component analysis (PCA) of the abundancies of all proteins identified in the interactome of SZT2 under starvation (light violet) or stimulation (violet) and of the GFP control (black). (B) Zoom in of volcano plot of all identified proteins interacting with SZT2 or the GFP control (see Figure S2A for whole volcano plot). The gray color scale depicts the number of proteins that have the same abundance and p-value. Proteins significantly binding to SZT2 have a p-value below 0.05 and an abundance ratio of 5 over the GFP control (within dotted lines). Representative components of KICSTOR and GATOR1 complexes are depicted in blue labeled with their protein names. (C) Summary of Top9 processes (KEGG pathway and WikiPathway) associated with proteins binding with high affinity to SZT2. Relevant processes were selected based on their −log10 (p-value). Maps of (D) autophagy, (E) cilia-associated terms, (F) neurological disorder-associated terms, with the depiction of proteins, which have a significantly higher affinity to bind to SZT2 than to the GFP control. The node size correlates with the number of mapped proteins per term and the node color with the significance of this term.\n\nFigure 3: Figure 3. Interactome analysis revealed SZT2 interactors that preferentially bind upon starvation or stimulation. (A) Volcano plot of all identified proteins interacting with SZT2 with the abundancy ratio of interacting proteins upon starvation versus stimulation. The gray color scale depicts the number of proteins that have the same abundance and p-value. Proteins binding with a higher affinity to SZT2 upon starvation have a p-value below 0.05 and an abundance ratio of 1.5 over proteins binding upon stimulation (within right dotted lines). Map of (B) autophagy, (C) cilia-associated and (D) neurological disorder-associated terms, depicting identified proteins found in the SZT2 interactome. The color code shows the log2-abundance ratio of the single proteins with proteins binding SZT2 upon starvation colored in blue and upon stimulation colored in yellow.\n\nFigure 4: Figure 4. Characterization of the SZT2 KO cells under amino acids starvation and stimulation conditions. (A) Wild type and SZT2 KO cells were starved for amino acids for 1 h followed or not by restimulation for 20 min. The corresponding lysates were run on SDS-PAGE and analyzed by immunoblotting. SZT2 was detected on a separate membrane with IQGAP1 detection as a loading control. Data are representative of three independent experiments. (B) Relative quantification of the expression of selected proteins detected in A. Graphics display mean + SEM. (C) Wild type and SZT2 KO cells were treated with either Chloroquine or Bafilomycin for 6 h. Obtained lysates were run on SDS-PAGE and analyzed by immunoblotting. Data are representative of three independent experiments. (D) Relative quantification of expression of LC3B-II versus total LC3B. Graphics display mean + SEM.\n\nFigure 5: Figure 5. Torin and Rapamycin reduce the mTORC1 hyperactivity seen in SZT2 KO cells. (A) Wild type and SZT2 KO cells were starved for amino acids for 1 h followed or not by restimulation for 20 min. In addition, cells were treated with either Rapamycin or Torin during starvation. Obtained lysates were separated by SDS-PAGE and the presence of the indicated proteins determined by immunoblotting. Data are representative of three independent experiments. (B) Analysis of the regulation of selected proteins detected in (A). Graphics display the mean + SEM. (C) Control and SZT2 KO cells were starved for amino acids for 3 h and restimulated for another 3 h prior to harvesting. The cell diameter of three biological replicates per cell line and condition were analyzed. Graphics represent the cell size of at least 45,000 viable cells per condition plotted against their relative number ± standard dev. (D) Quantification of the peak cell diameter of each cell line analyzed in (C). Graphic represents the peak diameter in the different conditions ± standard dev. The statistical significance was analyzed using a nonparametric Kruskal–Wallis test and subsequent Dunn’s test with the p-value depicted in italics."
      }
    ]
  },
  {
    "id": "PMC8534408_multi_2",
    "image": [
      "images/PMC8534408-f6.png",
      "images/PMC8534408-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The SZT2 Interactome Unravels New Functions of the KICSTOR Complex\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Ciliogenesis in SZT2 KO cells. (A) Control Hek293 Flp-In™ T-Rex™ cells and SZT2 KO cl.63 were either left untreated or starved for growth factors for 72 h to induce ciliogenesis. Cells were then fixed and stained with antibodies against acetylated tubulin (green) and PCM1 (red). The nucleus of the cells was counterstained with Hoechst. Arrow head points to a midbody that is also enriched in acetylated tubulin. Arrows indicate cilia. Scale bar 10 µm. (B) Quantifications of (A) representing the percentage of ciliated cells found in each cell line and condition ± standard dev. Statistical significance was calculated using a nonparametric Kruskal–Wallis test with subsequent Dunn’s test and the italic numbers represent the p-value.\n\nFigure 7: Figure 7. Ciliogenesis in MDCK SZT2 bulk KO cells. (A) Control MDCK cells and SZT2 bulk KO were grown to confluency and then either left untreated or starved for growth factors for 48 h. Cells were then fixed and stained with antibodies against acetylated tubulin (green) and Phalloidin (red). The nucleus of the cells was counterstained with Hoechst. Scale bar 10 µm. (B) Quantifications of (A) representing the percentage of ciliated cells found in each cell line and condition ± standard dev. More than 2000 cells per condition and replicate were counted. Statistical significance was calculated using a nonparametric Kruskal–Wallis test with subsequent Dunn’s test and the italic numbers represent the p-value. (C) Scanning EM of controls and MDCK SZT2 bulk KO cells. Three representative cilia from each cell line are shown. Arrow indicates shrunken cilia. Scale bar 2 µm."
      }
    ]
  },
  {
    "id": "PMC8549703_multi",
    "image": [
      "images/PMC8549703-f1.png",
      "images/PMC8549703-f2.png",
      "images/PMC8549703-f3.png",
      "images/PMC8549703-f4.png",
      "images/PMC8549703-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 Ubiquitin Ligase NEDD4-1 Mediates Temozolomide-Resistant Glioblastoma through PTEN Attenuation and Redox Imbalance in Nrf2–HO-1 Axis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. NEDD4-1 is associated with worse prognosis in glioblastoma. (A) NEDD4-1 expression evaluated across normal and glioblastoma datasets. (B) NEDD4-1 expression levels were evaluated from TCGA-GBM samples are grouped based on tumor and non-tumor counterparts. (C) Representative immunohistochemistry staining of clinical glioblastoma patient tissues. (D) Q-Score value comparison between non-tumor and tumor part taken from glioblastoma clinical tissue samples. Kaplan-Meier survival analysis of glioblastoma patients expressing NEDD4-1 was determined using gene correlation analysis by R2: Genomics Analysis and Visualization Platform (http://r2.amc.nl (accessed on 2 July 2021)) of the (E) French (n = 273) and (F) Kawaguchi (n = 50) datasets. *** p < 0.001.\n\nFigure 2: Figure 2. NEDD4-1 is highly expressed in temozolomide-resistant patient-derived GBM cell lines. (A) NEDD4-1/PTEN/AKT signaling pathway protein expression survey in glioblastoma cell lines. (B) Viability assay performed using SRB assay showing established TMZ-resistant cell lines, U87MGR and U251R, increased resilience against temozolomide treatment. (C) Tumorsphere formation assay demonstrating the higher potential of TMZ-resistant cell lines to form tumorspheres compared to their chemo-responsive counterpart. (D) Differential expression of NEDD4-1 and PTEN expression in adherent (adh) and tumorsphere (sph) cells in TMZ-responsive and TMZ-resistant U87MG and U251 cell lines. (E) Colony formation assay depicting higher clonogenicity of TMZ-resistant cell lines compared to their TMZ-responsive counterpart. Graph bars are mean ± SEM of 3 independent experiments. *** p < 0.001.\n\nFigure 3: Figure 3. miR-3129-5p and miR-199b-3p regulate NEDD4-1 expression in GBM cell line. (A) The top 10 miRNAs with strongest correlation to NEDD4-1 according to the Targetscan database were evaluated for their expression level in U87MG and U87MG R cell lines to find the two most downregulated miRNAs. (B) Evaluation of Ki-67 immunofluorescence staining intensity of U87MG R cell line transfected with miR-3129-5p and miR-199b-3p mimics. DAPI staining (blue) was used to label DNA in all cells. Scale bar = 100 µm (C) Immunofluorescence staining of NEDD4-1 and PTEN in U87MGR cell line transfected with miR-3129-5p and miR-199b-3p mimics demonstrating differential localization. DAPI staining (blue) was used to label DNA in all cells. Scale bar = 100 µm. (D) U87MGR cells were co-transfected with miR-3129-5p, miR-199b-3p, or a control mimic (miR-NC), as well as a wild-type or mutated (mut) NEDD4-1 3′UTR-directed luciferase reporter. Luciferase activity was measured by dual-luciferase reporter assays. (E) Western blot analysis of NEDD4-1 and PTEN differential protein expression in U87MGR cells transfected with control mimic (miR-NC), miR-3129-5p, miR-199b-3p, or both. Graph bars are the mean ± SEM of three independent experiments. * p < 0.05, ** p < 0.01, *** p < 0.001.\n\nFigure 4: Figure 4. Effect of NEDD4-1 inhibitor, indole-3-carbinol (I3C), on migration, invasion, and tumorsphere formation of temozolomide-resistant GBM cell lines. (A) Molecular structure of indole-3-carbinol (I3C). (B) SRB cell viability assay of temozolomide resistant and parental cell lines treated with I3C. (C) I3C treatment attenuated U251R and U87MGR tumorsphere-forming potential. (D) U251R and U87MGR migration ability evaluated using scratch assay. Gap closure was evaluated after 24 h incubation. (E) Gel-coated Transwell chambers were utilized to evaluate U251R and U87MGR invasion ability after treatment with I3C for 24 h. (F) Protein expression of NEDD4-1, NESTIN, SOX2, N-cadherin, and vimentin after treatment with I3C for 24 h, evaluated using Western blot. Graph bars are the mean ± SEM of three independent experiments. *** p < 0.001.\n\nFigure 5: Figure 5. I3C inhibits NEDD4-1 expression and represses temozolomide-resistant GBM cell line Nrf2-induced antioxidant response. (A) Protein expression of NEDD4-1, PTEN, p-AKT, AKT, NRF2, and HO-1 was evaluated after inducing oxidative stress with TBHp and treatment with I3C. (B) Effect of various doses of I3C on antioxidant enzyme activity in U87MGR cells. (C) Flow cytometry analysis of TBHp-induced ROS formation in U87MGR cells with/without I3C treatment using the ROS-sensitive fluorometric probe DCFDA. Relative ROS production in all cells tested normalized to TBHp + vehicle group. (D) Cell apoptosis rate assay using annexin V/PI staining of U87MGR cells treated with I3C and/or temozolomide. (E) Cell viability assay of U87MGR cells treated with I3C and/or temozolomide. Graph bars are the mean ± SEM of three independent experiments. * p < 0.05, ** p < 0.01, *** p < 0.001."
      }
    ]
  },
  {
    "id": "PMC8549703_multi_2",
    "image": [
      "images/PMC8549703-f6.png",
      "images/PMC8549703-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The E3 Ubiquitin Ligase NEDD4-1 Mediates Temozolomide-Resistant Glioblastoma through PTEN Attenuation and Redox Imbalance in Nrf2–HO-1 Axis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. In vivo experiments demonstrating the effectiveness of I3C and temozolomide combination against xenograft temozolomide-resistant GBM tumor. (A) Tumor volume of mice xenografted with U87MGR cells with vehicle, temozolomide, I3C, or both drugs combined was evaluated every 3 days after day 8 of tumor implantation to evaluate the effectiveness of cisplatin treatment. (B) Mouse body weight was evaluated every 3 days. (C) Representative images of the TUNEL assay (red fluorescence of apoptotic cells and blue fluorescence of cell nuclei) were detected using a fluorescence microscope (×400). ** p < 0.01.\n\nFigure 7: Figure 7. Graphical abstract. TMZ-resistant cells exhibited a dysregulated expression level of miR-3129-5p and miR-199b-3p, which results in the aberrant expression of NEDD4-1. Up-regulated NADD4-1 modulate the expression of tumor-suppressor PTEN and promotes the AKT/NRF2/HO-1 oxidative stress signaling axis on TMZ-resistant GBM cells. Thus, a combination of I3C, a well-known inhibitor of NEDD4-1 with TMZ results in the synergistic effect in improving therapeutics outcomes on TMZ-resistant GBM patients."
      }
    ]
  },
  {
    "id": "PMC8553673_multi",
    "image": [
      "images/PMC8553673-f1.png",
      "images/PMC8553673-f2.png",
      "images/PMC8553673-f3.png",
      "images/PMC8553673-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"NGS and phenotypic ontology-based approaches increase the diagnostic yield in syndromic retinal diseases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Presumed a priori diagnosis and phenotypic classification. All the cases were classified according to their phenotype into seven different categories: (i) suspicion of ciliopathy or ciliopathy-like (CILIOPATHY); (ii) suspicion of specific rare disease (SPECIFIC); (iii) RD + hearing loss and/or neurodevelopmental disorder (RD + HL ± ND); (iv) RD + neuropathy or myopathy or a suspicion of mitochondrial DNA disorder (mtDNA); (v) RD + skeletal disorder (RD + SD); (vi) RD + other (RD + OTHER); and (vii) SRDs unclassified without clinical information (UNCLASSIFIED). Subsequently, the patients with suspicion of ciliopathy or ciliopathy-like and specific rare disease were divided into different clinical entities using the pipeline provided in the Supplementary Table S1. ALMS Alström syndrome, ATS Alport syndrome, BBS Bardet-Biedl syndrome, CLN ceroid lipofuscinosis, neuronal, COH Cohen syndrome, JBTS Joubert syndrome, LCHAD deficiency long-chain 3-hydroxiacyl-CoA dehydrogenase deficiency, MUL Mulibrey nanism, RCD rod-cone dystrophy, RD retinal dystrophy, SLSN Senior–Løken syndrome, SRD syndromic retinal diseases, WFS Wolfram syndrome\n\nFigure 2: Figure 2. Summary of the HPO terms grouped by system. a Total identified and different HPO terms in the complete cohort and the fully characterized and uncharacterized (partially characterized, monoallelic, and negative cases) subcohorts. *The phenotypic terms without HPO annotation (n = 19) have been excluded. b All the terms identified in the complete cohort were classified. Numbers in bold represent the total HPO terms identified in each category, while the number of different HPO terms appears in brackets. c All the terms identified in the fully characterized and the uncharacterized subcohort were classified\n\nFigure 3: Figure 3. Molecular results. The genetic results were divided considering the a priori clinical groups: (i) suspicion of ciliopathy or ciliopathy-like (CILIOPATHY); (ii) suspicion of specific rare disease (SPECIFIC); (iii) RD + hearing loss and/or neurodevelopmental disorder (RD + HL ± ND); (iv) RD + neuropathy or myopathy or a suspicion of mitochondrial DNA disorder (mtDNA); (v) RD + skeletal disorder (RD + SD); (vi) RD + other (RD + OTHER); and vii) SRDs unclassified without clinical information (UNCLASS). a Diagnostic yields of molecular testing depending on the NGS technology carried out. Cases were divided into retrospective, CES (clinical-exome sequencing) (n = 79), using CES after the previous preliminary analysis, and prospective (n = 18), CES as first-tier approach. The 34 retrospective cases with inconclusive CES results were screened using WES (whole exome sequencing) plus 3 more cases directly sequenced by WES. b Molecular study results by clinical subgroup. c Inheritance mode distribution. The fully (n = 46) and incompletely (n = 6) characterized cases were classified according to the Mendelian inheritance mode of the causative gene and grouped into autosomal dominant (AD), autosomal recessive (AR), or X-linked (XL) trait. Non-Mendelian inheritances (mitochondrial and triallelism) were also considered, as well as the cases with co-occurrence of two different genetic causes. d Final classification of the SRD cohort after genetic testing. Cases that were reclassified into another clinical subgroup due to the identification of the causative gene are indicated\n\nFigure 4: Figure 4. Sankey chart of the clinical distribution of the characterized cases before and after molecular studies and the results of this analysis. The causative genes appear with the color corresponding to the clinical group to which each case was assigned a priori. Sankey chart was created using the Sankey Diagram Generator by Dénes Csala, based on the Sankey plugin for D3 by Mike Bostock (https://sankey.csaladen.es/; 2014). *Phenotypically partially characterized. DEL deletion, DUP duplication, RD retinal dystrophy, HL hearing loss, mtDNA mitochondrial DNA, ND neurodevelopmental disorder, SD skeletal disorder"
      }
    ]
  },
  {
    "id": "PMC8579195_multi",
    "image": [
      "images/PMC8579195-f1.png",
      "images/PMC8579195-f2.png",
      "images/PMC8579195-f2-2.png",
      "images/PMC8579195-f4.png",
      "images/PMC8579195-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitin ligase MARCH5 localizes to peroxisomes to regulate pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Identification of MARCH5-interacting proteins by PUP-IT. (A) Design of PUP-ITMARCH5. Pup(E) ligase PafA was fused to the C-terminus of MARCH5 and catalyzed biotin-Pup(E) ligation to MARCH5-interacting proteins. (B) iPUP cells expressing MARCH5-PafA-Myc were treated with Dox for 24 h. iPUP cells without MARCH5-PafA-Myc were used as the control. Biotin-modified proteins were analyzed with streptavidin-HRP. The asterisk indicates background from endogenous biotin-modified proteins. (C) The workflow of PUP-ITMARCH5–based proximity labeling to identify MARCH5-interacting proteins. (D) Volcano plot of proteins enriched as MARCH5-interacting proteins. The logarithmic ratios of protein LFQ intensity (iPUP/PUP-ITMARCH5) were plotted against negative logarithmic P values from a two-sided, two-sample t test in Perseus. Green and orange dots represent proteins that are enriched in the PUP-ITMARCH5 sample (FDR ≤0.05; n = 3 independent experiments). (E) Proteins enriched in PUP-ITMARCH5 sample were subjected to gene ontology analysis. STRING (functional protein-association networks) was used to analyze protein interactions (https://string-db.org/). The thickness of the lines indicates the strength of data support. Spec, spectrometry.\n\nFigure 2: Figure 2. Identification and validation of PEX19 as a MARCH5-interacting protein. (A) Reproducibility of the proximity labeling experiments to identify MARCH5-interacting proteins. Pearson’s correlation coefficients between replicate (Rep.) MS results for PUP-ITMARCH5 and control samples. (B) PEX19 peptides containing GGE modification on lysine residues identified by MS. Red highlights the modification sites. Blue highlights the peptides in the context of full-length PEX19. (C) Multiple MARCH5-interacting candidates, including PEX19, are modified with biotin-Pup, showing higher-molecular-weight bands on WBs. HeLa cells were cotransfected with MARCH5-PafA-Myc and V5-tagged interacting candidate proteins. Proteins labeled by biotin-Pup were enriched by streptavidin magnetic beads, then analyzed by WB with anti-V5 antibodies. Black arrow, unmodified PEX19-V5 (expected, 35 kD); red arrows, biotin-Pup–modified PEX19-V5 (expected, 55 kD for monomodification and 75 kD for dimodification).\n\nFigure 2: Figure 2. MARCH5 interacts with PEX19 and PEX3. (A) IP of MARCH5-Myc performed with HEK293T cells cotransfected with MARCH5-Myc and PEX19-V5. The samples were analyzed by IB with indicated antibodies. (B) HEK293T cells were cotransfected with PEX19-3×FLAG and different MARCH5-mCherry-Myc variants. Cells were collected 36 h after transfection for IP of PEX19-3×FLAG and IB with indicated antibodies. (C) V5-PEX19 or NLS fused V5-PEX19 were coexpressed with MARCH5-Myc or TOMM20-Myc in HeLa cells for 24 h. Cells are stained for Myc and V5 tags. (D) HEK293T cells were transfected with MARCH5-Myc and PEX3-3×FLAG for 30 h. Cells were treated with 50 μM MG132 for 6 h and then harvested for IP and IB with indicated antibodies. (E) HEK293T cells were cotransfected with PEX3-3×FLAG and different MARCH5-mCherry-Myc variants. IP and IB were performed with indicated antibodies. (F) HEK293T cells were transfected with MARCH5-Myc and PEX3-3×FLAG or PEX3(46–373)-3×FLAG for 36 h. Cells were treated with 50 μM MG132 for 6 h and then harvested for IP of MARCH5-Myc and IB with indicated antibodies. (G) Confocal fluorescent images of HeLa cells infected with lentiviruses expressing MARCH5-mCherry and PEX3-YFP. White arrows indicate where mCherry and YFP signals overlap.\n\nFigure 4: Figure 4. The effect of knocking down PEX19. (A) Representative images of WT HeLa cells expressing MARCH5-mCherry and Ub-GFP-SKL. Endogenous PEX19 was knocked down by using shRNA. (B) Percentage of MARCH5-mCherry colocalized with peroxisome from A was calculated in ImageJ using Mander’s colocalization coefficients. More than 50 cells were counted. Error bars indicate SD. **, P < 0.01; n.s., not significant (one-way ANOVA and Tukey’s multiple comparisons test). (C) The knockdown effect of PEX19 shRNAs was verified at the protein level. (D) RFP-GFP-SKL HeLa cells transfected with two different shRNAs targeting PEX19 were treated with Torin1 (1 μM for 24 h), folimycin (10 nM for 24 h), or a combination of the two. Cells were then analyzed by flow cytometry.\n\nFigure 3: Figure 3. MARCH5 partially locates on peroxisomes. (A) HeLa cells stably expressing GFP-SKL were transfected with MARCH5-mCherry or TOMM20-mCherry for 36 h. Mitochondria were stained with MitoTracker Deep Red (50 nM) for 30 min. Cells were analyzed with confocal microscopy. (B) PLA was performed with primary antibodies against Myc and V5. HeLa cells stably expressing GFP-SKL were transfected with PEX3-V5, PEX19-V5, and MARCH5-Myc as indicated for 24 h. (C) WT HeLa cells were transfected with the indicated constructs for 24 h, and PLA was performed with primary antibodies against Myc and V5. (D) PLA signal points in C were calculated and analyzed in ImageJ. Approximately 30 cells were counted in each condition. Error bar represents SD. ***, P < 0.001; ****, P < 0.0001; n.s., not significant (one-way ANOVA and Tukey’s multiple comparisons test). (E) Fractionation assay for 293T cells. 5 μg of each fraction isolated from cells was analyzed with IB using the indicated antibodies. The asterisk indicates the nonspecific band. 2.3K, 23K, and 100K, precipitates after centrifugation at indicated speeds; Cyt, supernatants after centrifugation at 100,000 g; Mito, mitochondrion; PO, peroxisome; WCE, whole-cell extraction. (F) Normalized protein level showing relative protein enrichment in different fractions. Band intensity in E was measured with ImageJ and normalized. Values are mean ± SD, n = 3 independent experiments. (G) A model for peroxisomal localization of MARCH5 mediated by PEX19 and PEX3. PEX19 binds to the TM region on newly synthesized MARCH5 in the cytosol and transfers it onto the peroxisome surface via PEX3. R, RING domain."
      }
    ]
  },
  {
    "id": "PMC8579195_multi_2",
    "image": [
      "images/PMC8579195-f4-2.png",
      "images/PMC8579195-f7.png",
      "images/PMC8579195-f5.png",
      "images/PMC8579195-f9.png",
      "images/PMC8579195-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitin ligase MARCH5 localizes to peroxisomes to regulate pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 4: Figure 4. MARCH5 binds and ubiquitinates PMP70. (A) IP was performed with anti-V5 antibody in HEK293T cells transfected with PMP70-V5 and MARCH5-Myc, followed by IB for V5, Myc, and β-actin. (B) HeLa cells were transfected with MARCH5-Myc plasmids for 48 h. After 10 μM MG132 treatment for 6 h, IP was performed with anti-PMP70 antibody, followed by IB for PMP70 and Myc. (C) HEK293T cells were transfected with HA-Ub, PMP70-V5, MARCH5-Myc, and MARCH5(HW)-Myc plasmids for 48 h. After 10 μM MG132 treatment for 6 h, cell lysates were immunoprecipitated with anti-V5 antibody and then immunoblotted with indicated antibodies. (D) HeLa cells were transfected with empty vector (EV), MARCH5-Myc, or catalytically inactive MARCH5-CS-Myc plasmids for 48 h. The cell lysates were immunoblotted with indicated antibodies. (E) The protein levels in D were quantified with ImageJ, then normalized to β-actin. Values are mean ± SD, n = 3 independent experiments. n.s., not significant (P > 0.05) by two-tailed Student’s t test. (F) HeLa cells were transfected with two different shRNAs targeting MARCH5. The cell lysates were immunoblotted with indicated antibodies. (G) The protein levels in F were quantified with ImageJ, then normalized to β-actin. Values are mean ± SD, n = 3 independent experiments. *, P < 0.05; ***, P < 0.001; ****, P < 0.0001; n.s., not significant (P > 0.05) by two-tailed Student’s t test.\n\nFigure 7: Figure 7. MARCH5 ubiquitinates PEX3. (A) HeLa cells were cotransfected with MARCH5-Myc and PEX3-V5 plasmids for 18 h and treated with 10 μM MG132 for 6 h in the indicated sample. IP and IBs were performed with anti-Myc and anti-V5 antibodies. (B) MARCH5 KO HeLa cells were cotransfected with HA-Ub, PEX3-3×FLAG, and MARCH5-Myc for 18 h and treated with MG132 (10 μM) for 6 h. IP was performed with anti-FLAG antibody and followed by IB with indicated antibodies. (C) 293FT cells were cotransfected with HA-Ub, PEX3-3×FLAG, and MARCH5-Myc for 48 h. Cells were treated with DMSO, MG132 (10 μM for 6 h), or folimycin (10 nM for 24 h). IP was performed with anti-FLAG antibody and followed by IB with indicated antibodies. L.E., long exposure; S.E., short exposure.\n\nFigure 5: Figure 5. Torin1 induces PMP70 ubiquitination and degradation. (A) Representative fluorescence images of HeLa cells treated with Torin1 (1 μM) or DMSO for 24 h as indicated and immunostained for PMP70. (B) Quantification of peroxisome numbers (green puncta) in cells treated as in A. Values are mean ± SD, n = 3 independent experiments, calculated using >90 cells. (C) HeLa cells were treated with Torin1 for the indicated time. The cell lysates were immunoblotted with the indicated antibodies. (D) Quantification of the protein levels in C. (E) HeLa cells were transfected with HA-Ub for 24 h and then treated with Torin1 (1 μM) for 24 h and MG132 (10 μM) for 4 h. Cell lysates were then subjected to a ubiquitination assay and immunoprecipitated with anti-PMP70 antibody, followed by WB analysis. (F) HeLa cells were treated with DMSO, Torin1 (1 μM for 24 h), MG132 (10 μM for 4 h), Baf-A1 (40 nM for 24 h), and folimycin (10 nM for 24 h) as indicated and immunoblotted with PMP70, catalase, PEX19, PEX3, PEX13, and β-actin antibodies. (G) Quantification of F. In D and G, the protein levels were quantified with ImageJ, then normalized to β-actin. Values are mean ± SD, n = 3 independent experiments. *, P < 0.05; **, P < 0.01; ****, P < 0.0001; ns, P > 0.05 by two-tailed Student’s t test.\n\nFigure 9: Figure 9. Torin1 induces pexophagy in different cells. (A) Representative fluorescence images of OVCAR8 cells treated with Torin1 (1 μM) or DMSO for 24 h as indicated and immunostained for PMP70. Scale bars: 10 µm. (B) Quantification of peroxisome numbers (green puncta) in cells treated in A. Values are mean ± SD, n = 3 independent experiments, calculated using >90 cells. ***, P < 0.001 by two-tailed Student’s t test. (C) OVCAR8 cells were treated with DMSO or Torin1 for the indicated time. The cell lysates were analyzed by WB and immunoblotted with PMP70 and β-actin antibodies. (D) HeLa cells stably expressing GFP-SKL were treated with DMSO or Torin1 (1 μM) for 24 h. Cells were then fixed and examined by microscopy to detect GFP signal. Scale bars: 5 µm. (E) HeLa cells stably expressing GFP-SKL were treated with or without Torin1 (1 μM for 24 h). Cells were then analyzed by flow cytometry. (F) Quantification of GFP intensity in E. Values are mean ± SD, n = 3 independent experiments. **, P < 0.01; ***, P < 0.001; n.s., not significant by one-way ANOVA and Dunnett’s multiple comparisons test.\n\nFigure 6: Figure 6. Torin 1 induces pexophagy. (A) HeLa cells stably expressing RFP-GFP-SKL were treated with DMSO or Torin1 (1 μM) for 24 h. Cells were then fixed and examined by microscopy to detect RFP and GFP signals. Scale bars: 5 µm. (B) Pearson’s correlation coefficients showing the colocalization between RFP-SKL and GFP-SKL derived from A. Values are mean ± SD, calculated using >50 cells. ***, P < 0.001; ****, P < 0.0001 by one-way ANOVA and Tukey’s multiple comparisons test. (C) Percentage of cells showing red fluorescence that are not overlapping with GFP. Values are mean ± SD, calculated using >50 cells. ****, P < 0.0001 by one-way ANOVA and Tukey’s multiple comparisons test. (D) HeLa cells stably expressing RFP-GFP-SKL were treated with Torin1 (1 μM for 24 h), folimycin (10 nM for 24 h), or a combination of the two. Cells were then analyzed by flow cytometry. (E) Hela cells stably expressing Ub-GFP-SKL were treated with Torin1 (1 μM for 24 h), folimycin (10 nM for 24 h), or a combination of the two. Cells were then fixed and examined by microscopy to detect GFP signal. Scale bars: 5 µm. (F) Quantification of peroxisome numbers by counting GFP-positive spots in E. Values are mean ± SD, n = 3 independent experiments, calculated using >60 cells. ****, P < 0.0001; n.s., not significant by one-way ANOVA and Tukey’s multiple comparisons test."
      }
    ]
  },
  {
    "id": "PMC8579195_multi_3",
    "image": [
      "images/PMC8579195-f11.png",
      "images/PMC8579195-f7-2.png",
      "images/PMC8579195-f8.png",
      "images/PMC8579195-f9-2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitin ligase MARCH5 localizes to peroxisomes to regulate pexophagy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Other supplementary information. (A) Schematic of the genome-editing strategy to knock out endogenous MARCH5 in HeLa cells. Exons 1–6 (E1-E6) are indicated. Three designed sgRNAs were tested initially, and the validated sgRNA confirmed by sequencing, as shown. Protospacer adjacent motif sequences are depicted in red. The KO of MARCH5 is confirmed by both Sanger sequencing (left) and IBs (right). (B) WT or MARCH5 KO HeLa cells expressing Ub-GFP-SKL were cultured in DMEM (supplemented with 10% FBS) or HBSS for 24 h. GFP signal was analyzed with FACS. (C) Representative images for Fig 9, D and E. WT or MARCH5 KO HeLa cells were transfected with Ub-GFP-FKBP and FRB-HA-PEX26 for 24 h. Cells were treated with DMSO or rapalog for 24 h, fixed, immunostained for PMP70, and imaged with confocal microscopy. Scale bars: 5 µm. (D) HeLa cells were treated with Torin1 (1 μM) for the indicated time. MARCH5 mRNA levels were detected with quantitative PCR assay. Values are mean ± SD, n = 3 independent experiments. n.s., not significant (P > 0.05) by two-tailed Student’s t test. (E) HeLa cells were transfected with MARCH5-Myc plasmid for 24 h, then with or without Torin1 (1 μM) were added for an additional 24 h before harvesting. Cells were then fixed and immunostained for PMP70 (Alexa Fluor 488, green) and Myc (Alexa Fluor 555, red) and examined by microscopy to detect GFP and RFP signals. Pearson’s correlation coefficients show the colocalization between PMP70 and MARCH5-Myc derived from above. Values are mean ± SD *, P < 0.05 by two-tailed Student’s t test.\n\nFigure 7: Figure 7. KO of MARCH5 blocks Torin1-induced PMP70 degradation and pexophagy. (A) WT and MARCH5 KO HeLa cells were treated with Torin1 (1 μM) or DMSO for 24 h and immunoblotted with indicated antibodies. (B) The protein levels in A were quantified with ImageJ, then normalized to β-actin. Values are mean ± SD, n = 3 independent experiments. **, P < 0.01; ***, P < 0.001; ns, P > 0.05 by two-tailed Student’s t test. (C) WT and MARCH5 KO HeLa cells were treated with Torin1 (1 μM) or DMSO for 24 h as indicated and immunostained for PMP70. Scale bars: 7 µm. (D) Quantification of peroxisome numbers (green puncta) in cells treated in C. Values are mean ± SD, n = 3 independent experiments, calculated using >50 cells. ****, P < 0.0001; n.s., not significant by one-way ANOVA and Tukey’s multiple comparisons test. (E) WT and MARCH5 KO HeLa cells stably expressing RFP-GFP-SKL were treated with Torin1 (1 μM for 24 h), folimycin (10 nM for 24 h), or a combination of the two. Cells were then analyzed by flow cytometry.\n\nFigure 8: Figure 8. MARCH5 ubiquitin ligase activity is required for PMP70 ubiquitination and degradation with Torin1 treatment. (A) MARCH5 KO cells were transfected with empty vector (EV), MARCH5-Myc, or catalytically inactive MARCH5-CS-Myc plasmid for 24 h and treated with Torin1 (1 μM for 24 h), as indicated. The cell lysates were immunoblotted with indicated antibodies. (B) The protein levels in A were quantified with ImageJ, then normalized to β-actin. Values are mean ± SD, n = 3 independent experiments. *, P < 0.05; **, P < 0.01; ns, P > 0.05 by two-tailed Student’s t test. (C) WT and MARCH5 KO HeLa cells were transfected with HA-Ub for 24 h and then treated with Torin1 (1 μM for 24 h) and MG132 (10 μM for 4 h). Cell lysates were then subjected to a ubiquitination assay and immunoprecipitated with anti-PMP70 antibody, followed by WB analysis. (D) MARCH5 KO cells were transfected with MARCH5-Myc or catalytically inactive MARCH5-CS-Myc and HA-Ub plasmid for 24 h and treated with Torin1 and MG132, as indicated. The ubiquitination assay was performed, and cell lysates were immunoprecipitated with anti-PMP70 antibody, followed by WB analysis.\n\nFigure 9: Figure 9. Peroxisome-localized MARCH5(RING) domain is sufficient to mediate Torin1-induced pexophagy. (A) MARCH5 KO HeLa cells were transfected with MARCH5(WT)-mCherry, MARCH5(Ring)-mCherry-PEX26(TM) (referred as po-MARCH5) or TOMM20-MARCH5(RING)-mCherry (referred as mito-MARCH5) for 24 h and treated with Torin1 (1 μM for 24 h), folimycin (10 nM for 24 h), or a combination of the two for an additional 24 h. Cells were then fixed and stained for PMP70 (Alexa Fluor 488; green). Scale bars: 5 µm. (B) Quantification of peroxisome numbers (green puncta) in cells treated in A. Values are calculated using >50 cells. ****, P < 0.0001; n.s., not significant by one-way ANOVA and Tukey’s multiple comparisons test. (C) Schematic of induced peroxisome ubiquitination (ub) using FRB-PEX26 and Ub-GFP-FKBP. (D and E) WT HeLa or MARCH5 KO HeLa cells were transfected with Ub-GFP-FKBP and FRB-HA-PEX26 for 24 h. Cells were treated with or without rapalog for 24 h, fixed, immunostained for PMP70, and imaged with confocal microscopy (representative images in Fig. S5). The peroxisome number was quantified. Values are mean ± SD, n = 3 independent experiments, calculated using >50 cells. ****, P < 0.0001 by two-tailed Student’s t test. (F) Model of the role of MARCH5 in Torin1-induced pexophagy. R, RING domain."
      }
    ]
  },
  {
    "id": "PMC8586424_multi",
    "image": [
      "images/PMC8586424-f1.png",
      "images/PMC8586424-f2.png",
      "images/PMC8586424-f3.png",
      "images/PMC8586424-f4.png",
      "images/PMC8586424-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Molecular Changes in Prader-Willi Syndrome Neurons Reveals Clues About Increased Autism Susceptibility\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Social Communication Questionnaire (SCQ) scores across all subjects. (A) SCQ scores across all subjects. (B) SCQ scores across individuals used for RNAseq analysis. A cutoff score of 15 (red line) is used as a threshold for “possible ASD.” The PW-UPD cohort has two segregated groups. Subjects that meet the criteria for “Possible ASD” (score of 15 or above) and those scoring within normal limits. For 2 of the neurotypical control subjects used, SCQs could not be collected. Significance testing was performed by one-way ANOVA testing. ** = p-value ≤ 0.01, *** = p-value ≤ 0.005.\n\nFigure 2: Figure 2. DPSC from both PWS and control subjects differentiate efficiently into neuronal cultures. (A) DPSC from all subjects are negative for neuronal markers, MAP2 and GABA A, but positive for stem cell marker NESTIN. After differentiation and 3 weeks of maturation, the cultures are positive for both MAP2 and GABA A receptor subunit beta 3. (B,C) Representative DPSC versus DPSC-derived neurons visualized with anti-beta tubulin (red) (B) DPSC show a flat fibroblast-like morphology as previously reported. (C) DPSC-derived neuronal culture contains cells with pyramidal neuron morphology. DAPI (blue) was used as a nuclear stain. 63× magnification. Scale bar is 20 μM.\n\nFigure 3: Figure 3. DPSC-derived neuronal cultures define PWS subtype specific expression and a core PWS molecular signature. (A) Venn diagram using all the significantly differentially expressed transcripts (p-value ≤ 0.05, FDR ≤ 0.05) versus control for each PWS subtype created using BioVenn (Hulsen et al., 2008). (B) Individual bar graphs showing mean counts per transcript across all groups for each of the transcripts located outside of the PWS critical region and identified as common across all PWS subtypes. These 9 genes, along with MAGEL2, SNRPN, and SNURF, represent a core molecular signature for PWS associated changes in neurons. Significance was determined by individual t-tests versus control for each subgroup (p ≤ 0.05). * = p-value ≤ 0.05, ** = p-value ≤ 0.01, *** = p-value ≤ 0.005.\n\nFigure 4: Figure 4. RNAseq analysis reveals enrichment in differentially expressed mitochondrial transcripts in the PW-UPD + ASD group. (A) Venn diagram using all the significantly differentially expressed transcripts (p-value ≤ 0.05, FDR ≤ 0.05) versus PW-UPD + ASD for each PWS subtype and control created using BioVenn (Hulsen et al., 2008). (B) The list of differentially expressed transcripts PW-UPD -ASD versus UPD + ASD (p-value ≤ 0.05, FDR ≤ 0.05) was used as input for DAVID (Huang da et al., 2009a, b) enrichment analysis. The top enrichments (enrichment score ≥ 3.0) were transcripts located within mitochondria and having mitochondrial functions (p-value ≤ 0.002). (C) Heatmap of transcripts identified by DAVID analysis as mitochondrial related. Expression of genes identified as driving the mitochondria enrichment in the PW-UPD + ASD group were used to create this heatmap across all subgroups (Metsalu and Vilo, 2015). Colors indicate read counts from high (red) to low (blue). Most of the mitochondrial transcripts identified in DAVID enrichment set have reduced expression in the PW-UPD + ASD group compared to all other groups.\n\nFigure 5: Figure 5. Mislocalization and reduced dispersion of mitochondria in ASD neurons. Neuronal cultures visualized with anti-beta tubulin (red) and the mitochondrial marker anti-TOMM20 (green). The PW-UPD -ASD neuron (top row) shows bright and evenly dispersed mitochondria within the neuronal projections. In PW-UPD + ASD neuron, the red arrows point to mitochondrial aggregates not seen in the PW-UPD -ASD neurons. (A,C) show neuronal morphology using anti-beta tubulin staining. (B,D) show the anti-TOMM20 staining to identify mitochondria. Confocal stacks were taken at 63X magnification. Scale bar is 20 μm."
      }
    ]
  },
  {
    "id": "PMC8586424_multi_2",
    "image": [
      "images/PMC8586424-f6.png",
      "images/PMC8586424-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Molecular Changes in Prader-Willi Syndrome Neurons Reveals Clues About Increased Autism Susceptibility\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Representative image of Imaris volumetric analysis. Z stacks from neuronal images taken on a Zeiss 810 confocal microscope were loaded into the Imaris software suite for analysis. (A,E) show a representative image of a neuron with mitochondrial aggregates while (C,G) depict a neuron with dispersed mitochondria. Anti-Beta Tubulin (A,C) was used to measure the surface area of the neuron, while anti-TOMM20 (E,G) was used to label total mitochondria content within the neuron. Using the surfaces function in Imaris, a mask for the Beta Tubulin (B,D) and TOMM20 (F,H) stained areas was constructed. From these surface masks, the area is calculated by the software (bottom right corner of B,D,F,H) for each surface. The mitochondrial area within the neuron was divided by the total neuronal area to determine a percentage of mitochondrial volume. Images were taken at 63× by confocal microscopy. Scale bar represents 20 μM.\n\nFigure 7: Figure 7. PW-UPD + ASD neurons show decreased mitochondrial coverage within neuronal area. Using Imaris, the total neuronal area (anti-Beta Tubulin) that contains mitochondria (anti-TOMM20) was calculated. Percent of mitochondrial coverage was measured for ≥15 neurons from each cell line and at least 5 cell lines per group in a blinded fashion. Significance testing was performed by both ordinary one-way ANOVA and Turkey’s multiple comparisons test with a single pooled variance. ns = not significant, **** = p-value ≤ 0.001."
      }
    ]
  },
  {
    "id": "PMC8591368_multi",
    "image": [
      "images/PMC8591368-f1.png",
      "images/PMC8591368-f2.png",
      "images/PMC8591368-f3.png",
      "images/PMC8591368-f4.png",
      "images/PMC8591368-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulation of mitochondrial cargo-selective autophagy by posttranslational modifications\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Key elements of the autophagy pathway. Cellular stress (i.e., starvation) is sensed by AMPK, which directly activates the ULK1 complex by a complex phosphorylation pattern, including S555, and relieves it from the mTOR block by suppressing ULK1 S757 phosphorylation. The ULK1 kinase phosphorylates several components of the ULK1 megacomplex as well as the PI3K-III complex, promoting its translocation to the ER, where it generates membrane domains rich in PI3P that are eventually recognized by PI3P-binding proteins which promote phagophore formation. Two enzyme conjugation systems mediate phagophore maturation and insert lipidated ATG8 (or LC3-II) as anchors for autophagy receptors/adaptors that couple to ubiquitylated cargo. Finally, autophagosomes fuse with lysosomes (or the vacuole in yeast) via interaction of the SNARE and HOPS complexes, respectively. See text for details. Thick gray arrows indicate protein translocations, thin black arrows indicate protein phosphorylations (arrowheads stimulatory, hammerheads inhibitory), and the thin red arrow indicates lipid phosphorylation. Blue arrows indicate enzyme conjugation systems, and the orange arrow endoproteolytic cleavage. The dashed line indicates an indirect transcriptional (CLEAR) pathway for lysosome biogenesis.\n\nFigure 2: Figure 2. Schematic representation of parkin-dependent mitophagy time course.A, in normal conditions, PINK1 is imported and partially cleaved by the mitochondrial protease PARL, after which PINK1 gets eliminated by the UPS following the N-end rule, leading to very low endogenous PINK1 levels in healthy conditions. MITOL prepares a ubiquitin coat on MOM substrates. Upon mitochondrial membrane depolarization, the protein import machinery gets compromised and PINK1 is accumulated at the MOM. PINK1 gets auto-phosphorylated, and this triggers its activation: PINK1 starts phosphorylating ubiquitin molecules that were previously attached to MOM substrates, antogonizing USP30-mediated ubiquitin removal of those chains. B, phosphorylation of ubiquitin by PINK1 triggers parkin recruitment to the MOM. Direct PINK1 phosphorylation of the parkin Ubl and the binding to phosphorylated ubiquitin trigger a conformation change of parkin, which activates its E3-ubiquitin ligase potential. As a result, diversely linked ubiquitin chains are built on MOM substrates. Proteins involved in mitochondrial transport and fusion are mostly polyubiquitylated with K48-linked chains and are rapidly eliminated via the ubiquitin-proteasome system. MIRO1/2 is also ubiquitylated through K27-linked chains and is involved in multiple functions other than mitochondrial transport. Differential linkages might explain the remaining forms of ubiquitylated MIRO1/2 after mitochondria depolarization (dashed arrow). Other MOM proteins such as VDAC2 and TOM20 are mostly ubiquitylated with K63-linked and K27-linked chains, which triggers the recruitment of autophagy receptors. Ubiquitin chain building may be counteracted by USP30. C, S473 within the UBL domain of optineurin is phosphorylated by bound TBK1 when recruited to ubiquitylated MOM proteins, further enhancing optineurin recognition of ubiquitin chains. TBK1 also phosphorylates optineurin and additional autophagy receptors within the LIR motif (S177 in optineurin), which increases the affinity for lipidated ATG8/LC3 molecules and eventually triggers the recruitment of mitochondria to autophagosomes for their final elimination.\n\nFigure 3: Figure 3. Parkin-independent driven mitochondria elimination.A, receptor-mediated mitophagy depends on phosphorylation of MOM-anchored autophagy receptors (i.e., NIX, BNIP3, AMBRA1, FUNDC1). Additionally, phospholipids such as cardiolipin can also act as autophagy receptors once they are externalized to the MOM under mitochondrial stress conditions. B, ubiquitin-mediated mitophagy involves parkin-independent E3 ligase ubiquitylations that specifically decorate mitochondria for subsequent autophagic removal. Such ubiquitylations may be performed by MOM-residing E3 ligases (i.e., MUL1), cytosolic E3 ligasses that translocate to mitochondria upon mitochondrial stress conditions (i.e., HUWE1) or ER-residing E3 ligases (i.e., gp78) that, together with MOM-residing ubiquitin ligases, act on ER–mitochondrial contact sites, enhancing mitochondria fragmentation and facilitating specific autophagic elimination of mitochondria.\n\nFigure 4: Figure 4. Fission and fusion factors driving mitophagy. Mitochondrial fragmentation triggers mitophagy while mitochondrial fusion has the opposite effect (upper scheme). A, mitochondrial fragmentation can occur through (1) parkin-dependent ubiquitylation of MFN, targeting MFN for proteasomal degradation, (2) phosphorylation of MFF by AMPK or (3) dephosphorylation of DRP1. Once mitochondria are fragmented, mitophagy is induced in an ATG5-dependent manner through recognition of ubiquitin chains via autophagy receptors or direct recognition of dephosphorylated DRP1 by FUNDC1. B, mitochondrial fission can be triggered by the RAB9/ULK1 complex, which indirectly influences the phosphorylation of DRP1. In this pathway, selective autophagy is activated in an ATG5-independent manner; the maturation of the phagosome is accomplished by the interaction of trans-golgi and late endosome membrane fusion. C, mitochondrial fusion can be driven through a change in DRP1 phosphorylation status by protein kinase A or by direct inhibition of L-OPA1 cleavage by SIRT4.\n\nFigure 5: Figure 5. Bcl-2 like proteins influence on the activation of autophagy and apoptosis.A, Bcl-2 like proteins can interact with beclin-1, inhibiting its autophagy function. BAD is able to relieve this repression, interfering with these interactions. B, under mitochondrial stress conditions, PINK1 phosphorylates BAD and parkin ubiquitinates BAX and BAK, inhibiting their proapoptotic functions and promoting mitophagy. It is possible—though not yet proven—that phosphorylation of BAD inhibits its proapoptotic functions also in this case. C, mitophagy can be inhibited by parkin-dependent ubiquitylation of the antiapoptotic factor Mcl-1 or direct interaction of Bcl-XL with parkin, which directly inhibits parkin translocation to mitochondria. It remains to be elucidated if both parkin-dependent ubiquitinations eventually trigger cell apoptosis and through which specific pathway. Arrowheads indicate activation, hammerheads indicate inhibition, dashed arrows indicate translocation."
      }
    ]
  },
  {
    "id": "PMC8601054_multi",
    "image": [
      "images/PMC8601054-f1.png",
      "images/PMC8601054-f2.png",
      "images/PMC8601054-f3.png",
      "images/PMC8601054-f4.png",
      "images/PMC8601054-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Genome-wide identification of RING finger genes in flax (Linum usitatissimum) and analyses of their evolution\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Variation in spaces between ml pairs ml1-ml2, ml3-ml4, ml4-ml5, ml5-ml6, and ml7-ml8 in different types of flax RING domains. (B) Comparison of the numbers of amino acids in the loops between ml2-ml3 and ml6-ml7 of the flax RING-H2, RING-HCa, RING-HCb, RING-v, and RING-C2 domains. X(n) denotes the number of amino acids observed between the conserved ml residues.\n\nFigure 2: Figure 2. The eight conserved metal-ligand residues are marked with asterisks, and zinc-coordinating amino acid pairs are shown. Bits in the Y-axis represent the amount of informational content at each sequence position.\n\nFigure 3: Figure 3. The neighbor-joining (NJ) tree constructed from 587 RING domains observed in 574 RING finger proteins in flax is shown. The colored ranges corresponding to the RING types in flax are shown. The three main branches, Clade I, II, and III, are represented in red, green, and blue color, respectively.\n\nFigure 4: Figure 4. Chromosomes 1–15 are shown with different colors and in a circular form. The approximate distribution of each flax RING finger gene is marked on the circle with a short black line. Colored curves denote the details of syntenic regions between flax RING finger genes (blue and red curves represent the segmental duplication events and the tandem duplication events, respectively).\n\nFigure 5: Figure 5. Gray lines in the background denote collinear blocks within flax and other plant genomes, and blue lines highlight the syntenic RING gene pairs, with four representative plant species being P. trichocarpa, A. thaliana, V. vinifera, and O. sativa."
      }
    ]
  },
  {
    "id": "PMC8640217_multi",
    "image": [
      "images/PMC8640217-f1.png",
      "images/PMC8640217-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Peroxisomal Membrane Contact Sites in Yeasts\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisome–ER contact sites. Peroxisome and PPVs contact the ER at subdomains enriched with the Pex23 and Pex24 protein families. ScPex30 and ScPex29 and OpPex24 and OpPex32 are at the ER–peroxisome contact sites. ScPex30 is at ER subdomains where ScPex14-containing nascent PPVs are formed. The table contains the family of Pex23 (magenta) and Pex24 (blue) proteins in different yeasts.\n\nFigure 2: Figure 2. Peroxisome contact sites in yeasts. (A) and (B) indicate peroxisome–LD contact sites. (A) Formation of pexopodia enriched in beta-oxidation enzymes into the core of LDs in peroxisome-proliferating growth conditions. (B) LDs and peroxisomes interact at the ScPex30 ER subdomains. (C) Peroxisome–plasma membrane contact site. Inp1 binds to the plasma membrane at sites enriched in PI (4,5) P2 with another possible binding partner. Inp1 tethers peroxisome to the plasma membrane by binding Pex3 localized on the peroxisomal membrane. (D) Peroxisome–mitochondria contact sites. Pex11 binds Mdm34 of the ERMES complex at the ER–mitochondria contact sites. Fzo1 on mitochondrial membrane contacts an unknown binding partner on peroxisomes, and Pex34 on peroxisomal membrane binds an unknown binding partner on the mitochondria. (E) Peroxisome–vacuole contact sites. OpPex3 accumulates at the peroxisome–vacuole contact sites in peroxisome-proliferating conditions or when overexpressed. The OpPex3 binding partner on the vacuolar membrane is unknown."
      }
    ]
  },
  {
    "id": "PMC8659757_multi",
    "image": [
      "images/PMC8659757-f1.png",
      "images/PMC8659757-f2.png",
      "images/PMC8659757-f3.png",
      "images/PMC8659757-f4.png",
      "images/PMC8659757-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Fatty Acid Oxidation and Glycolysis Are Triggered in Mouse Models of Lesional Atopic Dermatitis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Lipid composition and ultrastructural analysis of ft/ft mouse epidermis. (a) The function of the inside‒out epidermal barrier was assessed by measuring TEWL on the ears of control and ft/ft mice (n = 5). Relative and total amounts of (b, c) d18:1 Cers(NS), (d, e) ω-O-acylCers (n = 5), (f, g) SFAs and MUFAs in the epidermis of ft/ft mice compared with those in the epidermis of control mice (n = 5). Data are shown as analyte/IS ratio (AU) per mg protein or as the relative percentage of total lipid species. (h) Ultrastructural analysis of control (left) and ft/ft (right) mouse epidermis showing LB morphology (insets) and secretion (arrows). Osmium tetroxide after fixation. Bar = 250 nm. Data were analyzed with a Student’s t-test. ∗∗P < 0.01, ∗∗∗P < 0.001, and ∗∗∗∗P < 0.0001. AU, arbitrary unit; Cer, ceramide; CTRL, control; IS, internal standard; LB, lamellar body; MUFA, monounsaturated fatty acid; SC, stratum corneum; SFA, saturated fatty acid; SG, stratum granulosum; TEWL, transepidermal water loss.\n\nFigure 2: Figure 2. Changes in lipid metabolism in ft/ft mouse epidermis. (a) Microarray analysis showing a subset of genes involved in FA metabolism in mouse epidermis. The full gene list and respective fold changes are provided in Table 3. (b) Relative mRNA level of Acox1 and Hsd17b4 in the epidermis of mice (n = 9–10). (c, d) Protein abundance of ACOX1 in mouse epidermis. The dashed line indicates the dermal‒epidermal boundary. Bar = 50 μm (e) ACOX activity measured in mouse epidermal cells (expressed as mU per μg of proteins, n = 5–7). Relative mRNA expression of (f) Acot5, Acot8, (g) Crot, and (h) PPAR mRNA, Ppar, isoforms in epidermal samples from CTRL and ft/ft mice (n = 9–10). Data were analyzed with a Student’s t-test. ∗P < 0.05, ∗∗P < 0.01, ∗∗∗P < 0.001, and ∗∗∗∗P < 0.0001. CTRL, control; FA, fatty acid; H2O2, hydrogen peroxide; PPAR, peroxisome proliferator–activated receptor.\n\nFigure 3: Figure 3. Enhanced PPARδ signaling in ft/ft mouse epidermis. Relative mRNA levels of (a) Tnfa, (b) Il1b, and (c) Fabp5 in CTRL and ft/ft mouse epidermis (n = 9–10). (d) Representative western blot and immunofluorescence staining showing FABP5 in the epidermis of ft/ft and CTRL mice. (e) Nuclear localization of FAPB5 protein in mouse epidermis. The mean fluorescence intensities of FABP5 located in the nuclei are shown and represented by the spectrum of pseudocolors, ascending from black to white (see Materials and Methods). The dashed line indicates the dermal‒epidermal boundary. Bar = 50 μm. Data were analyzed with a Student’s t-test. ∗P < 0.05, ∗∗P < 0.01, and ∗∗∗P < 0.001. CTRL, control; PPAR, peroxisome proliferator–activated receptor.\n\nFigure 4: Figure 4. Detection of ACOX1 in human AD skin and overexpression of ACOX1 in HEEs. (a, b) Representative immunostaining showing the protein abundance of ACOX1 in ADL) and in ADNL epidermis compared with the epidermis of healthy donors (CTRL). The dashed line indicates the dermal‒epidermal boundary. Bar = 30 μm. (c) Representative H&E staining of HEEs generated with KCs infected with lentivirus containing either pHR-SFFV-ACOX1 (ACOX1 OE) or pHR-SFFV-Puro CTRL(Puro) vector. Bar = 50 μm. (d) mRNA and (e, f) protein levels of ACOX1 in HEEs overexpressing ACOX1 compared with those in their Puro CTRLs (n = 8). The dashed line indicates the basal epidermal layer. Bar = 50 μm. Data were analyzed with a paired Student’s t-test. ∗∗∗P < 0.001. AD, atopic dermatitis; ADL, lesional atopic dermatitis; ADNL, nonlesional atopic dermatitis; CTRL, control; HEE, human epidermal equivalent; KC, keratinocyte.\n\nFigure 5: Figure 5. Analysis of HEEs overexpressing ACOX1. (a) Ultrastructural analysis showing LB secretion (upper panel, arrows), LB numbers (lower panel, arrows), and morphology (insets) in HEEs overexpressing ACOX1 (right panel) and in their Puro controls (left panel). Osmium tetroxide after fixation. Bar = 250 nm or 125 nm (inset). (b) LB numbers and (c) quantified secretion areas in HEEs in eight randomly selected fields per group (n = 2). (d) TEER and (e) LY penetration assay (green) in HEEs. Nuclei were counterstained with DAPI (blue). Bar = 50 μm. (n = 3). (f) Representative Ki-67 staining and the number of Ki-67‒positive nuclei in HEEs overexpressing ACOX1 compared with those in their Puro controls (n = 5). (g) Heat map showing the fold changes in the mRNA level of inflammation-related genes in HEEs (n = 5–7). Data were analyzed with a paired Student’s t-test. ∗∗P < 0.01 and ∗∗∗P < 0.001. HEE, human epidermal equivalent; LB, lamellar body; LY, Lucifer yellow; SC, stratum corneum; SG, stratum granulosum; TEER, transepithelial electrical resistance."
      }
    ]
  },
  {
    "id": "PMC8659757_multi_2",
    "image": [
      "images/PMC8659757-f6.png",
      "images/PMC8659757-f7.png",
      "images/PMC8659757-f8.png",
      "images/PMC8659757-f9.png",
      "images/PMC8659757-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Fatty Acid Oxidation and Glycolysis Are Triggered in Mouse Models of Lesional Atopic Dermatitis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Lipidomic analysis of HEEs overexpressing ACOX1. (a) d18:1 Cers(NS) (n = 3) and (b) FFA (n = 3) species in HEEs generated with KCs infected with lentivirus containing either pHR-SFFV-ACOX1 (ACOX1 OE) or pHR-SFFV-Puro control (Puro) vector. Data are shown as analyte/IS ratio (AU) per mg protein or as the relative percentage of total lipid species. Data were analyzed with a Student’s t-test. ∗P< 0.05. AU: arbitrary unit; Cer, ceramide; FFA, free fatty acid; HEE, human epidermal equivalent; IS, internal standard; KC, keratinocyte; MUFA, monounsaturated fatty acid; SFA, saturated fatty acid.\n\nFigure 7: Figure 7. Fatty acid synthesis and elongation in ft/ft mouse epidermis. (a) Relative mRNA levels of Fasn, Elov11, Elov4, and Elov6 in the epidermis of ft/ft mice compared with those in the epidermis of the CTRL mice (n = 9–10). (b) Representative western blot and immunostaining showing protein abundance of ELOVL1 in the epidermis of CTRL and ft/ft mice. (c) qPCR showing the relative mRNA level of Acox1 (left panel) and its protein abundance (right panel) in the epidermis of ft/ft mice uncovered (CTRL) or covered with an occlusive dressing to reduce TEWL (n = 5). The dashed line indicates the dermal‒epidermal boundary. Bar = 50 μm. Data were analyzed with a Student’s t-test. ∗P < 0.05 and ∗∗∗P < 0.001. CTRL, control; TEWL, transepidermal water loss.\n\nFigure 8: Figure 8. Analysis of the glycolytic pathway in the epidermis of ft/ft mice. (a) Relative mRNA levels of Glut isoforms and protein level of GLUT1 in the epidermis of CTRL and ft/ft mice (n = 9). Bar = 50 μm. (b) Immunostaining of GLUT1 in the epidermis of patients withADL and healthy donors (CTRL). The dashed line indicates the dermal‒epidermal boundary, and the continuous line denotes the SG‒SC interface. Bar = 30 μm. (c, d) Relative mRNA and protein levels of key glycolytic enzymes in mouse epidermis (n = 9–10). (e) Glucose and pyruvate consumption. (f) ATP level in the epidermis of CTRL and ft/ft mice (n = 5). (g) Relative mRNA level of key enzymes of the pentose phosphate pathway in mouse epidermis (n = 9–10). Data were analyzed with a Student’s t-test. ∗P < 0.05, ∗∗P < 0.01, ∗∗∗P < 0.001, and ∗∗∗∗P < 0.0001. AD, atopic dermatitis; ADL, lesional atopic dermatitis; ATP, adenosine triphosphate; CTRL, control; SC, stratum corneum; SG, stratum granulosum.\n\nFigure 9: Figure 9. Anaerobic glycolysis but not mitochondrial function is triggered in ft/ft mouse epidermis. (a) Lactate production and (b) relative mRNA level of Ldha in mouse epidermis (n = 5–9). (c) Intracellular levels of the intermediates of the Krebs cycle in mouse epidermis quantified by LC‒MS. Fold changes between the mean values of five mice per group are shown. The list of all quantified metabolites as well as respective fold changes are provided in Table 4. (d) Relative mRNA expression of Mpc1 and Mpc2 in the epidermis of CTRL and ft/ft mice (n = 5–9). (e) Relative mRNA level of Pdk1 in mouse epidermis (n = 9–10). (f) Activity of Cx I and of Cx II of the respiratory chain in mouse epidermal cells (n = 9–10). Relative mRNA level of (g) Acadvl and (h) Acad9 in the epidermis of mice (n = 9–10). (i) Activity of mitochondrial ACADL measured in epidermal cells of CTRL and ft/ft mice (n = 10). (j) Relative mRNA level of Cpt1a in mouse epidermis (n = 5–9). Data were analyzed with a Student’s t-test. ∗P < 0.05, ∗∗P < 0.01, and ∗∗∗P < 0.001. CTRL, control; Cx, complex; LC‒MS, liquid chromatography‒mass spectrometry; min, minute.\n\nFigure 10: Figure 10. Inhibition of glucose uptake in ft/ft mouse epidermis. (a) mRNA and (b) protein levels of GLUT1 in the epidermis of mice treated with WZB-117 or vehicle CTRL (n = 4). (c) mRNA levels of key enzymes of glycolysis and of (d) Ldha in the epidermis of mice treated with WZV-117 compared with that in vehicle-treated CTRLs (n = 4). (e) Representative H&E staining of ear sections (Bar = 100 μm) and measured epidermal thickness and (f) mRNA level of keratin 16, that is, K16, in the epidermis of ft/ft mice treated with WZB-117 or vehicle CTRL (n = 4). (g) Representative Ki-67 staining and number of Ki-67+ nuclei in the epidermis of WZB-117 and vehicle-treated mice. Bar = 50 μm. (h) Intracellular ATP levels and (i, j) mRNA levels of inflammatory cytokines in the epidermis of mice treated with WZB-117 or vehicle CTRL (n = 4). Data were analyzed with a Student’s t-test. ∗P < 0.05, ∗∗P < 0.01, and ∗∗∗P < 0.001. ATP, adenosine triphosphate; CTRL, control; K, keratin."
      }
    ]
  },
  {
    "id": "PMC8659757_multi_3",
    "image": [
      "images/PMC8659757-f11.png",
      "images/PMC8659757-f12.png",
      "images/PMC8659757-f13.png",
      "images/PMC8659757-f14.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Fatty Acid Oxidation and Glycolysis Are Triggered in Mouse Models of Lesional Atopic Dermatitis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Lipidomic analysis of Flg-KO mouse epidermis. Relative and total amounts of (a) d18:1 Cers(NS), (b) ω-O-acylCers (n = 5), (c) SFAs, and MUFAs in the epidermis of Flg-KO mice compared with those in the epidermis of CTRL mice (n = 5). Data are shown as analyte/IS ratio (AU) per mg protein or as the relative percentage of total lipid species. Data were analyzed with a Student’s t-test. ∗P < 0.05 and ∗∗∗P < 0.001. AU, arbitrary unit; Cer, ceramide; CTRL, control; Flg-KO, Flg-knockout; IS, internal standard; KO, knockout; MUFA, monounsaturated fatty acid; SFA, saturated fatty acid.\n\nFigure 12: Figure 12. Metabolic and ultrastructural analysis of Flg-KO mouse epidermis. (a) Microarray analysis showing fold changes of a subset of genes involved in FA metabolism in the epidermis of Flg-KO mice compared with those in the epidermis of CTRLs. (b) Relative Acox1 mRNA level (n = 10) and protein abundance as well as (c) ACOX activity in CTRL and Flg-KO mouse epidermis (n = 5). (d) Relative levels of PPAR mRNA, Ppar, isoforms in mouse epidermis (n = 10). (e) Ultrastructural analysis of Flg-KO mouse epidermis showing LB morphology and secretion (arrows). Osmium tetroxide after fixation. Bar = 250 nm. (f) Relative mRNA level of Glut1 in mouse epidermis (n = 5). (g) Glucose consumption and (d) lactate production by epidermal sheets of CTRL and Flg-KO mice (n = 5). (h) Intracellular levels of metabolites and Krebs cycle intermediates quantified by LC‒MS in the epidermis of Flg-KO mice compared with those in the epidermis of CTRLs. Fold changes between the mean values of five mice per group are shown (n = 5). Data were analyzed with a Student’s t-test. The list of genes featured on the array and of all quantified metabolites as well as respective fold changes are provided in Tables 3 and 4. CTRL, control; Flg-KO, Flg-knockout; KO, knockout; LB, lamellar body; LC‒MS, liquid chromatography‒mass spectrometry; PPAR, peroxisome proliferator–activated receptor; SC, stratum corneum; SG, stratum granulosum.\n\nFigure 13: Figure 13. MC903 mouse model of ADL (a) Representative H&E staining of ear sections (bar = 200 μm) of MC903-treated mice compared with that of the vehicle-treated CTRLS (n = 7) and (b) TEWL values measured on the ears of mice (n = 7). (c) qPCR and immunostaining showing mRNA and protein level of ACOX1 in the epidermis of mice treated with MC903 or vehicle. The dashed line indicates the dermal‒epidermal boundary. Bar = 50 μm. mRNA level of (d) Acot5; (e) Crot; (f) PPAR mRNA, Ppar, isoforms; and Fabp5 in the epidermis of mice treated with MC903 or vehicle (n = 7). (g) mRNA level and protein abundance of GLUT1 and (h) mRNA level of key enzymes of glycolysis as well as of (i) Ldha and Pdk1 in the epidermis of mice treated with MC903 or vehicle (n = 7). The dashed line indicates the dermal‒epidermal boundary. Bar = 50 μm. Data were analyzed with a Student’s t-test. ∗P < 0.05, ∗∗P < 0.01, ∗∗∗P < 0.001, and ∗∗∗∗P < 0.0001. ADL, lesional atopic dermatitis; CTRL, control; PPAR, peroxisome proliferator–activated receptor; TEWL, transepidermal water loss.\n\nFigure 14: Figure 14. IMQ mouse model and biopsies from patients with PSO. (a) Representative H&E staining of ear sections (bar = 200 μm) of mice treated with 5% IMQ cream or with petroleum jelly (CTRL) (n = 7) and (b) TEWL values measured on the ears of mice (n = 7). (c) qPCR and immunostaining showing mRNA and protein level of ACOX1 in the epidermis of mice treated with 5% IMQ or with petroleum jelly. The dashed line indicates the dermal‒epidermal boundary. Bar = 50 μm. (d) Immunostaining of ACOX1 in the epidermis of patients with PSO and healthy donors (CTRL). The dashed line indicates the dermal‒epidermal boundary. Bar = 30 μm. Data were analyzed with a Student’s t-test. ∗∗∗P < 0.001. CTRL, control; IMQ, imiquimod; PSO, psoriasis; TEWL, transepidermal water loss."
      }
    ]
  },
  {
    "id": "PMC8693007_multi",
    "image": [
      "images/PMC8693007-f1.png",
      "images/PMC8693007-f2.png",
      "images/PMC8693007-f3.png",
      "images/PMC8693007-f4.png",
      "images/PMC8693007-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"16pdel lipid changes in iPSC-derived neurons and function of FAM57B in lipid metabolism and synaptogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Augmented local field potential activity in 16pdel syndrome differentiated neuronal culture (A) Local Field Potential (LFP) summary analyzed by log2 fold change between control and 16pdel patient differentiated neurons. MEA activity was recorded over 30 min starting in media, followed by physiological and high potassium chloride (KCl) solution. Data was summarized and pooled from 3 experiments. Control n = 9 (media), n = 17 (Physiological Solution), n = 13 (High KCl Solution). 16pdel n = 35 (media), n = 76 (Physiological Solution), n = 35 (High KCl Solution). Violin plot group analysis: Control - 16pdel two-way ANOVA. ∗p ≤ 0.05. Technical experimental replicates n = 3. (B) Increased sex specific activity in female 16pdel probands drives overall increased LFPs, compared to unaffected controls. Media unaffected neurons (Control) male (♂) n = 3, Control female (♀) n = 6,16pdel neurons (Proband) ♂ n = 21, Proband ♀ n = 14, Physiological Solution Control ♂ n = 7, Control ♀ n = 10, Proband ♂ n = 38, Proband ♀ n = 38, High KCl Solution Control ♂ n = 6, Control ♀ n = 7, Proband ♂ n = 18, Proband ♀ n = 17. Violin plot analysis: male versus female ttest. ∗∗∗∗p ≤ 0.0001. (C) Increased sex specific female electrogenic burst frequency analyzed by log2 fold change between 16pdel male and female Media ♂ n = 21, ♀ n = 14, Physiological Solution ♂ n = 38, ♀ n = 38, High KCl Solution ♂ = 18, ♀ n = 17. Violin plot analysis: male versus female ttest. ∗p ≤ 0.05. Technical experimental replicates n = 3.\n\nFigure 2: Figure 2. Significant lipid changes between control and 16pdel differentiated neurons (A) Total log2 fold change from normalized peak area of lipid class analysis from untargeted lipidomics. Bolded and colored indicate statistically significant changes by T test, p ≤ 0.05–0.0001. AcCa acyl carnitine, AEA N-arachidonoylethanolamine, Cer ceramide, ChE cholesterol ester, Co coenzyme, DG diacylglycerol, Hex1Cer hexosylceramide, LPC lysophosphatiylcholine, LPE lysophosphatiylethanolamine, LPG lysophosphatiylglycerol, MG monoacylglycerol, PA phosphatidic acid, PC phosphatidylcholine, PE phosphatidylethanolamine, PG phosphatidylglycerol, PI phosphatidylinositol, PS phosphatidylserine, SM sphingomyelin, SPH sphingosine, TG triacylglycerol. (B) Total lipid composition analysis from untargeted lipidomics between control and 16pdel neuron. Chain Length: Small 1–5, Medium 6–12, Long 13–21, Very Long 22+, and Unresolved. (C–F) Selected analysis of lipid species from untargeted lipidomics classes. Lipid Class specified for each histogram (c - phosphatidylethanolamine, (D) ceramide, (E) monoacylglycerol, (F) triacylglycerol) normalized peak area between control (gray) and 16pdel (orange). Statistical analysis by two-Way ANOVA, ∗p ≤ 0.05 ∗∗p ≤ 0.01,∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. Control n = 10, 16pdel n= 69, error bars represent SEM. TG and PE long and very long chain species not shown as no significant differences were found by ANOVA. Technical experimental replicates n = 3.\n\nFigure 3: Figure 3. FAM57B interacts with CerS but does not have CerS activity (A) CerS2 activity assayed using C24:1-CoA in CerS2 KO HEK293T cells. Statistical analysis by ttest ∗p ≤ 0.05, ∗∗p ≤ 0.01, error bars SEM. Technical experimental replicates n = 3. (B) (Upper) Western blot analysis of total human FAM57B-Flag and CerS2-HA after transfection in HEK293T cells. Proteins were prepared from HEK293T cells overexpressing the indicated constructs. Anti-HA and anti-Flag are indicated. (Lower) CerS2 activity assayed using C24:1-CoA in HEK293T cells. GAPDH was used as a loading control. Statistical analysis by ttest ∗p ≤ 0.05, ∗∗p ≤ 0.01, error bars SEM. Technical experimental replicates n = 3. (C) (Upper) Western blot analysis of total human FAM57B-Flag, CerS5-HA and CerS6-HA after transfection in HEK293T cells. Proteins were prepared from cells overexpressing the indicated constructs. Anti-HA and anti-Flag are indicated. (Lower) CerS5 and CerS6 activity was assayed using C16:0-CoA in HEK293T cells. Anti-HA and anti-Flag are indicated. GAPDH was used as a loading control. Technical experimental replicates n = 4. (D) Total cell lysates were prepared from the co-transfected cells with FAM57B-Flag and CerS2, 5 or 6-HA constructs and solubilized with 1% NP-40. Total lysates (input) or proteins immuno-precipitated with anti-Flag M2 agarose (IP) were subjected to immunoblotting with anti-HA or anti-Flag antibodies. GAPDH was used as a loading control. Technical experimental replicates n = 3.\n\nFigure 4: Figure 4. Significant lipid changes in sphingolipids and glycerolipids between WT and FAM57B mutant human differentiated SH-SY5Y neuronal cells (A–C) Total log2 fold change from normalized peak area of lipid class analysis from untargeted lipidomics. (A) FAM57B KO– WT, (B) FAM57B HET– WT, (C) FAM57B KO–FAM57B HET. Bolded and colored indicate statistically significant changes by ttest, p ≤ 0.05–0.0001. AcCa acyl carnitine, Cer ceramide, ChE cholesterol ester, CL cardiolipin, Co coenzyme, DG diacylglycerol, HexCerHexosylceramide, LPC lysophosphatiylcholine, LPE lysophosphatiylethanolamine, MG monoacylglycerol, PC phosphatidylcholine, PE phosphatidylethanolamine, PG phosphatidylglycerol, PI phosphatidylinositol, PS phosphatidylserine, SM sphingomyelin, TG triacylglycerol. Technical experimental replicates n = 3. (D–G) Selected analysis of lipid species from untargeted lipidomics classes. Lipid Class specified for each histogram, normalized peak area between WT (black) FAM57B HET (orange) and FAM57B KO (blue). Statistical analysis by two-Way ANOVA, ∗p ≤ 0.05 ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. Color of asterisks indicate comparison between WT – HET (orange), WT – KO (blue), HET – KO (black). WT n = 3, FAM57B HET n= 3, FAM57B KO n = 3, error bars represent SEM. Experiment repeated twice; analysis was similar between two separate runs.\n\nFigure 5: Figure 5. FAM57B knockout human neurons indicate altered synaptic composition (A and B) Isolated synaptosome protein abundance changes between (A) FAM57B KO relative to WT and (B) FAM57B HET relative to WT (Log2 Fold). Labeled and colored indicating increased (purple) or decreased (green) abundance. Only the top 20 proteins of statistical significance were labeled in A and analyzed in C-E. WT n = 8, HET n = 10, KO n = 7. Technical experimental replicates n = 3. (C–E) Gene ontology analysis of statistically significant synaptosome isolated proteins (E) in FAM57B KO relative to WT. (E) gene ontology pie graphs of top 20 decreased protein groups of cellular components, molecular function, protein classes, biological processes and pathways.(F) gene ontology figure legend. (G) Analysis of synaptic markers from isolated synaptosomes between all 3 genotypes. Bolded are significantly decreased protein abundance of synaptic structural and maturation proteins, and vesicle regulation machinery. INA – WT - HET & WT - KO, RAB11B – HET - KO, STXBP1 – WT - HET & WT - KO, YWHAZ – WT - HET & WT - KO. two-Way ANOVA, p ≤ 0.05–0.0001. (F) Isolated synaptosome lipid abundance between FAM57B KO relative to WT. Bolded text and color (purple increased and green decreased) indicates statistically significant changes by ttest, p ≤ 0.05–0.01. n = 6 per genotype, technical experimental replicates n = 2. No statistically significant differences observed when comparing FAM57B HET to WT, nor FAM57B KO to FAM57B HET."
      }
    ]
  },
  {
    "id": "PMC8693007_multi_2",
    "image": [
      "images/PMC8693007-f6.png",
      "images/PMC8693007-f7.png",
      "images/PMC8693007-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"16pdel lipid changes in iPSC-derived neurons and function of FAM57B in lipid metabolism and synaptogenesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Significant lipid changes in ceramides and glycerols between AB and fam57b mut brain tissue (A) Total log2 fold change from normalized peak area of lipid class analysis from untargeted lipidomics. Bolded and colored indicate statistically significant changes by ttest, p ≤ 0.05–0.0001. AcCa acyl carnitine, Cer ceramide, ChE cholesterol ester, CL cardiolipin, Co coenzyme, DG diacylglycerol, HexCerHexosylceramide, LPC lysophosphatiylcholine, LPE lysophosphatiylethanolamine, MG monoacylglycerol, PC phosphatidylcholine, PE phosphatidylethanolamine, PG phosphatidylglycerol, PI phosphatidylinositol, PS phosphatidylserine, SM sphingomyelin, TG triacylglycerol. Technical experimental replicates n = 3. (B–H) Selected analysis of lipid species from untargeted lipidomics classes. Lipid Class specified for each histogram, normalized peak area between AB (gray) and fam57b mut (green). Statistical analysis by two-Way ANOVA, ∗p ≤ 0.05 ∗∗p ≤ 0.01,∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. AB n = 3, fam57b mut n= 3, error bars represent SEM. Experiment repeated twice, analysis was similar between two separate runs. Individual MG species between fam57b het to AB n.s. Not shown for space: two-Way ANOVA analysis of TG. Increase in TG (16:0_16:0_16:1) in fam57b het compared to AB (p ≤ 0.01).\n\nFigure 7: Figure 7. Loss of fam57b results in altered plasma membrane architecture early in development and decreased localization of Synaptotagmin family at the synapse later in development (A) Schematic of Cholera toxin-B-488 (CT-B) injection into hindbrain ventricle of embryo and flat-mounted midbrain region for imaging at 24 hpf. (B) Representative embryo midbrain imaging and quantification of CT-B labeling of AB compared to fam57b mut. Punctate CT-B labeling (arrows), actin marker phalloidin indicates labeling of CT-B at the plasma membrane, merged with DAPI. Quantification of puncta between WT (gray) and fam57b mut (green) CT-B (p ≤ 0.05) ttest. Scale bar = 5 μm. AB n = 16, fam57b mut n = 18. Error bars SEM, statistical analysis by ttest ∗p ≤ 0.05. Technical experimental replicates n = 4. (C) Representative embryo midbrain imaging and quantification of Duramycin-488 labeling of AB compared to fam57b mut. Punctate Duramycin labeling (arrows), actin marker phalloidin indicates labeling of Duramycin at the plasma membrane, merged with DAPI. Quantification of puncta between WT (gray) and fam57b mut (green) Duramycin PE staining (p ≤ 0.05) ttest. Scale bar = 5 μm. AB n = 8, fam57b mut n = 8. Error bars SEM, statistical analysis by ttest ∗p ≤ 0.05. Technical experimental replicates n = 3. (D) Schematic of membrane protein labeling biotinylation assay and processing for MS/MS in 7 dpf larvae brains. (E) Larvae brain total plasma membrane protein abundance changes between fam57b mut relative to AB (Log2 Fold). Statistically significant p ≤ 0.05–0.0001 proteins labeled, indicating increased (purple) or decreased (green) abundance. Lowest abundance membrane protein Synaptotagmin-1a (red box). n = 3 per genotype. (F) Representative slice of 7 dpf whole larva brain mount with Sytaptotagmin-1a (green), GAD65/67 (red) and Beta-actin (magenta). z stack composite image merged with DAPI. Forebrain and midbrain areas of diffused Syt-1 localization (white arrows). Anatomical differences noted throughout brain, including (1) optic tectum and (2) corpus cerebelli (red arrows). Scale bar = 10 μm. Technical experimental replicates n = 2. (G) Representative 7 dpf whole brain Western blot indicate no significant change in total Syt-1a protein levels between fam57b mut relative to AB. Zebrafish larvae brains pooled (20 per genotype). Syt-1a protein abundance normalized to Beta-Actin loading control, repeated twice. (H) Larvae brain total isolated synaptosome protein abundance changes between fam57b mut relative to AB (Log2 Fold). Statistically significant p ≤ 0.05–0.0001 proteins labeled, indicating increased (purple) or decreased (green) abundance. Low abundance Synaptotagmin-2a like protein (red box). n = 7 per genotype. Technical experimental replicates n = 2. (I and J) Gene ontology analysis of statistically significant larvae synaptosome isolated proteins (H) in fam57b mut relative to AB. (I) Gene ontology pie graphs of increased and decreased protein groups of cellular components, molecular function, protein classes, biological processes and pathways. (J) Gene ontology figure legend. (K) Analysis of Synaptotagmin family members from larvae isolated synaptosomes. Significantly decreased protein abundance of Syt1a and Syt2a by two-Way ANOVA, ∗∗p ≤ 0.01, ∗∗∗∗p ≤ 0.0001. (L) Analysis of Synaptotagmin family members from differentiated SH-SY5Y isolated synaptosomes between all 3 genotypes. Significantly decreased protein abundance of elongated ESYT1 by two-Way ANOVA, ∗p ≤ 0.05, ∗∗p ≤ 0.01. Error bars SEM. (M) Analysis of synaptic markers from larvae isolated synaptosomes. Significantly decreased protein abundance (bolded) of vesicle regulation machinery and glutamate receptor activity by two-Way ANOVA, ∗∗p ≤ 0.01, ∗∗∗∗p ≤ 0.0001.\n\nFigure 8: Figure 8. Decreased spontaneous brain activity and diminished behavioral response after stimuli presentation in fam57b mutants (A and B) Local field potential (LFP) recordings in unanesthetized live larvae at 7dpf. Brain localized LFP recordings were pooled for each larva. (A) Decreased average number, mean rate and inter-LFP interval (ILI) coefficient of variation of LFP in fam57b mut compared to AB (orange). No electrographic burst activity was identified in fam57b mut at standard 5 LFPs/100 ms. Decreased electrographic burst parameters, including duration, number of LFPs per burst, frequency and percentage at 3 LFPs/200ms (blue). (B) Decreased average electrographic burst network activity and frequency, defined as a minimum or 3 electrographic bursts between 2 electrodes simultaneously, in fam57b mut compared to AB (gray). AB n = 21, fam57b mut n = 24 over 6 experiments. Statistical significance by unpaired ttest, ∗p ≤0.05, ∗∗p ≤ 0.01,∗∗∗p ≤ 0.001,∗∗∗∗p ≤ 0.0001. Technical experimental replicates n = 7. (C) Representative LFP waveform in brain region, indicating smaller relative waveform in fam57b mut compared to AB. (D) Representative LFP raster plot over experimental time frame, indicating less overall activity in fam57b mut compared to AB. (E) Representative image of 7 dpf immersed in cooled agarose in contact with electrodes on 12-well CytoView MEA plate. (F) Startle response behavioral assay. Light source was removed for 5 s at 10 min intervals. Mean distance reported from tracked movement during 70 min assay. Decreased light startle response identified in fam57b mut compared to AB. Statistical analysis of each startle response by ttest ∗∗p ≤ 0.01, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. Error bars SEM. No overall significant change in movement outside of the startle identified. AB n = 125, fam57b mut n = 33 over 5 experiments. (G) Seizure response behavioral assay. Normalized (baseline recording subtracted) mean distance from tracked movement after absence or presence of pentylenetetrazol (PTZ) 0.5 mM and 5 mM. Significantly increased seizure-induced movement observed at 5mM in AB, while increased movement observed at 0.5 and 5 mM PTZ in fam57b mut. Diminished overall seizure-induced movement at 5 mM in fam57b mut compared to AB. Relative fold change compared to absence of PTZ indicated below histogram. Statistical analysis of each condition by ttest ∗p≤ 0.05, ∗∗∗p ≤ 0.001, ∗∗∗∗p ≤ 0.0001. Error bars SEM. AB n = 166 (0 mM), 92 (0.5 mM), 150 (5 mM), fam57b mut n = 91 (0 mM), 70 (0.5 mM), 56 (5mM) over 6 experiments. (H) Model proposing role of Fam57b activity in the brain. Loss of function in fam57b mutants indicates significant changes in plasma membrane lipid groups alter architecture of plasma membrane early the developing brain. Architectural changes indicated by increased lipid raft abundance and aggregation. Altered plasma membrane homeostasis results in mis-localization of synaptic proteins, including synaptotagmins, after maturation. Decreased spontaneous brain and network activity suggests diminished synaptic function and developed circuits. As evidence has suggested spontaneous network activity shapes synaptic development, this cycles back to declined neuronal maturation and circuitry. Molecular changes to synaptic function and decreased spontaneous brain activity translate to altered behavioral response after stimuli presentation."
      }
    ]
  },
  {
    "id": "PMC8698433_multi",
    "image": [
      "images/PMC8698433-f1.png",
      "images/PMC8698433-f2.png",
      "images/PMC8698433-f3.png",
      "images/PMC8698433-f4.png",
      "images/PMC8698433-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"N-Acetylcysteine Reverses the Mitochondrial Dysfunction Induced by Very Long-Chain Fatty Acids in Murine Oligodendrocyte Model of Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. C26:0 reduced cell survival and ATP production in a concentration-dependent manner. (A) Percentage of viable 158 N cells after incubation with C26:0 (0–100 µM) for 24 h are shown (A, n = 6). At concentrations of C26:0 equal to and higher than 25 µM, significant cell death was observed, ** p < 0.01, ANOVA followed by Dunnett’s test. The 1% ethanol group is shown as vehicle control. (B) Percentage of ATP content after incubation with C26:0 (0–50 µM) for 24 h (B, n = 6). At concentrations of C26:0 equal to and higher than 25 µM, a significant decrease in ATP production compared to ethanol control was observed, * p < 0.05, ** p < 0.01, ANOVA followed by Dunnett’s test. The equations of the standard curve were used to calculate the concentration of ATP per well and the results are expressed as a percentage of control.\n\nFigure 2: Figure 2. ROS levels in 158 N cells after incubation with C26:0 and NAC for 24 h were measured (n = 3) by H2DCFDA. No statistically significant change was observed between 1% ethanol control and 25 µM C26:0 treatment (t-test, p =0.17). Co-incubation of NAC (100–1000 µM) and 25 µM C26:0 treatment did not change cellular ROS levels.\n\nFigure 3: Figure 3. Total intracellular GSH (A) and mtGSH levels (B) in 158 N cells were measured after incubation with C26:0 and NAC for 24 h (n = 3). A) No statistically significant change in total GSH was observed between control and C26:0 (25 µM) (t-test, p = 0.99). Co-incubation of NAC (100–1000 µM) and 25 µM C26:0 treatment increased total GSH in a concentration-dependent manner (A; *** p < 0.001, ANOVA followed by Dunnett’s test). (B) Significant decrease in mtGSH was observed between control and C26:0 (25 µM) (t-test, ## p <0.01). Additional co-incubation of NAC (500 µM) restored mtGSH depleted by C26:0 (*** p < 0.001 indicates a significant increase in mtGSH with co-incubation of NAC compared to C26:0 (25 µM) treatment only; ANOVA followed by Bonferroni’s test). Moreover, mtGSH was increased to 2.2 ± 0.1-fold of control when cells were incubated with C26:0 (25 µM) for 18 h followed by NAC (500 µM) for 6 h. The 1% ethanol-treated cells served as control.\n\nFigure 4: Figure 4. C26:0 increased mitochondrial superoxide level which was mitigated by NAC. (A–D) Representative images of 158 N cells show an increase in MitoSOX fluorescence following treatment with C26:0 (0, 12.5 and 25 µM) for 24 h. Additional co-incubation of NAC (500 µM) notably decreased MitoSOX fluorescence, indicating reduced levels of mitochondrial superoxide formation in presence of NAC. Scale bar (-) in white represents 50 µm.\n\nFigure 5: Figure 5. C26:0 decreased mitochondrial inner membrane potential (∆ψm), which was alleviated by NAC. (A) Representative images of 158 N cells show an increase in JC-1 monomers (green fluorescence in dead cells) and corresponding decrease in JC-1 aggregates (red fluorescence in healthy cells) following C26:0 (0–50 µM) incubation for 24 h. Additional co-incubation of NAC increased red fluorescence and decreased green fluorescence, indicating restoration of ∆ψm. Scale bar (−) in white represents 50 µm. (B) Bar plot indicates quantification of JC-1 fluorescence in 96-well plates. The ∆ψm decreased significantly following incubation with C26:0 (25 µM and 50 µM) compared to control (*** p < 0.001, ANOVA followed by Dunnett’s test). This mitochondrial toxicity was reversed by NAC (# p < 0.05, ANOVA followed by Bonferroni’s test)."
      }
    ]
  },
  {
    "id": "PMC8698433_multi_2",
    "image": [
      "images/PMC8698433-f6.png",
      "images/PMC8698433-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"N-Acetylcysteine Reverses the Mitochondrial Dysfunction Induced by Very Long-Chain Fatty Acids in Murine Oligodendrocyte Model of Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. C26:0 increased sensitivity to additional oxidants such as acrolein in 158 N cells. Cell survival (in %) following treatments with C26:0 only (25 µM, 24 h), acrolein only (25 µM, 1 h), C26:0 (25 µM, 24 h) followed by acrolein (25 µM, 1 h), and C26:0 (25 µM)-NAC (500 µM) co-incubation for 24 h followed by acrolein (25 µM, 1 h) and control is shown. Cell survival was significantly reduced in all treated groups versus control (*** p < 0.001). Pre-treatment with C26:0 and subsequent incubation with acrolein at the same conditions profoundly decreased cell survival (56 ± 1.5%) compared to a single treatment of C26:0 or acrolein. Co-incubation of NAC with C26:0 before acrolein challenge increased the cell survival to 71 ± 3%, ## p < 0.01. Data were analyzed using ANOVA followed by Bonferroni’s test.\n\nFigure 7: Figure 7. A hypothetical model depicting C26:0 injury in oligodendrocytes leading to the depletion of mtGSH. The loss of mtGSH predisposed cells to oxidant injury resulting in increased ROS accumulation, alteration of mitochondria inner membrane potential (∆ψm), and finally cell death. NAC treatment prevented the mitochondrial toxicity of C26:0 by replenishing mtGSH and thus protected cells from additional oxidative stress and death."
      }
    ]
  },
  {
    "id": "PMC8759595_multi",
    "image": [
      "images/PMC8759595-f1.png",
      "images/PMC8759595-f2.png",
      "images/PMC8759595-f2-2.png",
      "images/PMC8759595-f4.png",
      "images/PMC8759595-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulating peroxisome–ER contacts via the ACBD5-VAPB tether by FFAT motif phosphorylation and GSK3β\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The ACBD5–VAPB interaction is sensitive to phosphatase treatment. (A) Immunoblots of lysates of FLAG-ACBD4 or -ACBD5 expressed in COS-7 cells with or without λPP, using conventional and Phos-tag SDS-PAGE. αTubulin/Myc (unspecific band) served as loading control. (B) Binding assay with recombinant GST-VAPB and FLAG-ACBD4/5 expressed in COS-7 cells ± λPP. Samples were immunoprecipitated (GST-TRAP) and immunoblotted using FLAG/VAPB antibodies. (C) Myc-ACBD5 was expressed in COS-7 cells, and lysates were treated ± λPP. Myc-ACBD5 was immunoprecipitated, and endogenous bound VAPB was detected by immunoblotting using Myc/VAPB antibodies. Data were analyzed by a two-tailed unpaired t test (n = 5). Total VAPB (IP fraction) was normalized against Myc-ACBD5 (IP fraction). (D) ACBD5 protein sequence. Phosphorylation sites identified by database search (Hornbeck et al., 2015; Ullah et al., 2016) and our own MS-based analyses are indicated (filled boxes). Colored boxes, protein domains (colors as in Fig. 2 A); bold regions, peptides identified by MS (−TiO2 and +TiO2). The FFAT-like motif is underlined. (E) The FFAT-like motif region of ACBD4 was replaced with that of ACBD5 (ACBD5 FFAT). FLAG-ACBD4/5 constructs were expressed in COS-7 cells and immunoprecipitated to detect endogenous bound VAPB using FLAG/VAPB antibodies. Data were analyzed by one-way ANOVA with Sidak’s multiple comparison test (n = 3). *, P < 0.05; **, P < 0.01; ***, P < 0.001. Total VAPB (IP fraction) was normalized against total VAPB (input) and FLAG-ACBD4/5 (IP fraction). Source data are available for this figure: SourceData F1.\n\nFigure 2: Figure 2. ACBD5–VAPB binding, but not ACBD4–VAPB interaction, is sensitive to phosphatase treatment. (A) FLAG-ACBD4/5 was expressed in COS-7 cells, and lysates were treated with or without λPP. FLAG-ACBD4/5 was immunoprecipitated, and endogenous bound VAPB was detected by immunoblotting using FLAG/VAPB antibodies. Constructs with mutations in the FFAT-like motif (mFFAT) were used as a negative control. (B) Schematic overview of replacement of the ACBD4 FFAT-like motif region (bold) by that of ACBD5. (C) Myc-ACBD5 phospho mutants were expressed in COS-7 cells and immunoprecipitated to detect endogenous bound VAPB using Myc/VAPB antibodies. Source data are available for this figure: SourceData FS1.\n\nFigure 2: Figure 2. Phospho mutants of the acidic tract alter the ACBD5–VAPB interaction and its phosphatase sensitivity. (A) Schematic overview of ACBD5 domain structure; amino acid sequences of the phosphorylation sites mutated in this study in bold. (B) Schematic model of the interaction between the ACBD5 FFAT-like motif and the VAPB MSP domain. The interaction occurs in two steps (Furuita et al., 2010): (1) Initial nonspecific electrostatic interaction between the FFAT acidic tract and the basic electropositive surface of the MSP domain; (2) specific binding of the FFAT core to the FFAT-binding site of the MSP domain, which consists of an electropositive face. (C–E) ACBD5 constructs with nonphosphorylatable (A) and phosphomimetic (E) residues in the acidic tract were expressed in COS-7 cells. The proteins were immunoprecipitated, and endogenous bound VAPB was detected by immunoblotting using Myc/VAPB antibodies. In C, data were analyzed by one-way ANOVA with Dunnett’s multiple comparison test. Total VAPB (IP fraction) was normalized against total VAPB (input) and Myc-ACBD5 (IP fraction). In D and E, lysates were treated ± λPP before IP. Data were analyzed by one-way ANOVA with Dunnett’s multiple comparison test (D) or a two-tailed unpaired t test (E). Total VAPB (IP fraction) was normalized against Myc-ACBD5 (IP fraction). VAPB signal in the treated sample was then calculated as a percentage of VAPB signal in the untreated sample. *, P < 0.05; ***, P < 0.001; ****, P < 0.0001. Results of at least three independent IPs were quantified. Source data are available for this figure: SourceData F2.\n\nFigure 4: Figure 4. Potential phosphorylation sites involved in the ACBD4/5–VAPB interaction. (A) Schematic overview of ACBD4 and ACBD5 domain structure, including the amino acid sequences of the FFAT-like motif region, with the phosphorylation sites mutated in this study in bold. (B) Alignment of the FFAT-like motif region of ACBD4 and ACBD5 from Hs, Homo sapiens (human); Rn, Rattus norvegicus (rat); Mm, Mus musculus (mouse); Cl, Canis lupus familiaris (dog); Fp, Falco peregrinus (falcon); Xt, Xenopus tropicalis (frog); and Dr, Danio rerio (zebrafish). Conservation of the phosphorylation sites reported in this study is indicated in bold. (C) Overview of the FFAT-like motif region of ACBD4 and ACBD5 and the constructs used in this study. Mutated residues are indicated in bold.\n\nFigure 5: Figure 5. ACBD4 phosphomimetic mutants increase VAPB interaction. (A) Subcellular localization of ACBD4/5 constructs. COS-7 cells transfected with Myc-ACBD5 WT, mFFAT, S269E, S259A/S261A/S263A, or ΔTMD; or FLAG-ACBD4 WT, S183E, or S166A/S169A/S171A, were immunolabeled with PEX14 (peroxisomal marker) and Myc/FLAG antibodies. Bars: 10 µm (main), 2.5 µm (insets). (B and C) ACBD4 constructs with nonphosphorylatable (S → A) and phosphomimetic (S → E) residues upstream (S166/S169/S171) or within the FFAT core (S183) were generated and expressed in COS-7 cells. The FLAG-tagged proteins were immunoprecipitated, and endogenous bound VAPB was detected by immunoblotting using FLAG/VAPB antibodies. (B) Data were analyzed by one-way ANOVA with Dunnett’s multiple comparison test (n = 5). Total VAPB (IP fraction) was normalized against total VAPB (input) and FLAG-ACBD4 (IP fraction). (D) Quantification of peroxisome morphology in Myc-ACBD5 (S269E)- or FLAG-ACBD4 (S183E)-transfected COS-7 cells. Data were analyzed by one-way ANOVA with Tukey’s multiple comparisons test. n = 400 per condition, from four replicates. *, P < 0.05; ****, P < 0.0001. TMD, transmembrane domain. Source data are available for this figure: SourceData FS3."
      }
    ]
  },
  {
    "id": "PMC8759595_multi_2",
    "image": [
      "images/PMC8759595-f3.png",
      "images/PMC8759595-f4-2.png",
      "images/PMC8759595-f5-2.png",
      "images/PMC8759595-f9.png",
      "images/PMC8759595-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Regulating peroxisome–ER contacts via the ACBD5-VAPB tether by FFAT motif phosphorylation and GSK3β\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 3: Figure 3. The serine in the FFAT core of ACBD5 is phosphorylated and inhibits VAPB binding. (A) ACBD5 constructs with nonphosphorylatable (A) and phosphomimetic (E) residues upstream (T252) or within the FFAT core (S269) were expressed in COS-7 cells. The proteins were immunoprecipitated, and endogenous bound VAPB was detected by immunoblotting using Myc/VAPB antibodies. Data were analyzed by one-way ANOVA with Dunnett’s multiple comparison test (n = 3). Total VAPB (IP fraction) was normalized against total VAPB (input) and Myc-ACBD5 (IP fraction). (B) The serine residue within the core of the ACBD5 FFAT-like motif (position 5, S269) binds VAPB in a hydrophobic pocket (Kaiser et al., 2005; Furuita et al., 2010). Phosphorylation (P) at this position likely causes steric hindrance, inhibiting the FFAT–VAPB interaction. (C) Lysates of COS-7 cells expressing Myc-ACBD5 were treated ± λPP before IP. Phosphorylation of ACBD5 at S269 was examined by immunoblotting using ACBD5 pS269/ACBD5 control/Myc antibodies. (D) Myc-ACBD5 WT, S269A phospho mutant, or control vector (Myc) was expressed in COS-7 cells. The proteins were immunoprecipitated, and phosphorylation of ACBD5 at S269 was examined by immunoblotting using ACBD5 pS269/ACBD5 control/Myc antibodies. (E) Myc-VAPB and FLAG-ACBD5 were immunoprecipitated from COS-7 cells separately and then incubated together to allow Myc-VAPB and FLAG-ACBD5 to interact. ACBD5 S269 phosphorylation in the VAPB-bound (IP) and non–VAPB-bound fractions were examined by immunoblotting using ACBD5 pS269/FLAG/Myc antibodies. Source data are available for this figure: SourceData F3.\n\nFigure 4: Figure 4. ACBD5 phospho-sites alter peroxisome–ER associations. (A) Representative electron micrographs of peroxisome–ER contacts in ACBD5 KO HeLa cells transfected with Myc-ACBD5 WT, S259A, S261A, S259A/S261A/S263A, S269E, or control vector (Myc). (B) Quantitative analysis of the mean population of peroxisomes associated with the ER. (C) Assessment of the mean peroxisome membrane surface in direct contact with the ER. Data were analyzed by one-way ANOVA with Dunnett’s multiple comparison test; *, P < 0.05; **, P < 0.01; ***, P < 0.001. Results of four grids per condition. (D) Immunoblots of cell lysates from ACBD5 KO HeLa cells expressing the indicated Myc-ACBD5 constructs. αTubulin/Myc (unspecific band) served as loading control. Bars: 200 nm. Source data are available for this figure: SourceData F4.\n\nFigure 5: Figure 5. GSK3β affects the ACBD5–VAPB interaction. (A) Myc-VAPB was expressed in the absence or presence of GSK3β in COS-7 cells. Myc-VAPB was immunoprecipitated, and endogenous bound ACBD5 and PTPIP51 were detected by immunoblotting using Myc/ACBD5/PTPIP51 antibodies. Results of three independent IPs were quantified. ACBD5/PTPIP51 (IP fraction) was normalized against total ACBD5/PTPIP51 (input) and Myc-VAPB (IP fraction). (B) FLAG-ACBD5 was expressed in HEK293T cells. Cells were treated with 10 µM CHIR (GSK3β inhibitor) or DMSO for 16 h. FLAG-ACBD5 was immunoprecipitated, and endogenous bound VAPB was detected by immunoblotting using FLAG/VAPB antibodies. Inhibition of GSK3β by CHIR was confirmed using GSK3β/GSK3β pY216/β-catenin antibodies (arrowhead indicates GSK3β). VAPB (IP fraction) was normalized against total VAPB (input) and FLAG-ACBD5 (IP fraction). n = 5–8 of three independent IPs. Data were analyzed by a two-tailed unpaired t test; **, P < 0.01; ***, P < 0.001. Source data are available for this figure: SourceData F5.\n\nFigure 9: Figure 9. GSK3β expression alters peroxisome morphology in MFF-deficient fibroblasts. (A) GSK3β expression increased phosphorylation of its substrate β-catenin, resulting in its degradation in COS-7 cells, as assessed by immunoblotting using GSK3β/GSK3β pY216/β-catenin/β-catenin pS33pS37 antibodies. GAPDH served as loading control. GSK3β K85A, catalytically inactive mutant. (B) Myc-VAPB WT or mMSP (K87D/M89D), a mutant that cannot bind FFAT motifs, was coexpressed with FLAG-ACBD5 (or control vector [FLAG]). Myc-VAPB was immunoprecipitated, and bound FLAG-ACBD5 was detected by immunoblotting using Myc/FLAG antibodies. (C) Peroxisome morphology in MFF-deficient fibroblasts expressing GSK3β. Fixed cells were immunolabeled with PEX14 (peroxisomal marker) and GSK3β antibodies. Data were analyzed by two-tailed unpaired t test; ****, P < 0.0001. n = 800 per condition, from two independent experiments. Bars: 10 µm. Source data are available for this figure: SourceData FS4.\n\nFigure 6: Figure 6. GSK3β associates with ACBD5 and VAPB. (A) GSK3β (S237E “mFFAT”) was coexpressed with FLAG-VAPB, FLAG-ACBD5 WT/mFFAT/ΔTMD, or control vector (FLAG) in COS-7 cells. FLAG-VAPB/ACBD5 were immunoprecipitated, and bound GSK3β and endogenous VAPB were detected by immunoblotting using FLAG/GSK3β/VAPB antibodies. Asterisk indicates unspecific band (due to reprobing of the blot). (B) GSK3β was coexpressed with FLAG-VAPB (K87D/M89D mMSP) or control vector (FLAG) in COS-7 cells. FLAG-VAPB was immunoprecipitated, and bound GSK3β and endogenous ACBD5 were detected by immunoblotting using FLAG/GSK3β/ACBD5 antibodies. (C) FLAG-ACBD5 constructs with nonphosphorylatable (A) residues in the acidic tract were coexpressed with GSK3β in COS-7 cells. FLAG-ACBD5 was immunoprecipitated, and phosphorylation at S269 (pS269) was detected by immunoblotting using ACBD5 pS269 and ACBD5 control antibodies. Bound GSK3β was detected by immunoblotting using ACBD5 control/GSK3β antibodies. GSK3β (IP fraction) was normalized against total GSK3β (input) and ACBD5 control (IP fraction). Data were analyzed by one-way ANOVA with Dunnett’s multiple comparison test (n = 3); ***, P < 0.001; ****, P < 0.0001. TMD, transmembrane domain. Source data are available for this figure: SourceData F6."
      }
    ]
  },
  {
    "id": "PMC8759595_multi_3",
    "image": [
      "images/PMC8759595-f7.png",
      "images/PMC8759595-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Regulating peroxisome–ER contacts via the ACBD5-VAPB tether by FFAT motif phosphorylation and GSK3β\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 7: Figure 7. GSK3β modulates the ACBD5–VAPB interaction via S269. (A) GSK3β (K85A) was coexpressed with Myc-ACBD5 WT or S269A in COS-7 cells. Myc-ACBD5 was immunoprecipitated, and endogenous bound VAPB was detected by immunoblotting using Myc/VAPB antibodies. VAPB (IP fraction) was normalized against total VAPB (input) and Myc-ACBD5 (IP fraction). Phosphorylation of ACBD5 S269 (pS269) was detected by immunoblotting using ACBD5 pS269/Myc antibodies. GSK3β catalytic (in)activity was confirmed using GSK3β/GSK3β pY216/β-catenin antibodies. Data were analyzed by one-way ANOVA with Tukey’s multiple comparisons test (n = 4). (B) Recombinant His-ACBD5 was incubated in the absence or presence of recombinant GST-GSK3β. Phosphorylation of ACBD5 at S269 was examined by immunoblotting using ACBD5 pS269/ACBD5 control antibodies. (C) Representative electron micrographs of peroxisome–ER contacts in COS-7 cells transfected with a catalytically inactive GSK3β (GSK3β K85A) or GSK3β WT. (D) Assessment of the mean peroxisome membrane surface in direct contact with the ER. Quantitative analysis of the mean population of peroxisomes associated with the ER. Data were analyzed by a two-tailed unpaired t test. Results of four grids per condition. *, P < 0.05; ***, P < 0.001; ****, P < 0.0001. Bars: 200 nm. Source data are available for this figure: SourceData F7.\n\nFigure 8: Figure 8. Model of ACBD5–VAPB interaction and regulation at the peroxisome–ER interface. Peroxisomal ACBD5 and ER-resident VAPB interact via the FFAT and MSP domains to enable peroxisome–ER contacts. The FFAT-MSP interaction involves the FFAT core (VYCDSME) and flanking acidic tract. ACBD5 phosphorylation (P) can promote (green, acidic tract) or inhibit (red, FFAT core) VAPB interaction. GSK3β regulates the ACBD5–VAPB interaction via phosphorylation of the serine in the FFAT core. ACB, acyl-CoA binding domain."
      }
    ]
  },
  {
    "id": "PMC8773697_multi",
    "image": [
      "images/PMC8773697-f1.png",
      "images/PMC8773697-f2.png",
      "images/PMC8773697-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Structure and Function of the ABCD1 Variant Database: 20 Years, 940 Pathogenic Variants, and 3400 Cases of Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Dandelion plot illustrating variant density in ABCD1 (density is indicated by height of dandelion). (A) All variants (pathogenic, benign, VUS, and synonymous) in the ABCD1 gene (open circles). The highest variant density is in exon 6 followed by exon 1. (B) Only pathogenic variants in the ABCD1 gene (red pins) are shown. The highest event burden and pathogenic variant density are in exon 1 followed by exon 6. (C) All pathogenic variants in exon 1.\n\nFigure 2: Figure 2. Missense variant density by chromosome position: (A) across the ABCD1 gene, (B) exon 1, (C) exon 2, (D) exon 6, (E) exon 8, and (F) exon 9. Exons are indicated in orange, the PEX19-binding site is indicated in blue, the transmembrane segments are indicated in green and Walker A and B and the ABC signature are indicated in red.\n\nFigure 3: Figure 3. The evolutionary conservation of each amino acid within the ABCD1 protein based multiple sequence alignment among 54 different species. The overall height of each symbol represents the relative frequency of each amino acid at that position. Positively charged amino acids (KRH) are in blue; negatively charged amino acids (DE) are in red. Exons are indicated in alternating blue–pink–blue, etc.; the PEX19-binding site is indicated in blue; the 6 transmembrane segments are indicated in green; Walker A and B and the ABC signature are indicated in orange. Error bars indicating an approximate Bayesian 95% confidence interval are indicated in grey."
      }
    ]
  },
  {
    "id": "PMC8807639_multi",
    "image": [
      "images/PMC8807639-f1.png",
      "images/PMC8807639-f2.png",
      "images/PMC8807639-f3.png",
      "images/PMC8807639-f4.png",
      "images/PMC8807639-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal ATP Uptake Is Provided by Two Adenine Nucleotide Transporters and the ABCD Transporters\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. C8:0 β-oxidation activity in wild-type and mutant yeast strains. (A) In yeast, β-oxidation of fatty acids occurs exclusively in peroxisomes requiring the import of fatty acids, ATP and CoA. Medium-chain fatty acids (C8–C12) enter yeast peroxisomes as free fatty acids and are subsequently activated to their corresponding CoA ester by the peroxisomal enzyme acyl-CoA synthetase Faa2p. This activation step is ATP and CoA dependent. For completeness, the acyl-CoA uptake route, not involved in the uptake of medium-chain fatty acids, and a yet to identify CoA transporter are depicted in gray. (B) Yeast cells were cultured overnight in oleate medium and β-oxidation rates were measured using [1–14C] labelled octanoate (C8:0) as substrate. Data are means ± SD of values from 5–18 independent experiments. Only most relevant statistic relations are indicated in Figure 1B, all are given in Supplementary Table S1. ****, ***, **, and * indicate significance with a p-value of p < 0.0001, p < 0.001, p < 0.01, and p < 0.05 respectively.\n\nFigure 2: Figure 2. ATP uptake into liposomes reconstituted with peroxisomal membranes purified from different yeast strains. Isolated peroxisomal membranes were reconstituted in proteoliposomes with no counter substrate (A), or pre-loaded with AMP (B) or ADP (C). Uptake of [α-32P]ATP was measured as described in Methods. Data are means ± SD of values from three independent experiments. Only most relevant statistic relations are indicated in Figure 2, all are given in Supplementary Table S1. ****, ***, **, and * indicate significance with a p-value of p < 0.0001, p < 0.001, p < 0.01, and p < 0.05 respectively and # indicates significant difference between ADP or no counter substrate.\n\nFigure 3: Figure 3. Comparison of ATP levels determined with FRET-based ATeam reporter proteins in wild-type and mutant yeast strains. Cells were transformed with the different ATeam reporter proteins, grown overnight in oleate medium and transferred to 25 mM MES buffer (pH 6.0) supplemented with 20 g/L glucose prior to measurements. (A) Peroxisomal ATP levels determined with reporter proteins ATeam-per and ATeam-per (mut) (B) ATP levels determined with reporter proteins ATeam-cyt and ATeam-cyt (mut). FRET was determined by measuring 527/475 nm. Ratios were calculated after subtraction of the background signal from wild-type cells transformed with an empty vector. The semi-relative ATP levels were then calculated by subtracting the 572/475 ratio of the ATeam(mut) reporter from the 572/475 of ATeam reporter. Data are means ± SD of values from 4–13 independent experiments. Only most relevant statistic relations are indicated in Figure 3, all are given in Supplementary Table S1. ****, ***, **, and * indicate significance with a p-value of p < 0.0001, p < 0.001, p < 0.01, and p < 0.05 respectively.\n\nFigure 4: Figure 4. Peroxisomal localisation of Aac2p using self-assembling GFP assay. Wild-type cells were transformed with GFP(1–10)-PTS1, GFP(11)-tagged Ant1p, Sco2p, or Aac2p, as well as RFP-PTS1 for confirmation of peroxisomal localisation. All cells were cultured overnight in ethanol medium. Images show bright field to visualize the localization of the cells (left); fluorescence of self-assembling GFP (GFP(1–10)-PTS1; left centre), RFP-PTS1 (right centre) and the overlay of bright field, self-assembling GFP and RFP-PTS1 (Merge; right).\n\nFigure 5: Figure 5. Quantification of cells with Ant1p, Aac2p or MTSAac2p located in the peroxisomal membrane. Wild-type cells co-expressing the indicated GFP(11)-tagged MCF protein and the peroxisomal GFP(1–10)-PTS1 protein were analyzed for the number of cells displaying punctated GFP fluorescence, resulting from the physical interaction between GFP(11)-tagged MCF proteins and the peroxisomal GFP(1–10)-PTS1 protein. Expressed as percentage of number of analyzed cells indicated next to the bars. A one-way ANOVA test with Tukey’s multiple comparisons test was performed. ***, **, and * indicate significance with a p-value of p < 0.001, p < 0.01, and p < 0.05 respectively."
      }
    ]
  },
  {
    "id": "PMC8807639_multi_2",
    "image": [
      "images/PMC8807639-f6.png",
      "images/PMC8807639-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Peroxisomal ATP Uptake Is Provided by Two Adenine Nucleotide Transporters and the ABCD Transporters\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. C8:0 β-oxidation activity and ATP levels in wild-type and mutant yeast strains expressing MTS-Aac2p. (A) Untransformed strains and the same strains expressing MTSAAC2 were cultured overnight in oleate medium and β-oxidation rates were measured using [1–14C] labelled octanoate (C8:0) as substrate. Data are means ± SD of values from 5–14 independent experiments. (B) Untransformed wild type and ant1Δ strains and the same strains expressing MTSAAC2 were transformed with ATeam-per or ATeam-per (mut) to determine relative peroxisomal ATP levels as described in legend of Figure 3. Data are means ± SD of values from 3–8 independent experiments. (C) Untransformed wild type and ant1Δ strains and the same strains expressing MTSAAC2p were transformed with ATeam-cyt and ATeam-cyt (mut) to determine relative cytosolic ATP levels as described in legend of Figure 3. Data are means ± SD of values from 2–11 independent experiments. Only most relevant statistic relations are indicated in Figure 6, all are given in Supplementary Table S1. ** and * indicate significance with a p-value of p < 0.01 and p < 0.05 respectively.\n\nFigure 7: Figure 7. C8:0 β-oxidation activity in wild-type and mutant yeast strains expressing human ABCD proteins. Wild-type and mutant strains, including ant1Δpxa1Δpxa2Δ strains expressing ABCD1, ABCD2, or ABCD3 were cultured overnight in oleate medium (A), ethanol medium (B) or oleate medium supplemented with 100 µM C22:0 (C). Fatty acid ß-oxidation activity was measured with [1–14C] labelled octanoate (C8:0) (A–C). (D) Wild-type and mutant strains, including ant1Δpxa1Δpxa2Δ strains expressing ABCD1 were transformed with ATeam-per and ATeam-per (mut) to allow quantification of peroxisomal ATP levels as described in legend of Figure 3. Cells were grown overnight in oleate medium or oleate medium supplemented with 100 µM C22:0. Data are means ± SD of values from 3–12 independent experiments. Only most relevant statistic relations are indicated in Figure 7, all are given in Supplementary Table S1. ****, ***, **, and * indicate significance with a p-value of respectively p < 0.0001, p < 0.001, p < 0.01, and p < 0.05."
      }
    ]
  },
  {
    "id": "PMC8826238_multi",
    "image": [
      "images/PMC8826238-f1.png",
      "images/PMC8826238-f2.png",
      "images/PMC8826238-f3.png",
      "images/PMC8826238-f4.png",
      "images/PMC8826238-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The Peroxisomal-CoA Synthetase MoPcs60 Is Important for Fatty Acid Metabolism and Infectious Growth of the Rice Blast Fungus\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Phylogenetic analysis, yeast complementation, and expression profiles of MoPCS60. (A) Phylogenetic trees of MoPcs60 proteins from different organisms were constructed using the CLUSTAL_W and MEGA 5.1 programs by the neighbor-joining method with 1000 bootstrap replicates. Species names and GenBank accession numbers are as follows: XP_003712086.1 (M. oryzae); OLN86417.1 (C. chlorophyti); XP_009223944.1 (G. tritici R3-111a-1); XP_009649893.1 (V. dahliae); NP_001438.1 (H. sapiens); NP_075243.1 (R. norvegicus); NP_001054304.1 (O. sativa); NP_190468.1 (A. thaliana); NP_009781 (S. cerevisiae). AKL and SKL: major PTS1 tripeptides, VMF: minor PTS1 tripeptides. The rice blast fungus was showed in bold. (B) MoPcs60 partially rescued the growth defect of the yeast ΔScpcs60 mutant. Serial dilutions of BY4741, ΔScpcs60, and ΔScpcs60 transformed with pYES2 or pYES2-MoPCS60 were grown on YPG (galactose) with 6 μg/ml adriamycin plates at 30°C for 3 days and then photographed. (C) qRT-PCR analyses the expression levels of MoPCS60 at different fungal developmental stages. RNA was extracted from hyphae cultured for 36 h (HY), conidia (CO), and rice leaves inoculated with the wild-type conidia for 8, 24, 36, 48 and 72 h, respectively. Error bars represent the standard deviations of three replicates.\n\nFigure 2: Figure 2. The ΔMopcs60 mutant is defective in pathogenicity. (A) Conidial suspensions were sprayed onto rice seedlings and examined at 5 dpi (days postinoculation) (Top). Lesion types were counted within an area of 4 cm2 leaf from each strain (Bottom). Error bars represent the standard deviations of three replicates; asterisk represents significant difference (*p < 0.01). (B) Conidial suspensions were inoculated onto detached barley leaves and examined at 5 dpi (Top). Diseased leaf area (Bottom) was analyzed by ImageJ (Media Cybernetics Inc., Shanghai, China). The percentage was represented by a box-dot-plot. Statistical analysis was performed using GraphPad Prism 8.0.1, and asterisk represents significant difference (*p < 0.01). (C) Detached rice sheaths were injected with conidial suspensions. IH types were counted and statistically analyzed at 32 hpi. Error bars represent the standard deviations of three replicates.\n\nFigure 3: Figure 3. Papillary callose deposits are not changed in the ΔMopcs60 mutant. (A) Aniline blue staining to visualize appressorium of the wild-type Guy11, ΔMopcs60 mutant, and the complemented transformant MoPCS60-C at 32 hpi on rice leaves. Bar = 5 μm. (B) Statistically analyzed the number of papillary callose deposits formed underneath appressoria. Error bars represent the standard deviations of three replicates.\n\nFigure 4: Figure 4. The ΔMopcs60 mutant shows defect in utilization of long-chain fatty acids. (A) The wild-type strain Guy11, ΔMopcs60 mutant, and the complemented transformant MoPCS60-C were grown on minimal medium and MM with butyrate (1 mM), laurate (1 mM), olive (1% w/v), and oleate (1 mM) as the sole carbon sources and incubated at 28°C for 7 days. (B) Statistical analysis of the growth rate of the indicated strains on different media. Error bars are standard deviations from three biological repeats, and asterisk represents significant differences at *p < 0.01.\n\nFigure 5: Figure 5. The ΔMoPcs60 mutant shows a decreased number of peroxisomes and an increased number of lipid droplets. (A) Peroxisomes were examined in tip (TH) and basal (BH) hyphae of Guy11, ΔMopcs60, and MoPCS60-C strains expressing RFP-Pts1 protein. Differential interference contrast (DIC) and fluorescent images were taken under a confocal microscope. Bar = 5 μm. (B) Statistically analyzed the number of peroxisomes in 1 × 103 μm from 20 fields of view in each strain and represented by a box-dot-plot. Statistical analysis was performed using GraphPad Prism 8.0.1, and asterisks represent significant differences at *p < 0.01. (C) Lipid droplets were examined in TH and BH of Guy11, ΔMopcs60, and MoPCS60-C strains stained by BODIPY 493/503. Bar = 5 μm. (D) Statistically analyzed the number of lipid droplets in 1 × 103 μm from 20 fields of view in each strain and represented by a box-dot-plot. Statistical analysis was performed using GraphPad Prism 8.0.1, and asterisks represent significant differences at *p < 0.01."
      }
    ]
  },
  {
    "id": "PMC8831076_multi",
    "image": [
      "images/PMC8831076-f1.png",
      "images/PMC8831076-f2.png",
      "images/PMC8831076-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The Key Role of Peroxisomes in Follicular Growth, Oocyte Maturation, Ovulation, and Steroid Biosynthesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Immunofluorescence analysis of peroxisomal biogenesis proteins in developing follicles and the corpus luteum. Primary, secondary, tertiary follicles, and corpus luteus were stained with PEX14, catalase, and MFP2 antibodies and with DAPI for cell nuclei. Primary follicles are presented in (a, e, i). Secondary follicles are presented in (b, f, j). Tertiary follicles are shown in (c, g, j), and the corpus luteum is presented in (d, h, j). Scale bars = 40 μm.\n\nFigure 2: Figure 2. Schematic representation of peroxisomal regulation during folliculogenesis. Folliculogenesis is initiated with primordial follicles, which develop into primary follicles, secondary follicles, tertiary follicles, and finally preovulatory follicles. Under an LH surge triggered by oestrogen positive feedback, ovulation occurs for fertilization. This consecutive and synchronized event is accompanied by peroxisomal regulation to maintain the ROS balance and ensure the β-oxidation reaction. The peroxisomal marker enzyme catalase and peroxisomal biogenesis factor are induced during follicular maturation, whereas SODs are downregulated. A suitable concentration of ROS during different stages of the follicular phase is fundamental for ensuring oocyte development and ovulation. In addition to antioxidation, the peroxisomal β-oxidative enzymes ABCD3 and MFP2 are induced during follicular maturation and provide sufficient ATP and nutrition for oocyte growth, the selection of dominant oocytes, and the degradation of excessive lipid toxicity to maintain the efficiency of fertilization. The up arrow means “upregulation” while the down arrow stands for “downregulation.”\n\nFigure 3: Figure 3. Possible mechanism of peroxisomal regulation during steroidogenesis. According to the literature, the steroidogenic pathway is disturbed under peroxisomal-deficient conditions. The underlying mechanism may at least partly involve inhibition of the rate-limiting enzyme StAR. Excessive oxidative stress caused by peroxisomal deficiency can directly lead to the inhibition of steroid synthesis; moreover, the mitochondrial membrane potential is disturbed under peroxisomal-deficient conditions, which deteriorates StAR-mediated cholesterol transport. The specific molecular mechanism of StAR inhibition needs to be clarified in the future. Additionally, the lipid structure and lipid composition of the cell membrane are closely related to the activity of adenylyl cyclase (AC) and G protein-coupled receptor signalling. We hypothesize that peroxisomes may be involved in upstream cell signalling for hormone production by regulating the membrane composition of steroidogenic cells. Red line stands for “inhibit” while black line means “promote.”"
      }
    ]
  },
  {
    "id": "PMC8840315_multi",
    "image": [
      "images/PMC8840315-f1.png",
      "images/PMC8840315-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Whole-exome sequencing confirms implication of VPS13D as a potential cause of progressive spastic ataxia\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Family pedigree and brain imaging. A Family Pedigree. B WES identified two variants in VPS13D gene [NM_015378.3] in trans in patient (II.4). The first one is a nonsense variant inherited from his mother (I.2): c.946C > T, p.Arg316*; the second one is a missense variant inherited from his father (I.1): c.12416C > T, p.(Ala4139Val). WT: wild-type. C Brain MRI sections with (C.a) midline sagittal T1 showing vermian atrophy, (C.b) axial T2 showing pontocerebellar and cerebellar atrophy, and (C.c) axial T2, showing frontal angioma therapy after-effects. (A) Anterior; (P) Posterior; (L) Left; (R) Right\n\nFigure 2: Figure 2. Patient skin fibroblasts display abnormal mitochondrial morphology and a reduction of mitochondrial complexes. A Representative images of mitochondrial network in 2 healthy subjects and patient fibroblasts stained with Green mitotracker®. 3D-Images projection were obtained using a Zeiss Vivatome microscope (objectives × 63, scale bar = 10 μm). B Quantification of mitochondrial morphology by calculating number of circular mitochondria (MT) per cell [8]. C Summed branch length were measured with Mitochondrial Network Analysis (MiNA) toolset ImageJ plug-ins [15]. Data are represented as mean ± SEM from 5 independent experiments with 80 to 100 cells. * p < 0.05, ** p < 0.01, **** p < 0.0001. (D-E) Evaluation of mitochondrial respiratory complex proteins quantity in patient fibroblasts. Western blot analyses of mitochondrial OXPHOS complex subunits in patient and control (ctrl1) fibroblasts using β-actin (Sigma) and VDAC1 (Porin, Abcam) as loading controls. Total OXPHOS Antibody Cocktail® (Abcam) contains: ATP synthase 5A (Complex V, 55 kDa), COX II (complex IV, 22 kDa), UQCRC2 (complex III, 48 kDa), SDHB (complex II, 30 kDa), and NDUFB8 (complex I, 18 kDa). Data are expressed as mean ± SEM from 8 independent experiments. Statistical analyses were performed with GraphPad Prism 7 using Mann Whitney test or 2 Way ANOVA multiple comparisons tests (GraphPad Software, Inc.)"
      }
    ]
  },
  {
    "id": "PMC8847483_multi",
    "image": [
      "images/PMC8847483-f1.png",
      "images/PMC8847483-f2.png",
      "images/PMC8847483-f3.png",
      "images/PMC8847483-f4.png",
      "images/PMC8847483-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Mice with a deficiency in Peroxisomal Membrane Protein 4 (PXMP4) display mild changes in hepatic lipid metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Generation and validation of PXMP4 knockout (Pxmp4−/−) mice. (A) Small intestinal Pxmp4 levels in wild type (Pparα+/+) and Pparα-deficient (Pparα−/−) mice; (B) Schematic representation of the Pxmp4 gene. A 19 bp deletion in exon 1 was introduced by targeted CRISPR/Cas9 gene editing resulting in a premature stop codon in exon 2; (C) Hepatic mRNA levels of Pxmp4; (D) Targeted proteomic analysis of PXMP4 protein in livers of Pxmp4−/− mice and wild type littermates (n = 5–6). The blue line represents the internal standard and the red line the endogenous levels of PXMP4. Data in figure (A) and (C) are represented as mean ± SD and statistical significance was tested by a t-test.\n\nFigure 2: Figure 2. Effect of PXMP4 deficiency on peroxisome function under standard chow conditions. (A) Plasma levels of the VLCFAs docosanoic acid (C22), lignoceric acid (C24) and hexacosanoic acid (C26); (B) Hepatic expression of genes involved in VLCFA oxidation; (C) Plasma levels of the BCFAs phytanic and pristanic acid; (D) Hepatic expression of genes involved in metabolism of BCFAs phytanic and pristanic acid; (E) Biliary unconjugated and conjugated bile acid concentrations; (F) Hepatic expression of genes involved in bile acid metabolism in Pxmp4−/− mice and wild type littermates (n = 5–6). Scatter plots represent individual data with a median ± IQR and statistical significance was tested by a Mann–Whitney test. Bar plots represent mean ± SD and significance was tested by the non-parametric one-way ANOVA (Kruskal–Wallis) test, followed by Mann–Whitney U tests.\n\nFigure 3: Figure 3. Effect of PXMP4 deficiency on stimulation of peroxisome function by FF. (A) Plasma levels of the VLCFAs docosanoic acid (C22), lignoceric acid (C24) and hexacosanoic acid (C26); (B) Hepatic expression of genes involved in VLCFA oxidation; (C) Plasma levels of phytanic and pristanic acid; (D) Hepatic expression of genes involved in metabolism of phytanic and pristanic acid; (E) Biliary unconjugated and conjugated bile acid concentrations; (F) Hepatic expression of genes involved in bile acid metabolism in Pxmp4−/− mice and wild type littermates (n = 5–6). Scatter plots represent individual data with a median ± IQR and statistical significance was tested by a Mann–Whitney test. Bar plots represent mean ± SD and significance was tested by the non-parametric one-way ANOVA (Kruskal–Wallis) test, followed by Mann–Whitney U tests.\n\nFigure 4: Figure 4. Effect of PXMP4 deficiency on metabolism of phytanic and pristanic acid. (A) Hepatic levels of phytanic and pristanic acid. Data is represented as individual data with a median ± IQR and statistical significance was tested by a Mann–Whitney test; (B) Hepatic expression of genes involved in metabolism of phytanic and pristanic acid in Pxmp4−/− mice and wild type littermates (n = 6–8). Data is represented as mean ± SD and significance was tested by the non-parametric one-way ANOVA (Kruskal–Wallis) test, followed by Mann–Whitney U tests.\n\nFigure 5: Figure 5. Effect of PXMP4 deficiency and phytol supplementation on the hepatic lipidome. (A) Partial Least Square (PLS) regression analysis; (B) Most important changed lipid species based on PLS-derived VIP scores; (C) Effect of PXMP4 deficiency and phytol supplementation on total hepatic TG levels; (D) Effect of PXMP4 deficiency and phytol supplementation on total hepatic TG(O) levels; (E) Effect of PXMP4 deficiency and phytol supplementation on the hepatic abundance of TG(O-60) species."
      }
    ]
  },
  {
    "id": "PMC8850801_multi",
    "image": [
      "images/PMC8850801-f1.png",
      "images/PMC8850801-f2.png",
      "images/PMC8850801-f3.png",
      "images/PMC8850801-f4.png",
      "images/PMC8850801-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Deletion of RNF186 expression suppresses diet-induced hepatic steatosis by regulating insulin activity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Hepatocyte RNF186 KO mice are protected from high-fat-diet (HFD)-induced obesity (A) The representative gross morphology of control and RNF186LKO mice after 18 weeks of the HFD (n = 7 per genotype). (B) Body weights of control and RNF186LKO mice were measured weekly from weeks 1–18 (n = 7 per genotype). (C) Fat body weight and lean body weight of control and RNF186LKO mice at 18 weeks of age fed the HFD (n = 7 per genotype). (D) Food intake of control and RNF186LKO mice fed with HFD (n = 7 per genotype). (E) Gross morphology of different fat tissue mass of control and RNF186LKO mice after 18 weeks of the HFD (n = 7 per genotype). (F–G) The weight of different fat pads in control and RNF186LKO mice (n = 7 per genotype). (H) H&E staining of epiWAT and subWAT of RNF186f/f and RNF186LKO mice; scare bars, 50 μm (n = 7 per genotype).Data are presented as means ± SEM ∗p < 0.05, ∗∗p < 0.01 by Student's test.\n\nFigure 2: Figure 2. Protection against hepatic steatosis in RNF186LKO mice (A and B) Representative results of (A) morphology, (B) H&E staining of sections (top panel), and Oil Red O staining (bottom panel) of livers from control and RNF186LKO mice after the 18-week HFD; scare bars, 50 μm (n = 7 per genotype). (C) The ratio of the liver weight to body weight in wild type and KO mice (n = 7 per genotype). (D and E) Hepatic (D) and serum (E) TG levels in control and RNF186LKO mice after 18 weeks of the HFD and following a 6-h fast (n = 7 per genotype). (F and G) Hepatic (F) and serum (G) TC levels in control and RNF186LKO mice after 18 weeks of the HFD and following a 6-h fast (n = 7 per genotype). (H) Serum NEFA levels in control and RNF186LKO mice after 18 weeks of the HFD and following a 6-h fast (n = 7 per genotype).Data are present as means ± SEM ∗p < 0.05, ∗∗p < 0.01 by Student's test.\n\nFigure 3: Figure 3. Ablation of RNF186 improves glucose tolerance and hepatic insulin tolerance (A) Blood glucose levels of control and RNF186LKO mice after 18 weeks of the HFD followed by a 6-h fast (n = 7 per genotype). (B) Serum insulin levels for control and RNF186LKO mice after 18 weeks of the HFD followed by a 6-h fast (n = 7 per genotype). (C–F) GTTs analyses were performed in control and KO mice after 4 (C), 8 (D), and 18 (E and F) weeks of the HFD (n = 6 per genotype). (G–H) PTTs (G) and ITTs (H) analyses were performed in control and KO mice after 18 weeks of the HFD (n = 6 per genotype).Data are present as means ± SEM ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001 by Student's test.\n\nFigure 4: Figure 4. RNF186 regulates hepatic TG content in a lipogenesis-dependent manner (A) Scatterplot of differentially expressed genes of RNA-seq in livers from RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 3 per genotype). (B) KEGG pathway analysis showing downregulated pathways by RNA-seq. (C) Heatmap showing the expression of genes involved in hepatic lipid metabolism of RNA-seq (n = 3 per genotype). (D and E) qPCR (D) and western blot (E) analysis of genes involved in lipogenesis and fatty acid transport in the liver of RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 5 per genotype). (F) qPCR analysis of genes involved in gluconeogenesis, lipogenesis, and fatty acid oxidation in the livers of RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 5 per genotype).Data are present as means ± SEM ∗p < 0.05, ∗∗p < 0.01 by Student's test.\n\nFigure 5: Figure 5. RNF186 deficiency ameliorates insulin tolerance induced by HFD (A) Western blot analysis of insulin-stimulated AKT and GSK-3β phosphorylation in liver of RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 4 per genotype). (B) Quantitation of the western blot data shown in (A). (C) Western blot analysis of insulin-stimulated AKT and GSK-3β phosphorylation in subWAT of RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 4 per genotype). (D) Quantitation of the western blot data shown in (C). (E) Western blot analysis of insulin-stimulated AKT and GSK-3β phosphorylation in epiWAT of RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 4 per genotype). (F) Quantitation of the western blot data shown in (E).Data are present as means ± SEM ns > 0.05, ∗p < 0.05, ∗∗p < 0.01 by one-way ANOVA."
      }
    ]
  },
  {
    "id": "PMC8850801_multi_2",
    "image": [
      "images/PMC8850801-f6.png",
      "images/PMC8850801-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Deletion of RNF186 expression suppresses diet-induced hepatic steatosis by regulating insulin activity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. RNF186 deficiency protects mice from HFD-induced hepatic inflammation (A) Hepatic deletion RNF186 decreased serum ALT and AST levels (n = 7 per genotype). (B) Serum TNFα levels for control and RNF186LKO mice after 18 weeks of the HFD followed by a 6-h fast (n = 7 per genotype). (C) Histological F4/80 staining in liver sections from RNF186f/f and RNF186LKO mice fed the HFD for 18 weeks; scare bars, 25 μm (n = 4 per genotype). (D) Western blot analysis of NF-κB protein and phosphorylation levels in liver of RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 5 per genotype). (E) qPCR analysis of genes involved in inflammation response in the livers of wild-type and RNF186LKO mice fed the HFD for 18 weeks (n = 5 per genotype). (F) Western blot analysis of the ER stress marker proteins IRE1 and eIF2α phosphorylation levels in livers of RNF186f/f and RNF186LKO mice after 18 weeks of the HFD (n = 5 per genotype).Data are present as means ± SEM ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001 by Student's test.\n\nFigure 7: Figure 7. Overexpression of RNF186 in the liver of C57BL/6J mice exacerbates lipid metabolism (A) Blood glucose level in control C57BL/6J mice injected with Ad-GFP or Ad-RNF186 9 days after injection under fasting conditions (n = 7 per group). (B) Change of hepatic TG levels in C57BL/6J mice infected with Ad-GFP or Ad-RNF186 after 9 days under fasting conditions (n = 7 per group). (C) Hepatic RNF186 overexpression significantly increased the liver weight in mice infected with Ad-RNF186 compared with the control mice. (D and E) Change of serum insulin (D) and TNFα (E) levels in C57BL/6J mice infected with Ad-GFP or Ad-RNF186 under fasting conditions (n = 7 per group) (F and G) GTTs (F) and ITTs (F) in control C57BL/6J mice injected with Ad-GFP or Ad-RNF186 5 days after injection (n = 5 per group). (H) Relative mRNA levels of genes involved in lipogenesis and gluconeogenesis in the liver of C57BL/6J mice infected with Ad-GFP or Ad-RNF186 (n = 5 per group). (I) Western-blot analysis of PPARγ and SCD1 in the liver of C57BL/6J mice infected with Ad-GFP or Ad-RNF186 (n = 5 per group). (J) qPCR analysis of genes involved in inflammation response in the liver of C57BL/6J mice infected with Ad-GFP or Ad-RNF186 (n = 5 per group).(I) Western-blot analysis of PPARγ and SCD1 in the liver of C57BL/6J mice infected with Ad-GFP or Ad-RNF186 (n = 5 per group). (K) IRE1 and eIF2α phosphorylation were analyzed by western blot in the liver of C57BL/6J mice infected with Ad-GFP or Ad-RNF186 (n = 5 per group).Data are present as means ± SEM ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001 by Student's test."
      }
    ]
  },
  {
    "id": "PMC8868334_multi",
    "image": [
      "images/PMC8868334-f1.png",
      "images/PMC8868334-f2.png",
      "images/PMC8868334-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Stress Response and Inter-Organelle Communication in Cellular Homeostasis and Aging\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Cellular responses to peroxisomal dysfunction. Impaired peroxisomal function elicits cellular responses such as the impaired ROS homeostasis, dysregulated lipid metabolism, mitochondrial dysfunction, altered gene expression, pexophagy, elevated ER stress, and apoptosis.\n\nFigure 2: Figure 2. Peroxisome-organelle membrane contact sites and their roles in organelle functions. Peroxisomes’ contact with mitochondria involves (1) peroxisomal Pex11 and mitochondrial Mdm34, (2) peroxisomal Pex34 and an unknown mitochondrial protein, (3) mitofusin Fzo1 on both peroxisome and mitochondria, and (4) peroxisomal ACBD2/ECI2 and mitochondrial TOMM20. The interaction between peroxisomes and the ER involves (1) peroxisomal ACBD5 and resident ER protein VAPB and (2) peroxisomal ABCD3 and ER protein ATF6α upon Ceapin treatment. In mammalian cells, the contact between peroxisomes and lysosomes involves phospholipid PI(4,5)P2 on the peroxisomal membrane and lysosomal Syt7. Abbreviations: Pex11, peroxin 11; Mdm34, mitochondrial distribution and morphology protein 34; Pex34, peroxin 34; Fzo1, mitofusin; ACBD2/ECI2, acyl-coenzyme A-binding domain or enoyl-CoA-δ isomerase 2; TOMM20, translocase of outer mitochondrial membrane 20; ACBD5, acyl-CoA binding domain-containing protein 5; VAPB, vesicle-associated membrane protein-associated protein B/C; ABCD3, ATP binding cassette subfamily D member 3; ATF6, activating transcription factor 6; PI(4,5)P2, phosphatidylinositol 4,5-bisphosphate; Syt7, synaptotagmin VII.\n\nFigure 3: Figure 3. Metabolic and molecular signaling pathways mediate peroxisome-organelle crosstalk in response to peroxisomal dysfunction. (1) Peroxisome-nucleus: Peroxisomal dysfunction activates nuclear gene transcription through the transcription factors PPARα, AP-1, or Hnf4. The accumulation of long-chain fatty acids (LCFAs) activates PPARα to upregulate LONP2 and CAT expression to restore peroxisomal function (Blue arrow). Elevated ROS activates JNK signaling and AP-1 to induce the transcription of the pro-inflammatory cytokine IL-6. Peroxisomal dysfunction activates Hnf4 through unknown mechanisms to induce the expression of lipase 3 (Lip3), which leads to excessive free fatty acids (FFA) in the cytoplasm. FFAs hyper-activate Hnf4 via a positive feedback loop. (2) Peroxisome-mitochondrion: Peroxisomal dysfunction causes mitochondrial swelling, mitochondrial ROS generation, mitochondrial DNA (mtDNA) damage, disruption of oxidative phosphorylation (OXPHOS), and decreased inner membrane potential. Excessive ROS and elevated VLCFA are the potential signaling molecules that mediate the peroxisome-mitochondrion crosstalk. Peroxisomal dysfunction decreases plasmalogen, resulting in the inhibition of mitochondrial fission. (3) Peroxisome-ER: Peroxisomal dysfunction activates PERK signaling through unknown mechanisms to increase the phosphorylation of eIF2α and ATF4 induction. (4) Peroxisome-lysosome: Peroxisomal dysfunction due to the loss of Acox1 decreases peroxisome-derived acetyl-CoA, resulting in Raptor acetylation and lysosome localization of mTOR, leading to ULK1 activation and elevated lipophagy. Abbreviations: PPARα, peroxisome proliferator activated receptor alpha; AP-1, activator protein-1; Hnf4, hepatocyte nuclear factor 4; LONP2, lon peptidase 2; CAT, catalase; upd3, unpaired 3; IL-6, interleukin 6; Lip3, lipase 3; ROS, reactive oxygen species; JNK, Jun N-terminal kinase; VLCFAs, very-long-chain fatty acids; PERK, protein kinase RNA-like endoplasmic reticulum kinase; eIF2α, eukaryotic translation initiation factor 2a, ATF4, activating transcription factor 4; mTOR, mechanistic target of rapamycin kinase; ULK1, Unc-51-like autophagy-activating kinase 1."
      }
    ]
  },
  {
    "id": "PMC8868494_multi",
    "image": [
      "images/PMC8868494-f1.png",
      "images/PMC8868494-f2.png",
      "images/PMC8868494-f3.png",
      "images/PMC8868494-f4.png",
      "images/PMC8868494-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"NRF2 Activation in Autophagy Defects Suppresses a Pharmacological Transactivation of the Nuclear Receptor FXR\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Autophagy inhibition impairs a pharmacological transactivation of FXR. (a) A schematic diagram of an experimental procedure in mice. 8- to 9-week-old male Atg7F/F and Atg7LKO mice were intraperitoneally injected with vehicle (0.1% DMSO in 4:1 ratio of PEG 400 and Tween 80) or GW4064, a synthetic FXR agonist (100 mg/kg BW) twice a day. 5 h after last injection, all mice were sacrificed to harvest livers whose total RNAs were isolated for qPCR analysis; (b) Hepatic expression levels of FXR target genes Shp, Slc17a4, Bsep, and SR-B1 were determined in Atg7F/F and Atg7LKO mice shown in panel (a) by qPCR analysis. n = 3–4 per group, * p < 0.05, ** p < 0.01 vs. Atg7F/F mice treated with vehicle. # p < 0.05, ## p < 0.01. Data represent mean ± s.e.m. and are plotted as fold change. Each dot indicates individual mouse. Statistics by two-tailed t-test; (c) A schematic diagram of an experimental procedure in AML12 cells, a mouse hepatocyte-derived cell line. AML12 cells were treated with bafilomycin A1 (BafA1: 0.1, 0.5, or 1 μM), a known autophagy inhibitor in the absence or presence of synthetic FXR agonists GW4064 (1 μM) or obeticholic acid (OCA, 10 μM) for 24 h. Vehicle is 0.1% DMSO. Total RNAs from these cells were prepared to perform qPCR analysis; (d,e) Expression levels of FXR target genes Shp, Akr1b7, and Slc17a4 were determined in AML12 cells shown in panel (c) by qPCR analysis. n = 3 per group; ** p < 0.01 vs. AML12 cells treated with vehicle; # p < 0.05; ## p < 0.01. Data represent mean ± s.e.m. and are plotted as fold change. Each dot indicates individual sample. Statistics by a two-tailed, unpaired Student t-test. BW, body weight.\n\nFigure 2: Figure 2. Sulforaphane treatment in a dose-dependent manner impairs a pharmacological transactivation of FXR. (a) A schematic diagram of an experimental procedure in AML12 cells. AML12 cells were treated with sulforaphane (SFN: 12.5, 25, or 50 μM), a small molecule of NRF2 activator in a dose-dependent manner in the absence or presence of synthetic FXR agonists (GW4064: 0.1, 0.5 or 1 μM; OCA: 1, 5 or 10 μM) for 24 h. Vehicle is 0.1% DMSO. Total RNAs from these cells were prepared to perform qPCR analysis; (b,c) Expression levels of NRF2 target genes Nqo1 and Hmox1 were determined in AML12 cells shown in panel (a) by qPCR analysis. n = 3 per group, ** p < 0.01 vs. AML12 cells treated with vehicle. ## p < 0.01 vs. AML12 cells treated with 1 μM GW4064. Data represent mean ± s.e.m. and are plotted as fold change. Each dot indicates an individual well; (d,e) Expression levels of FXR target genes Shp, Ark1b7, and Slc17a4 were determined in AML12 cells shown in panel (a) by qPCR analysis. n = 3 per group; * p < 0.05; ** p < 0.01 vs. AML12 cells treated with vehicle; ## p < 0.01. Data represent mean ± s.e.m. and are plotted as fold change. Each dot indicates individual sample. Statistics by a two-tailed, unpaired Student t-test. OCA, obeticholic acid.\n\nFigure 3: Figure 3. Sulforaphane treatment in a time-dependent manner impairs a pharmacological transactivation of FXR. (a) A schematic diagram of an experimental procedure in AML12 cells. AML12 cells were treated with sulforaphane (SFN: 25 μM), a small molecule of NRF2 activator in a time-dependent manner (6 h, 12 h, or 18 h) in the absence or presence of synthetic FXR agonists GW4064 (1 μM) or OCA (10 μM) for 24 h. Vehicle is 0.1% DMSO. Total RNAs from these cells were prepared to perform qPCR analysis; (b) Expression levels of NRF2 target genes Nqo1 and Hmox1 were determined in AML12 cells shown in panel (a) by qPCR analysis. ** p < 0.01 vs. AML12 cells treated with vehicle. ## p < 0.01 vs. AML12 cells treated with either GW4064 or OCA; (c,d) Expression levels of FXR target genes Shp, Akr1b7, and Slc17a4) were determined in AML12 cells shown in panel (a) by qPCR analysis. n = 3 per group; ** p < 0.01 vs. AML12 cells treated with vehicle; ## p < 0.01. Data represent mean ± s.e.m. and are plotted as fold change. Each dot indicates individual sample. Statistics by a two-tailed, unpaired Student t-test. OCA, obeticholic acid.\n\nFigure 4: Figure 4. NRF2 activation is sufficient for suppressing a pharmacological transactivation of FXR in vivo. (a) A schematic diagram of an experimental procedure in mice. 8- to 9-week-old male C57BL/6J wild-type (WT) mice were orally gavaged with vehicle or butylated hydroxyanisole (BHA, 200 mg/kg BW) once a day for 3 days. During the last 24 h, all mice were intraperitoneally injected with vehicle (0.1% DMSO in 4:1 ratio of PEG 400 and Tween 80) or GW4064, a synthetic FXR agonist (100 mg/kg BW) twice a day (first injection: 00:00 a.m., second injection: 12:00 p.m.). 5 h after last treatment, all mice were sacrificed to collect livers whose total RNAs were prepared for qPCR analysis; (b) Hepatic expression levels of FXR target genes Shp, Slc17a4, SR-B1, and Saa1 were determined shown in panel (a) by qPCR analysis. n = 8 per group, ** p < 0.01 vs. WT treated with vehicle. # p < 0.05, ## p < 0.01; (c) A schematic diagram of an experimental procedure in mice. 8–9-week-old male Alb-Cre/+ and Keap1LKO mice were intraperitoneally injected with vehicle (0.1% DMSO in 4:1 ratio of PEG 400 and Tween 80) or GW4064, a synthetic FXR agonist (100 mg/kg BW) twice a day. 5 h after the last injection, all mice were sacrificed to harvest livers whose total RNAs were isolated for qPCR analysis; (d) Hepatic expression levels of Keap1, NRF2 target genes (Nqo1 and Gsta1), FXR target genes (Akr1b7, Saa1, and SR-B1) were determined shown in panel (c) by qPCR analysis. n = 4 per group; ** p < 0.01 vs. Alb-Cre/+ treated with vehicle; ## p < 0.01. Data represent mean ± s.e.m. and are plotted as fold change. Each dot indicates individual sample. Statistics by a two-tailed, unpaired Student t-test.\n\nFigure 5: Figure 5. NRF2 is necessary for BHA-mediated suppression of a pharmacological transactivation of FXR. (a) A schematic diagram of an experimental procedure in mice. 8- to 9-week-old male Nrf2F/F and Nrf2LKO mice were orally gavaged with vehicle or butylated hydroxyanisole (BHA, 200 mg/kg BW) once a day for 3 days. During the last 24 h, all mice were intraperitoneally injected with vehicle (0.1% DMSO in 4:1 ratio of PEG 400 and Tween 80) or GW4064, a synthetic FXR agonist (100 mg/kg BW) twice a day (first injection: 00:00 a.m., second injection: 12:00 p.m.). 5 h after last treatment, all mice were sacrificed to collect livers whose total RNAs were prepared for qPCR analysis; (b) Hepatic expression levels of Nrf2, its target genes Nqo1 and Gsta1, and FXR target gene Akr1b7 were determined shown in panel (a) by qPCR analysis. n = 3–4 per group, ** p < 0.01 vs. Nrf2F/F treated with vehicle. # p < 0.05, ## p < 0.01; (c) Cell-based reporter assays. AML12 cells were transiently transfected with a 2× PLTP luciferase reporter construct (2× PLTP-pTK-Luc), CMX-β-galactosidase, and expression plasmids of FXR and RXRα. After 24 h of transfection, cells were treated with either GW4064 (1 μM), 9-cis retinoic acid (9-cis RA, 1 μM), obeticholic acid (OCA, 10 μM) or both of GW4064 (or OCA) and 9-cis RA in the presence or absence of sulforaphane (SFN, 12.5, 25, or 50 μM) in a dose-dependent manner for 24 h. Vehicle is 0.1% DMSO; Normalized values (luciferase activity/β-galactosidase acidity) of vehicle-treated cells were set as fold 1; ** p < 0.01 vs. vehicle; # p < 0.05; ## p < 0.01. Data represent mean ± s.e.m. and are plotted as fold change. Each dot indicates individual sample. Statistics by a two-tailed, unpaired Student t-test."
      }
    ]
  },
  {
    "id": "PMC8876468_multi",
    "image": [
      "images/PMC8876468-f1.png",
      "images/PMC8876468-f2.png",
      "images/PMC8876468-f3.png",
      "images/PMC8876468-f4.png",
      "images/PMC8876468-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Renal tubular peroxisomes are dispensable for normal kidney function\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Relative Pex5 mRNA expression in kidneys of Ctrlm, cKOm, Ctrlf, and cKOf mice (n = 5–9). One hundred percent corresponds to the mean of Pex5 mRNA expression in kidneys of Ctrlm mice. (B) Western blot analysis of PEX5 protein expression in kidneys of cKOm and cKOf or of Ctrlf and cKOf mice. (C) Kidney weights of Ctrlm, cKOm, Ctrlf, and cKOf mice (n = 12–13). (D) Kidney weight/body weight ratio for Ctrlm, cKOm, Ctrlf, and cKOf mice (n = 5–6). Box and whiskers represent mean ± SEM; unpaired t test, ***P < 0.0001, *P < 0.05. The original full-length Western blot images for B are shown in Supplemental Figure 9.\n\nFigure 2: Figure 2. (A–D) Electron microscopy images of kidney proximal tubules in kidney cortex of Ctrlm (A), Ctrlf (B), cKOm (C), and cKOf (D) mice. The images are representative of 4 mice/genotype with 15 images analyzed/mice. White arrowheads indicate peroxisomes.\n\nFigure 3: Figure 3. (A) Number of peroxisomes/μm2 of cytoplasm; (B) fractional volume of peroxisomes in percentage of cytoplasm occupied by peroxisomes; (C) number of mitochondria/μm2 of cytoplasm; (D) fractional volume of mitochondria in percentage of cytoplasm occupied by mitochondria; (E) number of lysosomes/μm2 of cytoplasm; (F) fractional volume of lysosomes in percentage of cytoplasm occupied by lysosomes; (G) cell width. P = 0.083 (G). Stereology analysis was performed on n = 3–4 mice with 3 kidney cortex pieces per mouse, 15 micrographs per sample. Box and whiskers represent mean ± SEM; unpaired t test, ***P < 0.0001, **P < 0.001, *P < 0.05.\n\nFigure 4: Figure 4. (A and B) Volcano plot representing the relative transcriptional expression of all renal transcripts in cKOm versus Ctrlm (A) or cKOf versus Ctrlf (B). Transcripts depicted in blue are significantly downregulated while transcripts depicted in red are significantly upregulated. (C) Venn diagrams showing the number of transcripts significantly downregulated or upregulated in cKOm (in blue) or cKOf (in pink) mice versus Ctrl mice of the same sex. A significant transcript regulation is considered when the adjusted P value referred to as “FDR” is <0.05. (D) Enrichment analysis of a homemade gene set (based on the KEGG pathway mmu04146) targeting 100 transcripts related to peroxisomal functions, in cKOm versus Ctrlm mice. (E and F) Scatter plot of the top 25 most downregulated (E) or upregulated (F) metabolic pathways in cKOm versus Ctrlm mice, based on an untargeted GSEA using a database of 543 KEGG metabolic pathways. Pathways are sorted by their absolute normalized enrichment score. A significant pathway regulation can be considered when adjusted P value referred to as “q value” is <0.2.\n\nFigure 5: Figure 5. (A) Venn diagrams representing the number of detected renal metabolites showing a significantly decreased or increased abundance in cKOm (in blue) or cKOf (in pink) mice versus Ctrl mice of the same sex. (B) Volcano plot representing the relative abundance of all detected metabolites in kidneys of cKOm versus Ctrlm. Metabolites depicted with blue dots are significantly less abundant, and transcripts depicted with red dots are significantly more abundant in kidneys of cKOm mice as compared with Ctrlm mice. The names of some representative metabolites are depicted using colors shared for related metabolites. (C and D) Heatmaps of metabolites showing a significantly decreased (C) or increased (D) abundance in cKO mice of both sexes as compared with Ctrl mice. A significant difference of abundance is considered when adjusted P value from a 2-way ANOVA referred to as “FDR” is <0.05. Metabolites are identified by their biochemical name and sorted by related metabolisms and subclasses of metabolites. For each metabolite, the individual expression of 6 Ctrl and 6 cKO mice normalized between 0 and 1 and the log2-transformed mean fold change of expression (Log2FC) in cKO versus Ctrl mice are given, for both sexes. For calculation of the mean FC of expression, missing values (depicted in gray) have been replaced by the minimum value of both genotypes from the same sex."
      }
    ]
  },
  {
    "id": "PMC8876468_multi_2",
    "image": [
      "images/PMC8876468-f6.png",
      "images/PMC8876468-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Renal tubular peroxisomes are dispensable for normal kidney function\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. (A and B) Scatter plot of significantly downregulated (A) or upregulated (B) metabolic pathways, based on a joint pathway analysis of both regulated transcripts and modulated metabolites in kidneys of cKOm versus Ctrlm mice. Pathways are sorted by their absolute impact, and a significant pathway regulation is considered when adjusted P value referred to as “FDR” is <0.1. The size of each dot depends on the percentage of all transcripts and metabolites (“compounds”) of the pathway that are significantly affected in cKOm mice. (C and D) Relative expression of glutathione-related transcripts (C) and metabolites (D) significantly less abundant (FDR < 0.05) in cKOm mice as compared with Ctrlm mice. (E and F) Relative expression of glutathione-related transcripts (E) and metabolites (F) significantly more abundant (FDR < 0.05) in cKOm mice as compared with Ctrlm mice. Individual values from 6 cKOm and 6 Ctrlm mice are depicted after transformation from raw individual data: values of metabolite abundance have been divided by the median value of both genotypes, while values of transcript expression from both genotypes have been normalized between 0 and 1. Box and whiskers represent the mean and the SEM, respectively. ND, not detected.\n\nFigure 7: Figure 7. (A) Gross morphological structure and Oil Red O staining of neutral lipid depositions (in red) in the kidney of cKOm and Ctrlm adult mice fed under HFD for 4 weeks. The absence of the red color indicates the absence of lipid deposition. (B) Results of a Trolox assay performed on renal extracts showing nonenzymatic antioxidant capacity (left panel) and total antioxidant capacity (right panel) of Ctrlm and cKOm mice fed under control diet (CD) or HFD for 4 weeks. (C) Immunoblot performed on renal extracts targeting the product of lipid peroxidation malondialdehyde (left panel) and its quantification (right panel) in Ctrlm and cKOm mice fed under CD or HFD for 4 weeks. DJ-1 immunoblot is used as a loading control to normalize malondialdehyde abundance. (D) Amount of 4-HNE measured by competitive ELISA in kidney extracts from Ctrlm and cKOm mice fed under CD or HFD for 4 weeks. Box and whiskers represent mean ± SEM. Two-way ANOVA and post hoc Tukey’s multiple comparisons test, *P < 0.05."
      }
    ]
  },
  {
    "id": "PMC8919083_multi",
    "image": [
      "images/PMC8919083-f1.png",
      "images/PMC8919083-f2.png",
      "images/PMC8919083-f3.png",
      "images/PMC8919083-f4.png",
      "images/PMC8919083-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Insights Into the Peroxisomal Protein Inventory of Zebrafish\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Overview of the screening of the Danio rerio proteome to identify candidate proteins with a C-terminal peroxisomal targeting sequence (PTS1). See Materials and Methods for details.\n\nFigure 2: Figure 2. Schematic overview of the predicted molecular machineries and D. rerio proteins localized at the membranes of peroxisomes in zebrafish. See text for further details. Matrix protein import: after synthesis on free ribosomes, cargo proteins containing the peroxisomal targeting signals PTS1 or PTS2 bind to the corresponding cytosolic receptors Pex5 (E7FGF7) or Pex7 (A8KBW8) (Pex-proteins are indicated as sole numbers) and form receptor–cargo complexes. The Pex7–cargo complex requires accessory factors for import (e.g., Pex5L, a long isoform of Pex5). Import is achieved by a complex set of integral or peripheral PMPs that form the matrix protein import machinery, which mediates docking of the cargo-bound import receptor at the peroxisomal membrane [Pex13 (Q6PFQ3), Pex14 (A0A2R8QMZ2)], cargo translocation into the matrix of the organelle by a dynamic translocon [Pex2 (E7F4V8), Pex10 (Q5XJ92), Pex12 (B0R157)], and export of the receptor back to the cytosol [Pex1 (A0A0R4IPF0), Pex6 (F1QMB0)]. Recycling of the receptor involves its ubiquitination (Ub) and extraction from the membrane by an AAA–ATPase complex (Pex1, Pex6). Pex6 binds to the membrane protein Pex26 (F1RBL0). Membrane assembly and insertion of PMPs (containing an mPTS) depend on Pex19 (F1R313), Pex3 (Q5RIV3), and Pex16 (F1RDG2). Pex19 functions as a cycling receptor/chaperone, which binds the PMPs in the cytosol and interacts with Pex3 at the peroxisomal membrane. Proliferation, growth and division: Pex11α (A3QJY9), Pex11β (Q0P453), and Pex11γ (Q4V8Z0) are involved in the regulation of peroxisome size and number (proliferation). Pex11β remodels the peroxisomal membrane and interacts with the membrane adaptors Mff (F1Q877; A8E7S0) and Fis1 (A0A2R8Q8G0), which recruit the dynamin 1-like fission GTPase Dnm1l to peroxisomes, which in mammals is activated by Pex11β. Motility: mammalian peroxisomes move along microtubules, and Miro/Rhot (Rhot1a, Q6NVC5; Rhot1b, A0A0R4IGX0; Rhot2, Q32LU1) serves as membrane adaptor for the microtubule-dependent motor proteins kinesin and dynein. Tethering: Acbd5 (E9QCH6; A5WV69) and Acbd4 (F1QA31) interact with ER-resident Vap (Vapb, Q6P2B0) to mediate peroxisome–ER contacts. Metabolite transport: uptake of fatty acids in D. rerio peroxisomes is mediated by ABC transporter proteins (Abcd1, F1RBC8; Abcd2, E7F973; Abcd3a, A0A0R4IRL4; Abcd3b, B0UY91). Other peroxisomal transporter and membrane proteins in zebrafish include (functions are in part unclear): PMP34 (Slc25a17) (A5D6T2), a peroxisomal CoA transporter; PMP52 (Tmem135) (A4QN71) and PMP24 (Pxmp4) (A0A2R8QFW3) belong to the Tim17 family of transporters; PMP22 (Pxmp2) (Q66HU7); Slc27a2/4 (F1QQC5, Q1ECW0; Q567D7), acyl-CoA synthetase long chain family member; Marc (A0A2R8PWS6), mitochondrial amidoxime reducing component; Atad1 (A0A2R8RM20, B2GP29), ATPase family AAA (ATPase associated with various cellular activities) domain-containing protein 1 with a potential role in dislocation/quality control of tail-anchored membrane proteins; Aldh3a2 (A0A2R8PW97, E9QH31), fatty aldehyde dehydrogenase; Far1/2 (A0A0R4ICF6/Q1L8Q4), fatty acyl-CoA reductase 1/2 (ether lipid biosynthesis); Mavs (F1REK4), mitochondrial antiviral signalling protein with a putative role in innate immune response; Trim37 (E7FBZ8), tripartite motif-containing protein 37, an E3 ubiquitin-protein ligase involved in Pex5 mediated peroxisomal matrix protein import; Usp30 (A2BGT0), ubiquitin-specific protease 30, a deubiquitinase involved in the turnover of peroxisomes; Pnpla8 (F1RE62), Patatin-like phospholipase domain-containing 8. Proteins with a potential dual localization to both peroxisomes and mitochondria are marked with an asterisk. Pex, peroxin; PMP, peroxisomal membrane protein (adapted from Islinger et al., 2018, but containing the zebrafish specific nomenclature).\n\nFigure 3: Figure 3. Schematic representation of the pathways of fatty acid β-oxidation (A), ether phospholipid synthesis (B) and purine catabolism (C) in peroxisomes. (A) Peroxisomes degrade fatty acids in four consecutive steps: (1) oxidation, (2) hydration, (3) dehydrogenation, and (4) thiolytic cleavage. Step 1 is performed by multiple acyl-CoA oxidases (1-n) with different substrate specificities. Steps 2 and 3 involve two bifunctional proteins (L-BP, D-BP) harbouring both enoyl-CoA hydratase and 3-hydroxy-acyl-CoA dehydrogenase activity. Step 4 requires different thiolases (e.g., ACAA1, SCPx). Peroxisomes have acquired a set of accessory enzymes (e.g., for fatty acid α-oxidation) to transform the acyl-CoA esters of those fatty acids (FA), which cannot directly enter the β-oxidation pathway (e.g., phytanic acid) (see text for details). (B) The first three steps of ether phospholipid synthesis take place in peroxisomes; synthesis continues in the endoplasmic reticulum (ER). (C) Enzymes involved in purine catabolism in different vertebrate groups and their excretion products. Note that the cellular localisation (cytosolic, peroxisomal) of these enzymes varies amongst vertebrate species. Xanthine oxidase is cytosolic (Cyt) in H. sapiens (Hs) and D. rerio (Dr). Urate oxidase, HIUase, OHCU decarboxylase, and allantoicase are supposed to localise to peroxisomes (PO) in D. rerio, but are absent in H. sapiens (asterisks) (see also Table 1). Allantoinase is cytosolic in D. rerio, but absent in H. sapiens (asterisks). AADHAPR, alkyl-dihydroxyacetone phosphate reductase; ADHAPS, alkyl-dihydroxyacetone phosphate synthase; DHAP, dihydroxyacetone phosphate; DHAPAT, dihydroxyacetone phosphate acyltransferase; FAR1/2, fatty acyl-CoA reductases 1/2; HIUase, 5-hydroxyisourate hydrolase; OHCU decarboxylase, 2-oxo-4-hydroxy-4-carboxy-5-ureidoimidazoline decarboxylase (adapted from Islinger et al., 2010).\n\nFigure 4: Figure 4. Comparison of PTS1 motifs between D. rerio and H. sapiens: To depict the difference in the average abundance of amino acids at different positions of the PTS1 in fish (A) and humans (B), we selected proteins from each species, which were predicted to harbour a PTS1 (Neuberger et al., 2003), and depicted them as WebLogo (http://weblogo.threeplusone.com/create.cgi). (C) A comparison of the numerical values of the PTS1-predictions for those proteins is plotted for H. sapiens (x-axis) and D. rerio (y-axis) and depicted relative to the threshold for the evaluation of targeted proteins (>0, red) or the “twilight zone” (–10 < x < 0, grey); proteins with negative prediction are highlighted. (D) Systematic overview of orthologous fish proteins, which were either not found in D. rerio (ZADH2/PTGR3) or lack a PTS1 (Usp-L, long isoform; Prdx-5). (+) or (–) indicate presence or absence of the protein; 2x indicates 2 variants; traditional PTS1 identified (green) or not found (red); non-canonical PTS1 (yellow). (E) Schematic representation of the two isoforms of ubiquitin carboxyl-terminal hydrolase 2 (USP2) in H. sapiens (blue) and D. rerio (red). No PTS1 was found in the long isoform of Usp2 (Usp2-L). (F) Schematic representation of the two isoforms of peroxiredoxin-5 (Prdx-5) in H. sapiens (green) and D. rerio (orange). The long variant harbours an additional mitochondrial targeting signal, whereas the C-terminal sequence is identical. (G,H) Sequence comparison of the C-terminal end of USP2 orthologues (G) and PRDX5-orthologues (H). The loss of the PTS1 in Usp2-L is unique for D. rerio, whereas the PTS1 of human PRDX5 is found only in more ancient fish species.\n\nFigure 5: Figure 5. Verification of PTS1 functionality for selected candidate proteins. COS-7 cells were transfected with an EGFP fusion protein containing the C-terminal putative PTS1 of D. rerio Cdc5l DLLMLDKQTLSSKI (A), D. rerio Kctd5a DLKAKILQEQGSRM (B), and H. sapiens CDC5L DLLLEKETLKSKF (C). Cells were processed for immunofluorescence microscopy using anti-PMP70 (red) as a peroxisomal marker. White arrows highlight peroxisomes that are clearly detectable in both channels. Bars, 10 μm (A,C), 20 μm (B)."
      }
    ]
  },
  {
    "id": "PMC8927733_multi",
    "image": [
      "images/PMC8927733-f1.png",
      "images/PMC8927733-f2.png",
      "images/PMC8927733-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Ether Lipids in Obesity: From Cells to Population Studies\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Chemical structure of alkyl-, alkenyl- and mono-alkyl-ether lipids. Diacyl phospholipid and triacylglycerol exhibits typical structure of a glycerol-lipids.\n\nFigure 2: Figure 2. Biosynthetic and catabolic pathways of ether lipids: The formation of fatty alcohol by FAR1 and FAR2 in the peroxisome is the rate-limiting step: Metabolites are shown in blue and red: DHAP, dihydroxyacetonephosphate; G3P; glycerol-3- phosphate GPC, glycerophospho-choline; GPE, glycerophospho-ethanolamine; PC(O), Alkyl-phosphatidylcholine; PE(O), Alkyl-phosphatidylethanolamine; PC(P), PC plasmalogen, PE(P), PE Plasmalogen; LPC(P), Lyso-PC Plasmalogen; LPE(P), Lyso_PE Plasmalogen. Enzymes are shown in orange squares: DHAPAT, DHAP acyltransferase; ADHAP-S, alkyl- dihydroxyacetone phosphate synthase; AADHAPR, acyl/alkyl dihydroxyacetone phosphate reductase; AAG3PAT, acyl/alkyl-glycero-3- phosphate acyltransferase; PH, phosphohydrolase; AG kinase, alkylglycerol kinase; δδ1 Desaturase, plasmanyl-ethanolamine delta1-desaturase; C-PT, choline phosphotransferase; E-PT, ethanolamine phosphotransferase; PEMT, phosphatidylethanolamine N-methyltransferase; PLC, phospholipase C; CoA-IT, coenzyme A-independent transacylase; i-phospholipase A2, calcium independent phospholipase A2; TMEM86B, lysoplasmalogenase; FAR1, fatty acyl-CoA reductase 1; FAR2, fatty acyl-CoA reductase 2.\n\nFigure 3: Figure 3. Possible role of plasmalogens in adipose tissue metabolism and function in the setting of obesity. Obesity is characterised by enlarged adipocytes and severe lipid dysregulation, including reduced plasmalogens. Decreased plasmalogen levels impedes the normal function and size of adipocytes, further exacerbating the metabolic complications associated with obesity. Conversely, increasing plasmalogen levels via dietary supplementation appears to revert the effects of obesity on adipocytes by restoring their size and function. UCP1, uncoupling protein 1. Created with Biorender.com (2021)."
      }
    ]
  },
  {
    "id": "PMC8927814_multi",
    "image": [
      "images/PMC8927814-f1.png",
      "images/PMC8927814-f2.png",
      "images/PMC8927814-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"USP30: Structure, Emerging Physiological Role, and Target Inhibition\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Structure, regulation, and molecular characteristics of USP30. (A) Domain structure and post-translational modification sites of USP30. (B) Crystal structure of USP30 complexed with K6-di-Ub. Ubiquitin molecules are shown with a transparent surface in light yellow. The catalytic triad is shown in red. (C) The ubiquitin Phe4 patches contacting a hydrophobic surface of USP30 near its catalytic triad. (D) Coordination of β1–β2 strands and USP30 thumb and palm domains to form hydrogen bonds. (E) Cartoon model to illustrate the preference of USP30 for the cleavage of K6-di-Ub.\n\nFigure 2: Figure 2. USP30 antagonizes the ubiquitination process of mitochondria and peroxisome to prevent their autophagy. (A) USP30 prevents the activation of Parkin and the ubiquitination of mitochondria and then antagonizes mitophagy under the depolarization condition. (B) USP30 also limits the pexophagy through reversing the ubiquitination of peroxisome by PEX2.\n\nFigure 3: Figure 3. The development process and chemical structure of USP30 inhibitors. (A) The first small natural compound S3 was screened from 300 compounds in the cellular level. USP30i is a novel compound. Also, compound 39 is a benzosulphon amide compound characterized from a series of compounds reported in a previous study. (B) The racemic phenylalanine derivative compound 1 was identified from high-throughput screening, and MF-094, MF-095, and FT-385 were found based on the structure relationship study of the analogs derived from compound 1. (C) The cyano-amide containing small-molecule USP30Inh-1, USP30Inh-2, and USP30Inh-3 was synthesized based on the compound structure reported in a previous patent."
      }
    ]
  },
  {
    "id": "PMC8955265_multi",
    "image": [
      "images/PMC8955265-f1.png",
      "images/PMC8955265-f2.png",
      "images/PMC8955265-f3.png",
      "images/PMC8955265-f4.png",
      "images/PMC8955265-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Systematic Discovery of FBXW7-Binding Phosphodegrons Highlights Mitogen-Activated Protein Kinases as Important Regulators of Intracellular Protein Levels\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Design and validation of the protein degradation assay used for FBXW7 phosphodegron discovery. (A) The assay concept is based on elevated degradation of an EGFP-fused degradation probe upon heterologous FBXW7 expression. The probe contains a MAPK binding D(ocking)-motif (D-motif) to allow selective kinase recruitment and the putative FBXW7 binding phosphodegron (Target). EGFP fluorescence signal is compared to the DsRed signal, and similar expression of DsRed and the EGFP-probe is ensured by the internal ribosome entry site (IRES) between these two gene products. If the phosphodegron motif is functional, the EGFP/DsRed fluorescence signal ratio is expected to drop from 1 to a lower value. The target motifs that were used for the validation of the assay are shown with their kinase phosphorylation target sites (S/TP) highlighted in bold. CycEco (cyclinE C-terminal optimized degron) is a modified motif in which a glycine residue was modified to proline, shown in red, to make it compatible for MAPK-mediated double-phosphorylation. (B) Steady-state CycECO-V5 protein levels after inhibiting the proteosome (+MG132) or translation (+cycloheximide). Panels show the results of MG132 (10 µM) or cycloheximide treatment (100 µg/mL) using western blots. HEK293T cells were transfected with empty plasmid (control) or with the FBXW7α expression plasmid (+FBXW7) and the level of the CycECO chimera was monitored using an anti-V5 antibody after drug treatment in time. (C) CycEco-EGFP probe degradation is blocked by a proteosome inhibitor (MG132). (D) Intact phosphorylation target sites are required for probe degradation. WT: wild type; TA mutant: the phosphorylatable residues at position 0 (P0) or P + 4 are replaced by alanines (A). (E) Phosphodegron mediated degradation depends on MAPK recruitment for MYC, PGC1A, and SOX9 derived motifs, but CycECO mediated degradation was unaffected. (F) Kinase inhibitor treatment confirmed that, apart from CycECO, MAP kinases (ERK1/2 and p38) contribute to probe degradation. HEK293T cells (Control) were transfected with the FBXW7α expression plasmid and were untreated (+FBXW7) or incubated with a mix of ERK1/2- (SCH772984; 2 µM) and p38-specific (SB202190; 2 µM) inhibitors (+FBXW7 + p38/ERK inhibitors). (G) Performance of known FBXW7 binding motifs. In addition to CycECO, 9 out of 10 motifs were tested positive, where +FBXW7/control protein level ratio was lower than 1 (shown in black). Panel C-F show relative protein levels normalized to the EGFP/DsRed ratio determined for the degron probe when only an empty vector without FBXW7 cDNA was transfected (control). The basal EGFP/DsRed ratio was about 1 for all constructs tested (shown with a red line). Error bars show SD based on three independent experiments. Statistical significance was calculated based on two-tailed paired Student’s t-test (*: p < 0.05; **: p < 0.01; ***: p < 0.001).\n\nFigure 2: Figure 2. Refinement of the FBXW7 phosphodegron consensus. (A) Mutational analysis with the CycECO degron. The relative protein level of the CycECO probe was monitored in HEK293T cells (where the EGFP/DsRed ratio measured in FBXW7 plasmid transfected cells was normalized to the EGFP/DsRed ratio of control cells, where the latter were not transfected by the FBXW7 expression plasmid). Amino acid replacements/changes compared to the TPPQSP core motif are shown in red. (B) The scheme of the hierarchic strategy that coupled sequence pattern-based motif identification from the disordered part of the human proteome with experimental testing of chosen motifs in the ratiometric EGFP/DsRed degradation assay. The underlined residues denote the P0 position in the degron motif. (C) Experimental testing of putative motifs identified 19 novel phosphodegrons (ordered from strong to weak). (D) Sequence logo created based on all formerly known positive and the newly found 19 human positive phosphodegrons (see Supplementary Table S2). (E) Position of strictly restricted, restricted, and less/not restricted phosphodegron regions in the FBXW7(WD40)-CCNE peptide complex (PDB ID: 2OVQ) [12]. The crystallographic model of the WD40 domain bound to the CCNE peptide (LPSGLLpTPPQpSG) is shown from the side on the left panel, while the panel on the right shows a zoomed-in view of the structure from the top; peptide regions are colored as on Panel D; N denotes N-terminus and C denotes C-terminus. The core TPP sequence of the CCNE peptide is shown in stick representation and is colored in salmon. Notice how the proline in P + 1 snugly fits between W425 and R465 on this otherwise shallow protein–protein interaction surface. In addition, P + 2 may be important in positioning the phosphorylated serine (pS) by constraining the peptide backbone. The WD40 domain is shown with surface representation where contact residues (R465, R479, R505, and W425 are shown in stick representation and are colored in cyan). H-bond contacts between peptide atoms and protein residues are shown with black dashed lines.\n\nFigure 3: Figure 3. Newly identified phosphodegrons bind to FBXW7 with nanomolar affinity. (A) The scheme of the position–relaxation model describing FBXW7 binding phosphodegron motifs. The structural panel shows the crystal structure of the FBXW7(WD40)-CCNE peptide complex (PDB ID: 2OVQ) highlighting the different motif positions (from P − 3 to P + 4). The optimal sequence pattern, shown in the middle, was defined based on the analysis shown on Figure 2. Motifs with a relaxed position, namely with a sub-optimal amino acid, are shown below. The motif sequence newly identified in this study are shown in red, while known motifs are shown in black; motifs are listed according to the different position–relaxation model classes (see Supplementary Table S2). Note that motifs that deviate from the optimal pattern in more than one position may still bind, albeit with weaker affinity (e.g., JUN and JUNB). (B) Results of quantitative protein–peptide binding assays based on measuring fluorescence polarization. The first panel shows the result of the direct titration experiment with the fluorescently labeled CCNE peptide and increasing amounts of the Skp1-FBXW7 complex. Further panels show the results of competitive binding experiments where the binding of the fluorescently labeled CCNE peptide was competed off by different unlabeled peptides shown on the right (pT: phosphor-threonine and pS: phosphor-serine).\n\nFigure 4: Figure 4. Phosphodegrons in full-length proteins. (A) Intact phosphodegron-FXWB7 binding is essential for the regulation of full-length protein levels. The level of full-length proteins containing an FBXW7 interacting phosphodegron were analyzed by the EGFP/DsRed ratiometric assay in HEK293T cells 48 h after transfection with empty plasmid (Control), or with the expression plasmid for wild-type (WT) or mutated FBXW7 (Arg Mut: three arginine amino acids mutated in the WD40 domain important for phosphodegron-FBXW7 binding). (B) Similar experiment to Panel A, but protein levels were monitored by western blots. Each full-length protein construct was expressed with a V5-tag and the heterologously expressed FBXW7 constructs had a FLAG-tag. Anti-tubulin was used as the load control. (C) FBXW7-mediated degradation of the full-length protein constructs are inhibited by the MG132 proteosomal inhibitor. Western blot analysis was conducted similarly to Panel B. (D) Phosphorylation of the phosphodegron motifs in full-length protein constructs is essential for their FBXW7 mediated degradation. The experiment was carried out similarly as shown on Panel A. Control: co-transfection with intact full-length protein constructs and empty FBXW7 expression vector; FL (WT degron): co-transfection with intact phosphodegron motif containing full-length constructs and wild-type FBXW7; FL (TA Mut degron): co-transfection with mutated phosphodegron motif (two phosphorylatable residues replaced with alanines) containing full-length constructs and wild-type FBXW7. Relative protein levels show the EGFP/DsRed ratio for the different full-length constructs. Error bars show SD based on three independent experiments. Statistical significance was calculated based on two-tailed, paired Student’s t-test (*: p < 0.05; **: p < 0.01; ***: p < 0.001).\n\nFigure 5: Figure 5. Effects of kinase inhibitors on FBXW7-mediated protein degradation. The ratiometric DsRed/EGFP protein level assay was used to monitor the effects of kinase inhibitor treatments on the level of four different phosphodegron containing full-length proteins in HEK293T cells: JAZF1, ARID4B, ETV5, and ZMIZ1. Inhibitors (CHR99021, GSK3 inhibitor; SCH772984, ERK1/2 inhibitor; SB202190, p38α/β inhibitor; JNK-IN-8, JNK1-3 inhibitor) were added in 2 µM concentration 6 h before DsRed/EGFP measurements. EV: cells transfected with empty vector; Control: cells transfected with the wild-type FBXW7 expression plasmid. Relative protein levels show the EGFP/DsRed ratio for the different full-length constructs. Error bars show SD based on three independent experiments. Statistical significance was calculated based on two-tailed, paired Student’s t-test (*: p < 0.05; **: p < 0.01; ***: p < 0.001)."
      }
    ]
  },
  {
    "id": "PMC8955265_multi_2",
    "image": [
      "images/PMC8955265-f6.png",
      "images/PMC8955265-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Systematic Discovery of FBXW7-Binding Phosphodegrons Highlights Mitogen-Activated Protein Kinases as Important Regulators of Intracellular Protein Levels\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Regulation of JAZF1-SUZ12 fusion protein level by p38-FBXW7 partnership. (A) Scheme of JAZF1 fusions known to be associated with endometrial stromal sarcoma. (B) Western blot analysis of HEK293T cells transfected with Myc-tagged JAZF1 wild-type (WT), JAZF1 Mut (phosphodegron mutant), SUZ12, JAZF1-SUZ12 “wild-type” fusion (Fusion WT), and JAZF1-SUZ12 fusion with phosphodegron mutations (Fusion Mut). EV: cells co-transfected with empty vector; WT: cells co-transfected with wild-type FBXW7; Arg Mut: cells co-transfected with FBXW7 mutated at three arginine positions to eliminate WD40 domain-phosphodegron binding. The bar graph on the right shows the quantification of the western blot (WB) signal calculated based on three independent experiments. Relative protein level was calculated based on the ratio of Myc-protein and Tubulin WB signals and this value was normalized to that of cells transfected with the empty vector (EV). Error bars show SD based on three independent experiments. Statistical significance was calculated based on two-tailed, paired Student’s t-test (*: p < 0.05; **: p < 0.01). (C) Multiple sequence alignment of JAZF1 regions from human, mouse, chicken, a frog (Xenopus tropicalis), and a fish (Danio rerio). The FBXW7 binding degron region and the N-terminally located MAPK-binding D-motif is boxed. (D) Western blot analysis of cells co-transfected with JAZF1-SUZ12 fusion (Fusion WT) and FBXW7 in the absence or presence of a p38-specific inhibitor (2 µM; p38i: SB202190). A representative anti-Myc and anti-Tubulin WB is shown on the left (-FBXW7 refers to EV where cells were not transfected with an FBXW7 containing expression vector, only with an empty vector). The right panel shows that FBXW7 co-expression greatly decreases the protein level of Fusion WT, which is counteracted by the kinase inhibitor. Error bars show SD based on three independent experiments. Statistical significance was calculated based on two-tailed, paired Student’s t-test (*: p < 0.05; **: p < 0.01).\n\nFigure 7: Figure 7. Sequence analysis of proteins containing experimentally validated phosphodegrons. (A) New experimentally tested FBXW7 phosphodegron motifs located in the disordered region of the proteins are classified into different categories based on their functionality: transcription factors, chromatin regulators, cytoskeletal regulation, and some other proteins with miscellaneous functions. (B) Sequence alignment showing phosphodegron motifs of the 5 KLF family members. The most studied isoform of KLF4 lacks a small region (34 aa) including the FBXW7 phosphodegron motif. (C) Alignment of KAT6B and KAT6A showing that evolutionary conserved FBXW7 phosphodegron motif is present in KAT6B but is absent in its paralog KAT6A (* indicates conserved positions). (D) Sequence analysis of the SMTL2 protein hints on the co-evolution of a MAPK binding docking motif and the FBXW7 binding phosphodegron motif."
      }
    ]
  },
  {
    "id": "PMC8962085_multi",
    "image": [
      "images/PMC8962085-f1.png",
      "images/PMC8962085-f2.png",
      "images/PMC8962085-f3.png",
      "images/PMC8962085-f4.png",
      "images/PMC8962085-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Diagnostic performance of automated, streamlined, daily updated exome analysis in patients with neurodevelopmental delay\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Comparison of the number of pathogenicityof identified variants between the initial and final results, including the reanalysis\n\nFigure 2: Figure 2. The cumulative monthly number of undiagnosed patients (light blue), patients diagnosed by the initial analysis (green) and by reanalysis (red) from April 2018 to October 2021\n\nFigure 3: Figure 3. Schematic diagram showing patients divided according to the three reported categories\n\nFigure 4: Figure 4. The number of patients with newly reclassified variants (red line) and the number of newly reclassified variants (blue line) based on daily reanalysis data from April 2019 to October 2021\n\nFigure 5: Figure 5. The time interval between the first analysis (blue dot) and the molecular diagnosis (red dot) of patients diagnosed by reanalysis. Number: Time interval converted to years"
      }
    ]
  },
  {
    "id": "PMC8964741_multi",
    "image": [
      "images/PMC8964741-f1.png",
      "images/PMC8964741-f2.png",
      "images/PMC8964741-f3.png",
      "images/PMC8964741-f4.png",
      "images/PMC8964741-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Acox2 is a regulator of lysine crotonylation that mediates hepatic metabolic homeostasis in mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. A Percentage distribution of liver cancer was compared between Acox2−/− (n = 21) and WT (n = 17) mice at the age of 8–9 months. B The representative image of HE stained cross-sections of liver tissue in Acox2−/− and WT mice. Scale bar, 500 μm. C Three tumor lesions (I–III) from a single cross-section of Acox2−/− mouse liver are boxed to show the enlarged region (IV–VI) as indicated. Scale bars, 100 μm in upper panel and 30 μm in bottom panel. D Staining was performed using HE and immunostaining against CD3, CD20, CD68, and CD138 on liver paraffin sections of Acox2−/− or WT mice. Representative images were displayed as indicated. Scale bar, 100 μm. E Immunohistochemical staining of formalin-fixed paraffin-embedded section of mouse liver tissues using AFP antibody. Representative images were displayed as indicated. Scale bar, 20 μm. F, G ACOX2 expression level in humans is significantly downregulated in HCC than in normal liver specimens (fold-change = −3.193; p-value = 1.91 × 10−7) (F) and decreases gradually in malignant stage (III) when compared with the early stage (I) (p-value = 0.00096) (G) by analyzing data from TCGA portal. H, I Low ACOX2 expression in human HCC is correlated with a decrease in OS (overall survival, p-value = 0.036) (H) and DFS (disease free survival, p-value = 0.048) (I) when comparing to high ACOX2 expression as observed on analyzing data from TCGA portal.\n\nFigure 2: Figure 2. A Overlapped Acox2-interacting proteins in MHCC97H and HEK293T cells by TAP-MS analysis were displayed. B Anti-Myc immunoprecipitation assays were performed in HEK293T cells overexpressing Flag-tagged ACOX2 and Myc-tagged MCCC2 constructs followed by immunoblotting with the indicated antibodies. Specificity of antibodies was evaluated as indicated (left panel). MCCC2 methylcrotonoyl-CoA carboxylase subunit 2, MS mass spectrometry, TAP tandem affinity purification.\n\nFigure 3: Figure 3. A Fluorescent immunohistochemistry using DAPI, anti-Ehhadh and pan anti-Kcr were performed on three slides of a single tumor focus. Scale bar, 25 μm. B Immunohistochemical staining showed Kcr signals were concentrated in the nucleus of tumor cells (upper panel) but mainly located in the cytoplasm of adjacent normal liver cells (bottom panel) in Acox2−/− mice, Scale bar, 3 μm. C Kcr levels were increased in the regions of bile duct proliferation in Acox2−/− mice by double immunostaining with Kcr and a ductal marker CK7. Co-localization of Kcr signal with CK7 was observed and indicated by white arrow. Representative images were displayed. Scale bar, 10 μm (upper) and 3 μm (bottom).\n\nFigure 4: Figure 4. A–D Overview of anti-ubiquitin (A), -succinyl lysine (B), -acetyl lysine (C), and –crotonyl lysine (D) in liver tissues of Acox2−/− (n = 3) and WT (n = 3) mice using corresponding pan-antibodies by western blots. E, F Overview of anti-acetyl lysine (E), and –crotonyl lysine (F) in kidney tissues of Acox2−/− (n = 3) and WT (n = 3) mice using corresponding pan-antibodies by western blots.\n\nFigure 5: Figure 5. A Volcano plots showing the significantly changed Kcr sites (FDR < 1%, p < 0.05). Up- and downregulated Kcr sites are highlighted in red and blue, respectively. B Score plots of principal component analysis (PCA) of Acox2−/− and WT crotonylome. C Motif analysis of all identified crotonylated sites. D Compared with the wild type (WT) group, 50 downregulated Kcr sites on 38 proteins and 3 upregulated Kcr sites on 3 proteins were identified in Acox2−/− mice (fold-change >1.4; FDR < 1%; p < 0.05). E Venn diagram showing 32% (16/50) and 22% (11/50) of downregulated Kcr sites were located in the proteins involved in peroxisomal and mitochondrial metabolism, respectively. F, G Analysis of Biological Process (F) and Cellular Component (G) of downregulated Kcr proteins by Gene Ontology (GO) enrichment (Fisher’s exact test; p < 0.05). Top selected pathways are shown in each category as indicated. H Schematic representation of downregulated hepatic Kcr on enzymes involved in fatty acid oxidation and TCA cycle in Acox2−/− mice. Proteins carrying downregulated Kcr sites are marked in brown."
      }
    ]
  },
  {
    "id": "PMC8964741_multi_2",
    "image": [
      "images/PMC8964741-f6.png",
      "images/PMC8964741-f7.png",
      "images/PMC8964741-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Acox2 is a regulator of lysine crotonylation that mediates hepatic metabolic homeostasis in mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. A Key peroxisomal enzymes including Ehhadh, Scp2, Crot, and Hsd17b4 carrying downregulated Kcr sites were significantly upregulated (fd > 1.5) in Acox2−/− mice. B Upregulation of Ehhadh expression in Acox2−/− mice was verified through western blotting. C Heatmap showing profiles of all quantifiable Kcr sites in Crot, Ehhadh, and Scp2 before or after normalization according to quantitative proteomics analysis. D, E Sequence alignment of identified Kcr sites in Ehhadh (D) or Crot (E) in different species including xenopus and zebrafish. F, G Replacing lysine with arginine at Kcr sites lead to decreased Ehhadh Kcr levels in 293T (F) and HepG2 (G) cells as indicated. Cells were transfected with Myc-tagged WT and point mutants of Ehhadh. Cell lysates were immunoprecipitated with an anti-Myc antibody followed by immunoblotting with a pan-Kcr antibody. H, I Replacing lysine with arginine at Kcr sites leads to decreased Crot Kcr levels in 293T cells (H) and HepG2 cells (I). Representative image from three independent experiments was displayed.\n\nFigure 7: Figure 7. A Hierarchical clustering and Heatmap showing the profiles of differentially expressed genes (DEGs) in 293T cells expressing Ehhadh K572R when compared with Ehhadh WT. B Gene Ontology enrichment analysis revealed that “DNA topoisomerase type I (single strand cut. ATP-independent) activity” was the most significantly enriched term in the K572R vs WT group. C, D mRNA levels of TOP3B were further confirmed by cDNA PCR (C) and quantitative real-time PCR (D). *p < 0.05; ***p < 0.001 (one-way ANOVA test, n = 4). E Western blot showed protein levels of TOP3B was downregulated whereas expression of FH and HK2 was not affected in cells overexpression K572R when compared with WT and other mutants. Representative image from three independent experiments was displayed.\n\nFigure 8: Figure 8. A Immunofluorescence staining with anti-gammaH2AX antibody in cells expressing Ehhadh WT or (K-R) mutants. B Immunoblot analysis of gammaH2AX and pan- or phospho-ATM and CHK2 in cells expressing Ehhadh WT or (K-R) mutants. Beta-actin served as a loading control. C, D Top3b protein levels were significantly downregulated in the livers of Acox2−/− mice by western Blot (C). Quantification data of Top3b expression level when normalized against Beta-actin (D). **p value < 0.01 (two-tailed Student’s t test; n = 6). A.U arbitrary units. Representative image from three independent experiments was displayed."
      }
    ]
  },
  {
    "id": "PMC9023513_multi",
    "image": [
      "images/PMC9023513-f1.png",
      "images/PMC9023513-f2.png",
      "images/PMC9023513-f3.png",
      "images/PMC9023513-f4.png",
      "images/PMC9023513-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Clinical diagnosis of metabolic disorders using untargeted metabolomic profiling and disease-specific networks learned from profiling data\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Overview of CTD-based data-driven diagnostic approach.\n\nFigure 2: Figure 2. CTDncd and CTDdm extend CTD to quantify distances between two sets of nodes in a network. (A) CTD outputs highly connected subsets of a node set (given as an input) in a graph (also given as an input). (B) CTD assigns higher significance to highly connected node sets compared to sparsely connected node sets. (C) Node sets found in identical or neighboring regions in a graph are assigned shorter distances compared to node sets found in distal regions of a graph. CTDncd calculates distances between two individuals, where node sets being compared are based on observed metabolite perturbations in two individuals’ metabolomics profiles. CTDdm calculates distances between an individual and a disease state, where node sets being compared are the main disease module in a graph (see Algorithm 1 in Supplemental Text 1) and the observed metabolite perturbations in a single individual’s metabolomic profile.\n\nFigure 3: Figure 3. Data-derived networks are competitive with metabolic pathways as background knowledge network representations. For all models, (A) argininosuccinic aciduria, (B) argininemia, (C) ornithine transcarbamylase deficiency and (D) citrullinemia, the mean profile for each urea cycle disorder cohort is overlaid onto the urea cycle pathway. Red denotes a positive and blue denotes a negative perturbation, where the radius of the circle is modulated to reflect the magnitude of the perturbation. Below each urea cycle pathway, receiver-operator curves (ROC) between the two pathway-based models “ASA-Arg-Orn-Cit”, “Pathway” and the full-profile model are compared to the “Network” model.\n\nFigure 4: Figure 4. Impact of citrulline supplement on disease-specific network modeling ornithine transcarbamylase (OTC) deficiency. (A) Treatment module overlaps with main disease module for OTC deficiency and are well-connected. (B) Prediction performance of OTC deficiency model before and after removal of treatment module.\n\nFigure 5: Figure 5. Zellweger spectrum disorder (ZSD), rhizomelic chondrodysplasia punctata (RCDP) and reference (REF) individuals cluster by disease using CTDncd. (A) Dots represent individual samples in a lower dimensional 2-D space using multi-dimensional scaling. Individuals are colored by their diagnostic state (e.g., ZSD samples in pink and blue, RCDP samples in green, and reference samples in orange). Within the ZSD cluster, age-related effects can be identified whereby the older individuals with the disease (\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ge$$\\end{document}≥ 10 years old) generally show less pronounced abnormalities in metabolite levels, in agreement with Wangler et al.6, while younger patients (< 10 years of age) showed greater heterogeneity in this regard. (B,C) Main disease modules for ZSD and RCDP, respectively."
      }
    ]
  },
  {
    "id": "PMC9024924_multi",
    "image": [
      "images/PMC9024924-f1.png",
      "images/PMC9024924-f2.png",
      "images/PMC9024924-f3.png",
      "images/PMC9024924-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"CRISPR-Mediated Base Editing: From Precise Point Mutation to Genome-Wide Engineering in Nonmodel Microbes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The process of gene editing using CRISPR/Cas9 and a BE. (A) Directed by gRNA, CRISPR/Cas9 recognizes the PAM site (5′-NGG-3′, highlighted in red) and introduces DSBs at the target. DSBs induces two cellular DNA repair systems, NHEJ and HR. Through NHEJ, a few imprecise indels are created through error-prone DNA repair. Through HR, the target is replaced by homologous donor DNA with desired edits and is therefore introduced with deletions, insertions, or substitutions of nucleotides. (B) The BE is also directed by gRNA to the target. At the target, deaminase enzyme achieves base conversion without causing DSBs and requiring donor DNA. CBE mediates the conversion of a C:G base pair to a T:A, which can replace four codons (CAA, CAG, CGA, TGG) with premature stop codons (TAA, TAG, TGA) to inactivate the gene. ABE mediates the base conversion from an A:T base pair to G:C, which can replace start codon ATG with GTG or ACG to disrupt the initiation of gene translation. Other than point mutation, BEs can achieve multiplex gene editing, in vivo evolution of protein and strain, metabolic engineering, etc., in various microbes, as discussed in detail below.\n\nFigure 2: Figure 2. Phylogenetic tree of all microbes that have been researched by BEs, based on small-subunit rRNA sequences and constructed using the maximum-likelihood estimation. The phylogenetic tree includes 21 genera and six classes which are shadowed in different colors. (A) Microbes belong to the kingdom Fungi, phylum Ascomycota, and class Saccharomycetes. Saccharomyces and Kluyveromyces belong to the same family, Saccharomycetaceae, highlighted in brown. Yarrowia and Aspergillus belong to the same family, Dipodascaceae, highlighted in yellow. (B) Microbes belong to the kingdom Bacteria, phylum Proteobacteria, and class Alphaproteobacteria. Rhodobacter and Brucella belong to the family Rhodobacteraceae and Rhizobiaceae, respectively. Agrobacterium and Sinorhizobium belong to the same family, Brucellaceae, highlighted in purple. (C) Microbes belong to the kingdom Bacteria, phylum Proteobacteria, and class Gammaproteobacteria. Pseudomonas, Acinetobacter, and Shewanella belong to the family Pseudomonadaceae, Moraxellaceae, and Shewanellaceae, respectively. Escherichia and Klebsiella belong to the same family, Enterobacteriaceae, highlighted in pink. (D) Microbes belong to the kingdom Bacteria, phylum Actinobacteria, and class Actinomycetia. Streptomyces, Mycobacterium, and Corynebacterium belong to the family Streptomycetaceae, Corynebacteriaceae, and Mycobacteriaceae, respectively. (E) Genus Clostridium belongs to the kingdom Bacteria, phylum Firmicutes, class Clostridia, and family Clostridiaceae. (F) Microbes belong to kingdom Bacteria, phylum Firmicutes, and class Bacilli. Paenibacillus, Companilactobacillus, Staphylococcus, and Bacillus belong to the family Paenibacillaceae, Lactobacillaceae, Staphylococcaceae, and Bacillaceae, respectively.\n\nFigure 3: Figure 3. The basic components and working mechanisms of CRISPR-mediated base editing systems. The common editing windows are highlighted in dark red in the DNA sequence. (A) CBE consists of cytosine deaminase (PmCDA1 in (A)), impaired Cas9, gRNA, and UGI (inhibits uracil DNA glycosylase, abbreviated to UNG, to improve the efficiency of CBE but is not essential). Under the R-loop, CBE deaminates C to U. If UNG removes U, the apurinic/apyrimidinic (AP site) will soon be reversed to C. If UGI is added to CBE, U will be retained at the locus where DNA polymerase will read U as T. The C:G is successfully conversed to T:A. If dCas9 is replaced with nCas9, the nonedited strand will be nicked. Without the inhibition of UGI, U will be removed at the other strand, where AP endonuclease nicks the edited strand and leads to DSBs, bringing indels or cell death. (B) ABE consists of impaired Cas9, gRNA, and ecTadA–TadA* homodimer (ecTadA: wild-type tRNA adenosine deaminase from E. coli, TadA*: evolved ecTadA that can operate on DNA). ABE deaminates A to I at the target, where I is misread as G by DNA polymerase. (C) PE consists of nCas9, reverse transcriptase (RT), and prime editing gRNA (pegRNA). PegRNA comprises two essential parts: PBS (primer binding site) and RTT (reverse transcriptase template). PE nicks the edited strand. The strand then hybridizes with PBS and extends with the copy of RTT by RT so that the mutation is introduced to the strand. The 5′ flap intermediate is removed by flap endonuclease, and the 3′ flap is ligated. The desired edits are consequently introduced into the DNA sequence. (D) GBE consists of nCas9, PmCDA1, and UNG in E. coli. GBE deaminates the C at the edited strand and nicks the other strand. U is removed by UNG, so the target becomes an AP site where TLS polymerases assemble and extend the nicked strand by Polζ. When passing by the locus opposite to the AP site, Rev1 cooperates with C and Polδ with T, which results in the creation of G:C and A:T, respectively, after DNA repair or replication.\n\nFigure 4: Figure 4. Current development of BEs in different microbial species. (A) In theory, any base pair could be converted to any of the others, which only takes three steps at most using the combination of ABE, CBE, and GBE. Firstly, C:G and T:A can be converted to each other by CBE and ABE. Secondly, C:G can be converted to G:C or A:T by GBE. (a) If C:G is predominantly converted to A:T by GBE, the most complicated editing step, shaded in grey, is from A:T to C:G, by firstly converting A:T to G:C by ABE, then to T:A by GBE, and finally to C:G by ABE. (b) If C:G is predominantly converted to G:C by GBE, the most complicated conversion, shaded in grey, is from A:T to T:A, firstly converting A:T to G:C by ABE, then to C:G by GBE, and finally converting to T:A by CBE. (B) The establishment of BEs in different microbes are listed in the table. The achieved base conversions are drawn with a solid line, and base conversions that have not been completed in some microbes are drawn with a dotted line."
      }
    ]
  },
  {
    "id": "PMC9030085_multi",
    "image": [
      "images/PMC9030085-f1.png",
      "images/PMC9030085-f2.png",
      "images/PMC9030085-f3.png",
      "images/PMC9030085-f4.png",
      "images/PMC9030085-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Effects of a Short-Term Lipopolysaccharides Challenge on Mouse Brain and Liver Peroxisomal Antioxidant and β-oxidative Functions: Protective Action of Argan Oil\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Effect of argan oil, olive oil, and colza oil treatments on GSH level (A,C) and lipid peroxidation (B,D) in brain and liver. Male C57BL/6 mice received for 28 days a standard diet (control: CTRL), a diet enriched with 6% (w/w) AO, OO, or CO, and an intravenous injection of LPS (100µg) four hours antemortem. All values are means ± SD (n = 3), Statistical significance of higher mean signal strength (* p ≤ 0.05) compared to control, (## p ≤ 0.01, # p ≤ 0.05) compared to LPS and ($$$ p ≤ 0.001, $$ p ≤ 0.01, $ p ≤ 0.05) compared to the different treatments with or without LPS administration.\n\nFigure 2: Figure 2. Effect of argan oil, olive oil, or colza oil treatment on gene expression of the proinflammatory marker Tnf-α (A,B) in the brain and liver, respectively, and on the anti-inflammatory marker Il-10 in the liver (C). Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) AO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. First, total RNA was isolated from mice brains or livers, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are means ± SD (n = 3), Statistical significance of higher mean signal strength (** p ≤ 0.01) compared to control, (## p ≤ 0.01. # p ≤ 0.05) Compared to LPS and ($$$ p ≤ 0.001. $ p ≤ 0.05) compared to the different treatments with or without LPS administration.\n\nFigure 3: Figure 3. Effect of argan oil, olive oil, or colza oil treatment on gene expression of Cat (A,D) and Acox1 (B,E) in brain and liver, respectively, and Sod in the brain (C). Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) AO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. First, total RNA was isolated from mice brains and livers, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are means ± SD (n = 3), Statistical significance of higher mean signal strength (*** p ≤ 0.001. ** p ≤ 0.01. * p ≤ 0.05) compared to control, (## p ≤ 0.01. # p ≤ 0.05) Compared to LPS and ($$$ p ≤ 0.001. $$ p ≤ 0.01. $ p ≤ 0.05) compared to the different treatments with or without LPS administration.\n\nFigure 4: Figure 4. Effect of argan oil, olive oil or colza oil treatment on brain expressions of peroxisomal proteins, CAT (A), ACOX1 (B), ABCD1 (C), ABCD2 (D) and the heatmap for all protein expression (E). Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) AO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. Brain homogenates were separated in PAGE-SDS electrophoresis and subjected to immunoblotting as described in Section 4. Band intensities were analyzed by densitometry and standardized to β-actine expression level. Tables represent the standardized densitometric analysis obtained after signal intensity quantification of different proteins.\n\nFigure 5: Figure 5. Effect of argan oil, olive oil or colza oil treatment on liver expressions of peroxisomal proteins, CAT (A), ACOX1 (B), ABCD1 (C), ABCD2 (D) and the heatmap for all protein expression (E). Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) AO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. Liver homogenates were prepared as described in Section 4. Band intensities were analyzed by densitometry and standardized to β-actin expression level. Tables represent the standardized densitometric analysis obtained after signal intensity quantification of different proteins."
      }
    ]
  },
  {
    "id": "PMC9036281_multi",
    "image": [
      "images/PMC9036281-f1.png",
      "images/PMC9036281-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Newborn Screening for X-Linked Adrenoleukodystrophy: Review of Data and Outcomes in Pennsylvania\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The Pennsylvania X-ALD newborn screening algorithm utilizes a tiered approach. C26:0-LPC is measured first with flow injection analysis tandem mass spectrometry (FIA-MS/MS), then with liquid chromatography tandem mass spectrometry (LC-MS/MS). Repeat dried blood spot samples were requested for newborns with concerning second-tier screens. Sequencing of the ABCD1 gene was performed for repeat specimens with C26:0-LPC exceeding the cutoff value.\n\nFigure 2: Figure 2. A visual summary of Pennsylvania X-ALD newborn screening results between 1 April 2017 and 26 May 2021. LPC = lysophosphatidylcholine; X-ALD = X-linked adrenoleukodystrophy; VUS = variant of uncertain significance."
      }
    ]
  },
  {
    "id": "PMC9065050_multi",
    "image": [
      "images/PMC9065050-f1.png",
      "images/PMC9065050-f2.png",
      "images/PMC9065050-f3.png",
      "images/PMC9065050-f4.png",
      "images/PMC9065050-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Improved engraftment and therapeutic efficacy by human genome-edited hematopoietic stem cells with Busulfan-based myeloablation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Improved engraftment of genome-edited human HSPCs in TBI- and busulfan-conditioned mice (A) Schematic depicting the AAV6 vector genome used for HDR, the experimental design, and timeline. (B) Human cell engraftment measured by human CD45 and HLA double-positive cells and presented as the percentage of total CD45 cells in the bone marrow, peripheral blood, and spleen of NSG-MPSI mice 20 weeks post-transplantation. Each dot/square represents a mouse. Three different human HSPCs donors were transplanted into n = 14 mice for total body irradiation (TBI) and n = 12 for busulfan (BU); two-tailed Mann-Whitney test. (C) Percentage of indels in human cells that did not undergo HDR engrafted in the bone marrow of primary recipients. Dashed line represents the average of indels found in the transplanted cells. (D) Fraction of edited alleles in human cells engrafted in the bone marrow of primary recipient mice. Dashed line represents the fraction of edited alleles in the transplanted HSPC population (input) as measured by ddPCR; two-tailed unpaired t test. (E) Fraction of edited alleles in the bone marrow of secondary recipient mice, after 36 weeks in vivo (20 weeks in primary and 16 weeks in secondary recipient mice), measured by ddPCR. Each dot represents a mouse (TBI, n = 5; BU, n = 4); two-tailed unpaired t test. (F and G) Percentage of edited alleles in the input HSPC population and after transplant in primary and secondary recipient mice conditioned with BU or TBI. Each dot represents a mouse, and each shade of pink or yellow represents a different human cell donor. Lines link recipients of cells with their respective donors. Input: independent donor HSPCs before transplantation (n = 3). Primary: human cells in the bone marrow after 20 weeks in vivo (TBI, n = 13; BU, n = 12). Secondary: edited cells in the bone marrow of serially transplanted recipient mice, 36 weeks total in vivo (TBI, n = 5; BU, n = 4). All data are shown as median. (F) Ordinary one-way ANOVA with post-hoc Tukey. (G) Kruskal-Wallis with Dunn’s post-hoc test. ns, not significant.\n\nFigure 2: Figure 2. The bone-marrow niche is less pro-inflammatory in BU-conditioned NSG mice (A) Cytokine secretion measured using the mouse 48-plex Luminex assay in the plasma of NSG mice at 2 and 24 h (H) following TBI (2.1 Gy, n = 5) or BU (66 mg/kg, n = 5) conditioning. The 2 and 24 h time points correspond to the time of transplantation after conditioning, respectively. (B) Cytokine secretion in bone marrow 24 h (24H) post-conditioning. (A and B) Fold changes were calculated relative to untreated NSG control mice (n = 4). Statistically significant changes are depicted in bold. No statistically significant cytokine changes were found other than those depicted. (C–F) Frequency and median fluorescence intensity (MFI) monocyte and macrophage progenitors (CD11b+, Ly6C+) and erythrocytes (TER119+) measured in the bone marrow by flow cytometry. (A–F) Statistical analysis: one-way ANOVA with Tukey post-hoc test. ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001, and ∗∗∗∗p < 0.0001.\n\nFigure 3: Figure 3. BU conditioning enhances biochemical correction of genome-edited HSPCs in visceral organs of NSG-MPSI mice (A–G) White: normal; green: sham-transplanted MPSI; pink: BU-conditioned and transplanted MPSI; yellow: TBI-conditioned and transplanted MPSI. (A–C) Enzyme activity of IDUA in (A) serum, (B) liver, and (C) spleen of BU- (pink, n = 8) and TBI- (yellow, n = 5) conditioned and transplanted mice, represented as percentage of the average of normal heterozygous mice. (D) Urinary GAG excretion in 28-week-old mice measured by modified DMB assay. Results are presented as μg of GAGs normalized by mg of creatinine. (E) Disaccharides of dermatan (Di-0S) and heparan (HS-NS, HS-0S) sulfate measured by LC-MS/MS. Results are presented as ng of GAGs normalized by mg of creatinine. Normal, n = 6; MPSI, n = 7; BU, n = 8. (F) Storage of GAGs in the liver measured by DMB assay. Results are presented as μg of GAGs normalized by mg of protein. Normal, n = 6; MPSI, n = 5; BU, n = 9. (G) GAG disaccharides in the spleen. Results are presented as ng of GAGs normalized by mg of protein. Normal, n = 7; MPSI, n = 3; BU, n = 9. For all graphs, each symbol represents a mouse, and all data are represented as mean ± SD. Statistical analysis: (A) Mann-Whitney test; (B and C) two-tailed unpaired t test; (D–G) ordinary one-way ANOVA with post-hoc Tukey test. ns, not significant.\n\nFigure 4: Figure 4. BU conditioning enhances therapeutic efficacy of edited HSPCs in the CNS (A) Enzyme activity of IDUA in the brain of BU- (n = 8) and TBI- (n = 5) treated mice, represented as the percentage of normal heterozygous mice (n = 5). MPSI mice have undetectable levels of enzyme, represented in this log scale as 0.01%. (B) Storage of GAGs in the brain measured by the DMB assay. Results are presented as μg of GAGs normalized by mg of protein. Normal, n = 6; MPS I, n = 5; BU, n = 9. (C) Percentage of Purkinje cells with visible vacuoles, indicative of substrate storage within the cell. Ten histological sections were analyzed per mouse. Normal, n = 2; MPS I, n = 3 and BU, n = 4. (D) Representative histological sections from cerebellum, stained with toluidine blue for visualization of storage vacuoles. (E) Representative flow cytometry plots from microglia-enriched populations from mouse brains. (F) Percentage of human CD45+ cells among live cells (propidium iodide negative) and among total CD45 cells (mouse and human CD45+) in the microglia isolated from BU-treated mice. (G) Percentage of human DNA measured by ddPCR in microglia cells from BU-treated mice, normalized by total mouse and human DNA. BU, n = 5, BU-2ary, n = 4. (H) Correlation between percentage of human DNA in microglia cells and IDUA activity measured in brains of BU-treated mice. n = 5; p = 0.0070; R2 = 0.9362. (I) Representative brain sections of BU-conditioned HSPC transplanted mice, stained for a human-specific Ku80 marker and the microglial marker IsolectinB. Scale bar is 50 μm. (J) Percentage of human cells (given by Ku80 positivity) normalized by total nuclei (given by DAPI+ cells) in the meninges and in the parenchyma of BU- and TBI-conditioned mice. (K) Percentage of human microglia (Ku80+IB4+) normalized by total human cells (Ku80+) in the meninges and parenchyma. (A–C and F–H) Medians shown; each dot represents a mouse. (J and K) Medians; each symbol represents a section. (A, J, and K) Two-tailed Mann-Whitney test. (B and C) Ordinary one-way ANOVA with post-hoc Tukey test.\n\nFigure 5: Figure 5. Engraftment of human genome-edited HSPCs in the CNS of NSG-SGM3 mice (A) Representative flow cytometry plots showing mouse (mCD45+ CD11b+), human (hCD45+ CD11b+), and edited (YFP+) human microglia-like cells isolated from brain tissue of transplanted NSG-SGM3 mice. (B) Purity of murine microglia (mCD45+ CD11b+) among total myeloid CD45+ cells. (C and D) Characterization of human cells among (C) total myeloid CD45+ cells and (D) human CD45+ cell populations. (E) Proportion of human alleles measured by ddPCR in the microglia preparations, normalized by mouse genomic DNA. (F and G) Characterization of edited YFP+ human HSPCs among (F) total CD45+ and (G) human CD45+ cell populations. (H) Fraction of edited human CCR5 alleles in cells isolated from microglia preparations. Dashed line refers to the fraction of edited alleles in the transplanted HSPC population (input). (I) Representative brain sections of transplanted mice showing YFP expression (natural fluorescence) from edited HSPCs and staining for nuclei (DAPI) and for the specific human marker Ku80. Scale bar is 100 μm. Medians shown; each dot represents a mouse, n = 4."
      }
    ]
  },
  {
    "id": "PMC9092451_multi",
    "image": [
      "images/PMC9092451-f1.png",
      "images/PMC9092451-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Tricky Isomers—The Evolution of Analytical Strategies to Characterize Plasmalogens and Plasmanyl Ether Lipids\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Overview of the chemical structures and unique features of diacyl (ester) lipids, and plasmanyl and plasmenyl lipids. Ether lipids comprise lipids that harbor both alkyl (1-O-alkyl, plasmanyl, indicated in blue) and alkenyl (1-O-alk-1′-enyl, plasmenyl, indicated in green) residues, while the latter is also referred to as plasmalogens. The alkyl/alkenyl residues of mammalian ether lipids are predominantly localized at the sn-1 position, while the sn-2 position is frequently substituted with polyunsaturated fatty acyls. Ether lipids belong for the most part to the lipid classes phosphatidylethanolamines (PEs), phosphatidylcholines (PCs), and 1-O-alkyl-2-acylglycerols (alkyl-DG). (B) Ether lipid metabolism. The initial steps of ether lipid biosynthesis take place in the peroxisomes and are based on substrates derived from glycolysis and fatty acid metabolism. The rate-determining step is the provision of fatty alcohols, which are formed from acyl-CoA by fatty acid reductase 1 (FAR1). Remodeling/interconversion pathways of ether lipids are partially shared with their ester lipid analogs. The enzyme plasmanylethanolamine desaturase (PEDS1) is responsible for converting plasmanyl lipids (blue) into their plasmenyl counterparts (green) and accepts PE as substrates. The catabolism of ether lipids proceeds from their lyso-forms and is catalyzed by alkylglycerol monooxygenase (AGMO; in the case of plasmanyl lipids) and (lyso)plasmalogenases (in the case of plasmenyl lipids).\n\nFigure 2: Figure 2. Timeline of selected noteworthy discoveries and milestones in plasmalogen and ether lipid research. In the more than a hundred years since the first evidence for the existence of ether lipids was found, there have been groundbreaking results on a wide variety of conceptual levels. These include their 1) discovery (blue), 2) structural characterization (green), 3) enzymology and metabolism (yellow), and 4) function and physiological roles (red). Corresponding references and additional pioneering findings are listed in Table 1."
      }
    ]
  },
  {
    "id": "PMC9107455_multi",
    "image": [
      "images/PMC9107455-f1.png",
      "images/PMC9107455-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Glycoprotein nonmetastatic melanoma protein B (GNMPB) as a novel biomarker for cerebral adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. CSF GNMPB levels are elevated in boys with cALD. (A) shows levels of CSF GNMPB. (B) shows the difference between low risk and high-risk boys based on a Loes score cutoff of ≥ 10. (C) shows Loes score as a continuous variable and p-value derived from a linear regression analysis. (D) shows the comparison of CSF GNMPB amongst cALD patients categorized by GIS. Two-comparisons shows p-values derived from a Student’s t-test. P-value in (D) was derived from an ANOVA and Tukey post-hoc test. The main effect p-value was p = 0.0204.\n\nFigure 2: Figure 2. CSF GNMPB correlates with neurologic function and chitotriosidase. (A) The cerebral adrenoleukodystrophy neurologic function score (NFS), which was used to evaluate gross clinical neurologic severity for the cALD cohort pre-transplantation. Note that a score of zero denotes absence of clinical signs of cerebral disease. Maximal signs within a domain score the total of all grades within that domain (for example, a patient with “total urinary or fecal incontinency” scores 3, for the sum of “Episodes of incontinency” [1 point] and “Total Incontinency” [2 additional points]). (B) The difference between neurologically affected boys (NFS ≥ 2) versus those with NFS ≤ 1 is depicted. (C) Use of the NFS as a continuous variable and p-value derived from a linear regression analysis. (D) The correlation between CSF GNMBP and CSF chitotriosidase and p-value derived from a linear regression analysis. (D) shows the comparison of CSF Two-comparisons shows p-values derived from a Student’s t-test."
      }
    ]
  },
  {
    "id": "PMC9145909_multi",
    "image": [
      "images/PMC9145909-f1.png",
      "images/PMC9145909-f2.png",
      "images/PMC9145909-f3.png",
      "images/PMC9145909-f4.png",
      "images/PMC9145909-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MDM2-Mediated Ubiquitination of RXRβ Contributes to Mitochondrial Damage and Related Inflammation in Atherosclerosis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. RXRβ is ubiquitinated in ox-LDL-induced HAECs. (A,B) protein and mRNA expression of RXRβ in HAECs which were incubated with 100 μg/mL ox-LDL at various times. (C) HAECs pretreated with 3-methyladenine (3-MA, 5 mM), chloroquine (25 μM), or MG132 (20 μM) for 1 h were incubated in the presence and absence of ox-LDL (100 μg/mL) for 24 h. Then, protein expression of RXRβ was determined. (D) The immunoprecipitation results showed the ubiquitination of RXRβ in HAECs under ox-LDL (100 μg/mL) for 24 h in the presence of MG132 (20 μM). Results are presented as the mean ± SD. n = 6. * p < 0.05 vs. control group, # p < 0.05 vs. ox-LDL alone group.\n\nFigure 2: Figure 2. MDM2 can affect the stability of RXRβ. (A,B) MDM2 is predicted as the specific E3 ligase of RXRβ by the UbiBrowser database. In the confidence mode (A) and evidence mode (B), a node is positioned in the center of the canvas showing the putative substrates, surrounded by nodes revealing predicted E3 ligases. The node colors and characters denote the E3 ligase type with the edge width and node size representing the confidence score. (C,D) mRNA and protein expression of MDM2 in HAECs which were incubated with 100 μg/mL ox-LDL at various times. (E) HAECs were incubated with control siRNA (si-con, 100 nM) or MDM2 siRNA (si-MDM2, 100 nM) for 24 h and then with 100 μg/mL ox-LDL for additional 24 h. Then, the protein expression of RXRβ in HAECs was determined. (F) HAECs were incubated with a non-targeting control vector (Ad-con) or MDM2-adenoviral vector (Ad-MDM2) in the presence and absence of MG132 (20 μM) for 24 h. Then, the protein expression of RXRβ in HAECs was determined. (G,H) Western blotting in lysates from HAECs transfected with si-MDM2, si-con, Ad-MDM2 or Ad-con in the presence of cycloheximide (100 μg/mL) for up to 8 h. The results of (C) were represented as median, 10th percentile, 90th percentile, and minimum and maximum values. The results of (D–H) are presented as the mean ± SD. n = 6. * p < 0.05 vs. control group, # p < 0.05 vs. ox-LDL alone group, Δ p < 0.05 vs. Ad-MDM2 group.\n\nFigure 3: Figure 3. MDM2 mediates the poly-ubiquitination of RXRβ. (A) HAECs pretreated with JNJ-165 (10 μM) or vehicle for 1 h were incubated in the presence and absence of ox-LDL (100 μg/mL) for 24 h. Then, protein expression of RXRβ was determined. (B) HAECs were incubated with a non-targeting control vector (Ad-con) or MDM2-adenoviral vector (Ad-MDM2) in the presence and absence of JNJ-165 (10 μM) for 24 h. Then, the protein expression of RXRβ in HAECs was determined. (C) HEK293 cells were transfected with Flag-tagged wild-type (WT) MDM2 or Flag-tagged MDM2 C464A mutant plasmids for 48 h. The efficiency was confirmed by Western blot analysis. (D) Western blot analysis of Myc (RXRβ) in HEK293 cells transfected with Flag-tagged WT MDM2 or Flag-tagged MDM2 C464A mutant plasmids together with Myc-tagged-RXRβ plasmids, then treated with cycloheximide (100 μg/mL) for up to 8 h. (E) The immunoprecipitation results showed the ubiquitination of RXRβ in MDM2 siRNA transfected HAECs under ox-LDL (100 μg/mL) for 24 h in the presence of MG132 (20 μM). (F) The immunoprecipitation results showed the ubiquitination of RXRβ in JNJ-165 (10 μM) pretreated HAECs under ox-LDL (100 μg/mL) for 24 h in the presence of MG132 (20 μM). (G) Myc-RXRβ and HA-Ub with either Flag-MDM2 or Flag-MDM2 C464A mutant plasmids were transfected and maintained for 48 h in HEK293 cells. Cells were treated with MG132 for 4 h before collecting. The cell lysates were immunoprecipitated with Myc and immunoblotted with HA. The results of (A–F) are presented as the mean ± SD. The results of (G) were represented as median, 10th percentile, 90th percentile, and minimum and maximum values. n = 6. * p < 0.05 vs. control group. # p < 0.05.\n\nFigure 4: Figure 4. MDM2 interacts with RXRβ. (A,B) HAECs were incubated with 100 μg/mL ox-LDL in the presence of MG132 (20 μM) for 24 h, and cell lysates were then immunoprecipitated with anti-MDM2 or anti-RXRβ or negative control IgG antibodies followed by immunoblotting with an anti-MDM2 or anti-RXRβ antibody to verify endogenous interaction between MDM2 and RXRβ. The input protein was immunoblotted with antibodies against RXRβ, MDM2, or GAPDH. (C–E) Transfection of HEK293 cells with Myc-RXRβ together with Flag-MDM2 for 48 h, and cell lysates were then immunoprecipitated with anti-Myc or anti-Flag antibody followed by immunoblotting with an anti-Myc or anti-Flag antibody to verify the exogenous interaction between MDM2 and RXRβ. The input protein was immunoblotted with antibodies against Myc, Flag, or GAPDH.\n\nFigure 5: Figure 5. MDM2 inhibitor JNJ-165 provides protection against ox-LDL-induced mitochondrial damage via RXRβ. HAECs were transfected with RXRβ siRNA (si-RXRβ) or si-con for 24 h and then treated with or without JNJ-165 (10 μM). After 1 h, the cells were stimulated with 100 μg/mL ox-LDL for an additional 24 h. The mitoROS levels were determined based on the mitoSOX fluorescence by fluorescence microscope (A) and fluorescence microplate reader (B). The ΔΨm levels were determined based on the fluoroprobe JC-1 by fluorescence microscope (C) and fluorescence microplate reader (D). (E) The content of cytosolic mtDNA. (F) The protein expression of PGC1α. Results are presented as the mean ± SD. n = 6. * p < 0.05 vs. si-con with no treatment, # p < 0.05 vs. ox-LDL + si-con group, Δ p < 0.05."
      }
    ]
  },
  {
    "id": "PMC9145909_multi_2",
    "image": [
      "images/PMC9145909-f6.png",
      "images/PMC9145909-f7.png",
      "images/PMC9145909-f8.png",
      "images/PMC9145909-f9.png",
      "images/PMC9145909-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"MDM2-Mediated Ubiquitination of RXRβ Contributes to Mitochondrial Damage and Related Inflammation in Atherosclerosis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. MDM2 inhibitor JNJ-165 provides protection against ox-LDL-induced mitochondrial-related inflammation via RXRβ. HAECs were transfected with RXRβ siRNA (si-RXRβ) or si-con for 24 h and then treated with or without JNJ-165 (10 μM). After 1 h, the cells were stimulated with 100 μg/mL ox-LDL for an additional 24 h. (A) The protein expression of TLR9. (B) NF-κB p65 DNA binding activity. (C) The protein expression of NLRP3. (D,E) The protein expression of caspase-1. (F) The level of caspase-1 p20 in culture supernatants. (G–I) The mRNA expression of TNF-α (G), IL-6 (H) and IL-1β (I). (J–L) The secretion of TNF-α (J), IL-6 (K) and IL-1β (L). Results are presented as the mean ± SD. n = 6. * p < 0.05 vs. si-con with no treatment, # p < 0.05 vs. ox-LDL + si-con group, Δ p < 0.05.\n\nFigure 7: Figure 7. MDM2 inhibitor JNJ-165 provides protection against ox-LDL-induced mitochondrial damage and related inflammation independent of p53. For (A–I), HAECs were transfected with p53 siRNA (si-p53) or si-con for 24 h and then treated with or without JNJ-165 (10 μM). After 1 h, the cells were stimulated with 100 μg/mL ox-LDL for an additional 24 h. (A) mitoROS. (B) ΔΨm. (C) mtDNA. (D–F) The mRNA expression of TNF-α (D), IL-6 (E) and IL-1β (F). (G–I) The secretion of TNF-α (G), IL-6 (H) and IL-1β (I). Results are presented as the mean ± SD. n = 6. * p < 0.05 vs. si-con with no treatment, # p < 0.05 vs. ox-LDL + si-con group.\n\nFigure 8: Figure 8. MDM2 inhibition alleviates atherosclerotic lesion formation and RXRβ protein expression in HFD-fed LDLr-/- mice. (A,B) Representative images and quantification of Oil Red O staining of en face preparations of aortas. n = 6. (C,D) Representative images and quantification of aortic root sections stained with Oil Red O. n = 6. (E–G) Serum levels of TC, TG and LDL-c. n = 12. (H) Representative images of thoracic aorta cross-sections stained with anti-RXRβ antibody and CD31, respectively. (I) Quantification of fluorescence intensity of RXRβ staining. n = 6. (J) Protein expression of RXRβ in the aorta. n = 6. (K) mRNA expression of RXRβ in the aorta. n = 6. Results are presented as the mean ± SD. * p < 0.05 vs. control group. # p < 0.05 vs. HFD group. The individual data points are shown as the circles, the normal or upside down triangles on top of the corresponding bars.\n\nFigure 9: Figure 9. MDM2 inhibition alleviates mitochondrial damage and related inflammation in HFD-fed LDLr-/- mice. (A,B) Representative images and quantification of thoracic aorta cross-sections stained with mitoSOX Red. (C) The protein expression of PGC1α. (D) The protein expression of TLR9. (E) NF-κB p65 DNA binding activity. (F) The protein expression of NLRP3 in the aorta. (G,H) The protein expression of caspase-1. (I–K) mRNA expression of TNF-α (I), IL-6 (J) and IL-1β (K) in the aorta. Results are presented as the mean ± SD. (n = 6). * p < 0.05 vs. control group. # p < 0.05 vs. HFD group. The individual data points are shown as the circles, the normal or upside down triangles on top of the corresponding bars.\n\nFigure 10: Figure 10. Illustration of the mechanism by which MDM2-mediated ubiquitination of RXRβ contributes to atherosclerosis. Under conditions that lead to atherosclerosis, such as upon prolonged exposure to ox-LDL in endothelial cells, the expression of MDM2 is induced, and MDM2 functions as a ubiquitin E3 ligase for RXRβ. MDM2 promotes RXRβ poly-ubiquitination and degradation by proteasomes, which contributes to mitochondrial damage. Subsequently, the elevated amounts of mtROS and release of mtDNA active TLR9/NF-κB pathway and NLRP3/caspase-1 inflammasome, which further produces pro-inflammatory cytokines TNF-α, IL-6 and IL-1β in endothelial cells and finally promotes the progression of atherosclerosis."
      }
    ]
  },
  {
    "id": "PMC9175428_multi",
    "image": [
      "images/PMC9175428-f1.png",
      "images/PMC9175428-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Pseudo-neonatal Adrenoleukodystrophy: A Rare Peroxisomal Disorder\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (a) Illustrating facial dysmorphism with hirsute forehead, broad eyebrows, depressed nasal bridge, short nose and philtrum, inverted V-shaped wide-open mouth, and minimal retrognathia (b) hyperextensibility of the wrist joint. (Consent taken)\n\nFigure 2: Figure 2. (a) AP radiograph of the pelvis reveals bilateral acetabular dysplasia (b) Axial T1W Magnetization Prepared - RApid Gradient Echo (MPRAGE) image of the patient at 31 months shows bilateral perisylvian polymicrogyria (arrows). Axial T2WI (c) and (d) demonstrate hyperintensity (arrows) in bilateral centrum semiovale and corticospinal tracts in the midbrain, respectively. Similar signal changes are appreciated along pyramidal tracts (arrows) involving basipontis on coronal T2W (e) and medullary pyramids (f) on axial T2W images. There is also the involvement of peridentate cerebellar white matter (arrowhead) and dentate hilus with sparing of dentate nuclei (f). (Consent taken)"
      }
    ]
  },
  {
    "id": "PMC9177597_multi",
    "image": [
      "images/PMC9177597-f1.png",
      "images/PMC9177597-f2.png",
      "images/PMC9177597-f3.png",
      "images/PMC9177597-f4.png",
      "images/PMC9177597-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural basis of substrate recognition and translocation by human very long-chain fatty acid transporter ABCD1\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a ATPase activity of chABCD1 in the presence or absence of C22:0-CoA in detergent of LMNG + CHS. 0.05% methyl-β-cyclodextrin (M-β-CD) which functions as the solvent of substrate, was also tested as the control group. The data points were fitted with a Michaelis-Menten equation. b Substrate concentration-dependent ATPase activity of chABCD1 in detergent of LMNG + CHS and 2 mM ATP upon addition of varying fatty acyl-CoA. The data points were fitted with a Hill equation. All data points for a and b represent means of three independent measurements (n = 3) in detergent of LMNG and CHS. Error bars indicate standard deviation. Source data are provided as a Source Data file. c Refined cryo-EM map of three ABCD1 structures. The unsharpened maps are displayed as the outline to show the position of the detergent micelle. The cryo-EM map are colored by UCSF ChimeraX 1.2.5 according to the local resolution of the cryo-EM estimated by RELION 3.1 or cryoSPARC 3.1.\n\nFigure 2: Figure 2. a Cartoon representation of the apo-form ABCD1. Two subunits are colored in green and rose, respectively. Transmembrane helices (TMs), C-terminal helices and coupling helices (CH1’ and CH2’) are labeled. Two extra lipid-like densities are shown as the blue mesh. The peroxisome membrane is indicated as the gray lines. b Top view of ABCD1 (from the inside of peroxisome). The six TMs of each subunit are numbered. c The ATPase activity of the C-terminal helix truncated variant (ΔGlu694-Thr745) and T693M mutant in detergent of LMNG + CHS and 2 mM ATP upon addition of C22:0-CoA at various concentrations. Each data point is the average of three independent experiments (n = 3), and error bars represent the means ± SD. The data points were fitted with a Hill equation. Source data are provided as a Source Data file.\n\nFigure 3: Figure 3. a Side and b Top view of the overall structure of C22:0-CoA-bound ABCD1. Two subunits of ABCD1 are colored in green and rose, respectively. The peroxisome membrane is indicated as the gray lines. The α-helices (termed α5a/5a’) in the peroxisome matrix is labeled. The two C22:0-CoA molecules are shown as yellow spheres, and the two cholesteryl hemisuccinate (CHS) molecules are shown as blue sticks. c Superposition of the apo-form (gray) against C22:0-CoA-bound ABCD1 (pink). TM4a/4a′ and TM4b/4b′ are labeled. d The C22:0-CoA molecule binding to TMDs. The density map of C22:0 and CHS, shown as blue mesh, are contoured at 5σ. The CHS and C22:0-CoA are shown as blue and yellow sticks, respectively. e The binding pocket of the CoA portion of C22:0-CoA. The binding residues are shown as sticks, and hydrogen bonds (≤3.5 Å) and salt bridges (≤4.0 Å) are shown as black dotted lines. The electrostatic surface properties of the binding pocket are color-coded by electrostatic potential generated by PyMOL 2.5.2. f The binding pocket of fatty acyl chain of C22:0-CoA. The hydrophobic residues surrounding the fatty acyl chain within 4.5 Å are shown as sticks. The fatty acyl chain and CHS are shown as blue and yellow sticks, respectively. g Relative ATPase activities of chABCD1 and mutants in detergent of LMNG + CHS and 2 mM ATP upon addition of C22:0-CoA. The relative activity represents the substrate-stimulated activity of chABCD1 or its mutant that harboring a single mutation of residues at the substrate-binding pocket. Each data point is the average of three independent experiments (n = 3), and error bars represent the means ± SD. One-way analysis of variance (One-way ANOVA) is used for the comparison of statistical significance of mutants and wild-type. The p value of R104A, R152A, K217A, K336A, Y337F, R401Q, A247W, G343V, P350W and A395W is 0.00019, 0.00062, 0.00076, 0.00092, 0.00053, 0.00063, 0.00014, 0.000178, 0.00031 and 0.00012. The p values of <0.05, 0.01, and 0.001 are indicated with *, ** and ***. Source data are provided as a Source Data file.\n\nFigure 4: Figure 4. a Cartoon representation of ATP-bound ABCD1. Two subunits of ABCD1 are colored in green and rose, respectively. ATP molecules are shown as yellow sticks, and Mg2+ ions are displayed as green spheres. The number of TMs are labeled. Conformational changes upon ATP binding accompanied with substrate release, as shown by b cutaway representation of the electrostatic surface, and c top view of C22:0-CoA-bound-ABCD1 and ATP-bound-ABCD1. TM3/TM3′ and TM4/TM4′ are shown as cartoon. The electrostatic surface was generated by PyMOL 2.5.2. The residue Arg280 is shown as sticks. Superposition of (d) the TMDs and (e) the CoA portion binding pocket of C22:0-CoA-bound ABCD1 (gray) against the ATP-bound form (rose). TM helices are shown as cartoons and numbered. The shifts of TM1/TM1′ and TM6/TM6′ are indicated in green or blue arrows, respectively. The residues interacting with CoA portion of C22:0-CoA are displayed as sticks.\n\nFigure 5: Figure 5. Schematic illustration of the transport cycle of ABCD1, inferred from the three resolved structures. The apo-form ABCD1 adopts an inward-facing conformation, with the two NBDs properly separated via the C-terminal helical crossover (resting state). Cooperative substrate binding drags two TMDs approaching each other, resulting in a narrowed inward-facing transport cavity (substrate-bound state). Upon ATP binding, the NBDs approach each other and dimerize, making ABCD1 in an outward-facing conformation, and facilitating the substrate release into the peroxisome (post-translocation state). Finally, the hydrolysis of ATP resets ABCD1 to the resting state, and ready for another transport cycle. The CoA portion and fatty acyl chain of fatty acyl-CoA are shown as green ovals and brown curved lines, respectively."
      }
    ]
  },
  {
    "id": "PMC9190015_multi",
    "image": [
      "images/PMC9190015-f1.png",
      "images/PMC9190015-f2.png",
      "images/PMC9190015-f3.png",
      "images/PMC9190015-f4.png",
      "images/PMC9190015-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitin-conjugating activity by PEX4 is required for efficient protein transport to peroxisomes in Arabidopsis thaliana\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Cytosolic GFP fluorescence in apem7 mutants. Peroxisomes were visualized as spherical structures in both GFP-PTS1 and apem7 plants. In addition, GFP fluorescence was observed in the cytosol of apem7 mutants. In root and trichome cells, central vacuole is so well developed that the fluorescence in cytosol between the cell wall and the vacuole is observed to frame the cell. Some representative cytosolic GFP is indicated by arrowheads. Bars represent 50 μm. apem, aberrant peroxisome morphology; PTS, peroxisome targeting signal 1.\n\nFigure 2: Figure 2. Immunodetection of peroxisomal proteins.A, GFP-PTS1 parent plant and apem7 mutants were grown under continuous darkness for 3 days (lanes 1 and 5), 5 days (lanes 2 and 6), 7 days (lanes 3 and 7), or 2 days under continuous illumination after 5 days (lanes 4 and 8). Five micrograms of total protein were subjected to immunoblotting using antibodies against 3-ketoacyl CoA thiolase (Thio), isocytolate lyase (ICL), hydroxypyruvate reductase (HPR), and glycolate oxidase (GO). B, 10 μg of total protein prepared from 6-day-old plants under continuous darkness (6D) and 7-day-old plants under continuous light (7L) were used for immunoblotting. The arrowheads and asterisk represent the positions of the precursor proteins of thiolase and the nonspecific band, respectively. apem, aberrant peroxisome morphology; PTS1, peroxisome targeting signal 1.\n\nFigure 3: Figure 3. Phenotype of apem7 mutants.A, 21-day-old and (B) 34-day-old plants grown under the light conditions are shown. Bars represent 1 cm. C and D, GFP-PTS1, ped1, and apem7 mutants grown on medium without sucrose (C) or medium containing 2,4-DB (D) in the normal conditions. Statistical significance was analyzed by one-way ANOVA test. ∗p < 0.05, ∗∗p < 0.01, ∗∗∗p < 0.001, and ∗∗∗∗p < 0.0001. 2,4-DB, 2,4-dichlorophenoxybutyric acid; apem, aberrant peroxisome morphology; PTS1, peroxisome targeting signal 1.\n\nFigure 4: Figure 4. Positional cloning of the APEM7 gene and rescue of the apem7 phenotype.A, mutation position in the apem7 mutant. The apem7 mutation causes a nucleotide substitution of the 368th cytidine to thymidine (nucleotide residue 1 corresponds to the adenosine of the first methionine codon). Exons are indicated by boxes. Bar represents 100 bp. B, the PEX4 gene restored the GFP fluorescence pattern in the apem7 mutant. Some representative cytosolic GFP is indicated by arrowheads. Bars represent 50 μm. C, recovery of root growth of T1 plants of apem7;PEX4 gene and apem7;35S:PEX4. Plants were grown for 7 days on medium without sucrose. Photographs were taken after the seedlings were removed from the medium and rearranged on agar plates. apem, aberrant peroxisome morphology; PEX4, peroxin 4.\n\nFigure 5: Figure 5. Immunodetection of PEX4 polypeptides and immunocytochemical localization of PEX4.A, 30 μg of total protein extracts from 7-day-old plants were used for immunoblot analysis with antibodies against PEX4. Lane 1: GFP-PTS1 plants; lane 2: apem7 mutants. Molecular markers are indicated in kilodalton on the right. An arrow and an arrowhead on the left represent PEX4 and ubiquinated-PEX4, respectively. B, fractionation of total proteins into soluble and membrane fractions. Total proteins from the aerial parts of GFP-PTS1 plants grown for 13 days were fractionated into soluble and membrane fractions by centrifugation and immunoblotted for the indicated antibodies. Ten micrograms of protein were loaded on all lanes for PEX4 and PEX14, and 5 μg of protein was used for GFP. Lanes 1 and 2 represent soluble and membrane fractions, respectively. Molecular markers are indicated in kilodalton on the right. C, immunogold labeling of ultrathin sections of 3-day-old dark-grown cotyledons was performed using antibodies against PEX4 (15 nm, arrows) and catalase (10 nm, open arrowheads). Bar represents 500 nm. Mt, mitochondrion; Ob, oil body; P, peroxisome; PEX, peroxin; PTS1, peroxisome targeting signal 1."
      }
    ]
  },
  {
    "id": "PMC9190015_multi_2",
    "image": [
      "images/PMC9190015-f6.png",
      "images/PMC9190015-f7.png",
      "images/PMC9190015-f8.png",
      "images/PMC9190015-f9.png",
      "images/PMC9190015-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitin-conjugating activity by PEX4 is required for efficient protein transport to peroxisomes in Arabidopsis thaliana\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Enzymatic activity of PEX4 as a ubiquitin-conjugating enzyme.A, 30 μg of total extracts prepared from 7-day-old seedlings of GFP-PTS1 plants (lanes 1 and 4), apem7 plants (lanes 2 and 5), and transgenic plants of apem7;PEX4 gene (lanes 3 and 6) were used for immunodetection with antibodies against PEX4 under reducing (lanes 1–3) and nonreducing conditions (lanes 4–6). Chloroplast-Cpn20 antibody was used as a loading control for 10 μg of total extracts. B, WT (PEX4WT) and mutant PEX4 cDNAs (PEX4C90A and PEX4P123L) were translated in a total volume of 12.5 μl using a rabbit reticulocyte lysate system, and each extract was divided into two fractions. After adding SDS sample buffer with and without β-mercaptoethanol, 7.5 μl was used for immunodetection with antibodies against PEX4. Lanes 1 and 5: empty vector as a negative control. Lanes 2 and 6: PEX4WT. Lanes 3 and 7: PEX4C90A. Lanes 4 and 8: PEX4P123L. Lanes 1 to 4: reducing conditions. Lanes 5 to 8: nonreducing conditions. Open and closed arrowheads represent PEX4 and ubiquitinated PEX4 polypeptides, respectively. Asterisks indicate nonspecific bands. Molecular markers are indicated in kilodalton on the center. apem, aberrant peroxisome morphology; cDNA, complementary DNA; PEX4, peroxin 4; PTS1, peroxisome targeting signal 1.\n\nFigure 7: Figure 7. Membrane-associated PEX5 is increased in apem7 mutant. Total proteins from 14-day-old GFP-PTS1 and apem7 plants were fractionated into soluble and membrane fractions. Ten micrograms of protein were used for immunodetection. Lanes 1 and two represent soluble and membrane fractions from GFP-PTS1 plants, respectively. Lanes 3 and 4 represent soluble and membrane fractions from apem7 mutants, respectively. Molecular markers are indicated in kilodalton on the right. apem, aberrant peroxisome morphology; PEX5, peroxin 5; PTS1, peroxisome targeting signal 1.\n\nFigure 8: Figure 8. Histochemical analysis of PEX4:GUS reporter gene expression in various organs at different stages. Transgenic Arabidopsis plants harboring the PEX4:GUS construct were grown for 7 days in the light (A and B), 21 days in the light (C), 28 days in the light (D–G), and 3 days in the dark (H). A and H, seedlings. B, lateral root. C, cauline leaf. D, flower. E, pistil. F, stamen. G, fruit. Scale bars represent 1 mm (A, C, D, F–H) and 200 μm (B and E). H, two images were neatly connected and arranged. An, anther; Co, cotyledon; Fl, filament; Gy, gynoecium; Hy, hypocotyl; Pe, petal; PEX4, peroxin 4; Rc, root cap; S, seed; Se, sepal; St, stigma; Vc, vascular cylinder.\n\nFigure 9: Figure 9. Figure S1Normal plant growth apem7 mutants on medium with sucrose. GFP-PTS1 and apem7 mutants grown for 7 days on medium with sucrose. Photographs were taken after the seedlings were removed from the medium and rearranged on agar plates. Bar, 1 cm\n\nFigure 10: Figure 10. Figure S2Alignment of amino acid sequences of the APEM7 gene product with other PEX4 proteins. The deduced amino acid sequence of the APEM7 gene product (Arabidopsis thaliana) was compared with homologs in other plants and yeast. The asterisk represents the conserved cysteine residue in the active site, which is essential for thioester formation with ubiquitin. The proline residue, which is replaced by a leucine residue in the apem7 mutant, is boxed. Accession IDs are At5g24760 for Arabidopsis thaliana, XP_002872181.1 for Arabidopsis lyrata, XP_009151099.1 for Brassica rapa, OTG23315.1 for Helianthus annuus, XP_011081811.1 for Sesamum indicum, XP_006450648.1 for Citrus clementine, AFK37806.1 for Lotus japonicas, XP_012077418.1 for Jatropha curcas, XP_003522698.1 for Glycine max, XP_011016247.1 for Populus euphratica, NW_001263901 for Dictyostelium discoideum AX4, DQ793194 for Penicillium chrysogenum, NP_011649 for Saccharomyces cerevisiae, CR382125 for Kluyveromyces lactis, A53848 for Pichia pastoris, and AF061604 for Hansenula polymorpha"
      }
    ]
  },
  {
    "id": "PMC9190015_multi_3",
    "image": [
      "images/PMC9190015-f11.png",
      "images/PMC9190015-f12.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Ubiquitin-conjugating activity by PEX4 is required for efficient protein transport to peroxisomes in Arabidopsis thaliana\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 11: Figure 11. Figure S3Enzymatic activity of PEX4 as a ubiquitin-conjugating enzyme. Wild-type (PEX4WT) and mutant PEX4 cDNAs (PEX4C90A and PEX4P123L) were translated using a rabbit reticulocyte lysate system in the presence of [35S]-radiolabeled methionine. Equal amounts of wild-type and mutant PEX4 proteins were run side-by-side on reducing (lanes 1–4) and non-reducing (lanes 5–8) gels, followed by detection of [35S]-labeled proteins using the Bioimage analyzer BAS-5000. Lanes 1 and 5: empty vector as a negative control. Lanes 2 and 6: PEX4WT. Lanes 3 and 7: PEX4C90A. Lanes 4 and 8: PEX4P123L. Open and closed arrowheads represent PEX4 and ubiquitinated PEX4 polypeptides, respectively. Molecular markers are indicated in kDa on the center\n\nFigure 12: Figure 12. Figure S4Requirement of UBC activity by PEX4 in vivo. Wild-type and mutant PEX4 genes were expressed in apem7 mutants. Leaf (A, C, and E) and root (B, D, and F) cells in 26-day-old plants were observed. (A and B) PEX4WT. (C and D) PEX4P123L. (E and F) PEX4C90A. Bar = 20 μm"
      }
    ]
  },
  {
    "id": "PMC9192799_multi",
    "image": [
      "images/PMC9192799-f1.png",
      "images/PMC9192799-f2.png",
      "images/PMC9192799-f3.png",
      "images/PMC9192799-f4.png",
      "images/PMC9192799-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Adaptations of the 3T3-L1 adipocyte lipidome to defective ether lipid catabolism upon Agmo knockdown\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Determination of adipocyte-specific markers and AGMO activity during 3T3-L1 adipocyte differentiation. A: Oil Red O staining of differentiated (day 11, upper panel) and undifferentiated (day 0, lower panel) 3T3-L1 cells. B: Gene expression of late adipocyte markers adiponectin (Adipoq), leptin (Lep), peroxisome proliferator-activated receptor gamma (Pparg), and fatty acid-binding protein 4 (Fabp4) was analyzed by RT-qPCR using TaqMan technology. Open bars and open circles represent undifferentiated cells at day 0 prior to differentiation; gray bars, full circles correspond to mature adipocytes at day 11 after exposure of 3T3-L1 cells to the adipocyte differentiation medium 1 and 2 (n = 3). C: AGMO enzymatic activity in cell pellets of 3T3-L1 exposed to the basal medium at day 0 (open bars and open circles) and cells supplemented with the differentiation medium 1 and 2 at day 11 (gray bars and full circles) of adipogenesis (n = 3). D: Agmo gene expression of cells at day 0 (open bars and open circles) and day 11 (gray bars and full circles) of adipocyte differentiation. E: Time course of AGMO activity during differentiation of 3T3-L1 cells exposed to the standard hormonal differentiation cocktail (diff. med. control) or a hormonal induction medium devoid of either IBMX, RGZ, DEX, or IBMX/RGZ and DEX/RGZ in combination (n = 5). F: Lipid droplet quantification by Bodipy and Hoechst staining using the CellProfiler™ analysis software of 3T3-L1 cells at day 0 and day 11 incubated with the complete differentiation medium (control) or differentiation medium with omitted IBMX, RGZ, DEX, or IBMX/RGZ and DEX/RGZ (three areas per well; n = 4). Mean ± SEM except for the boxplots in F, which show the median ± interquartile range (IQR). Whiskers range from minimum to maximum. ∗P < 0.05, ∗∗P < 0.01, ∗∗∗P < 0.001, and ∗∗∗∗P < 0.0001.\n\nFigure 2: Figure 2. Agmo knockdown and the impact on lipid droplet mass and size during adipogenesis. A: AGMO enzymatic activity of 3T3-L1 cells harboring either a knockdown against the firefly luciferase as a control (black bars) or against Agmo (gray bars) at day 0 prior to differentiation and day 11 at the end of differentiation when mature adipocytes have formed (n = 5). B: Lipid droplet formation per cell of undifferentiated cells at day 0 and differentiated cells at day 11 using Bodipy for lipid droplet staining and Hoechst to stain cellular nuclei (four areas per well, n = 5). C: Violin plots showing lipid droplet size frequency distribution in the differentiated shLuc cell line (black) and the differentiated shAgmo knockdown cell line (gray) (12 areas per well, two wells per replicate, n = 3). The solid line represents the median and the staggered line the quartiles. D: Histogram showing the relative distribution of the lipid droplet size of shLuc adipocytes and shAgmo adipocytes (n = 3). Black bars and plots are representative for the shLuc control, while shAgmo cell lines are presented in gray. Mean ± SEM except for the boxplots in B, which show the median ± interquartile range (IQR). Whiskers range from minimum to maximum. ∗P < 0.05 and ∗∗P < 0.01.\n\nFigure 3: Figure 3. Remodeling of the cellular lipidome during adipocyte differentiation. A: Heatmap representation of the relative abundances of the 40 analyzed lipid classes for control (shLuc) and Agmo knockdown (shAgmo) after 0 and 11 days (d0 and d11). B: Pie chart of the relative abundances of the 40 major lipid classes during differentiation of the shLuc control and shAgmo from day 0 to day 11. All species are colored according to their respective lipid class indicated in the color legend on the right. C: Pie charts showing the relative abundance of neutral lipid species sorted according to their degree of desaturation in shLuc and shAgmo in vitro differentiated adipocytes at day 11. Total values below each chart indicate the cumulative relative abundance of all identified single lipid species that are shared in both cell lines and form the respective lipid class. Mean of N = 5 is shown.\n\nFigure 4: Figure 4. Detailed analysis of carbon chain length and saturation of single TG species upon Agmo knockdown in mature adipocytes. A: Volcano plot depicting the lipidomics data of TGs at day 11 of adipocyte differentiation. Significance cutoff is P < 0.01 as indicated by the horizontal dotted line. The vertical dotted line separates the log2(fold change) of decreased (blue dots) and increased (red dots) lipid species. B: Boxplots showing the relative abundances of TG at day 11 of adipocyte differentiation in the shLuc and shAgmo cell lines. A full list of accumulated or depleted metabolites is shown in supplemental Table S2.\n\nFigure 5: Figure 5. Behavior of lipid classes during 3T3-L1 adipocyte differentiation from day 0 to day 11 of adipocyte differentiation. Black symbols represent the shLuc cell line, and gray symbols depict the shAgmo cell line. Data are presented as mean ± SD, n = 5. ∗P < 0.05, ∗∗P < 0.01, and ∗∗∗P < 0.001."
      }
    ]
  },
  {
    "id": "PMC9221082_multi",
    "image": [
      "images/PMC9221082-f1.png",
      "images/PMC9221082-f2.png",
      "images/PMC9221082-f3.png",
      "images/PMC9221082-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Characterization of Severity in Zellweger Spectrum Disorder by Clinical Findings: A Scoping Review, Meta-Analysis and Medical Chart Review\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Flowchart showing overview of the literature search and study selection process for the scoping review.\n\nFigure 2: Figure 2. Kaplan–Meier analyses of survival according to severe, mild, and intermediate severity categories in individuals with ZSD. (A) Survival for 46 severe (red), 21 intermediate (blue), and 36 mild (green) (total 103) subjects from the case studies is shown; (B) survival for 72 severe, 52 intermediate, and 71 mild (total 195) subjects from the cohort studies is shown; (C) survival for 23 severe, 64 intermediate, and 49 mild (total 136) subjects from the natural history study is shown. The corresponding log-rank p value is shown for each cohort. The numbers at risk (number of surviving patients) are indicated below each curve.\n\nFigure 3: Figure 3. Predicted probabilities of each severity category by number of clinical findings at any age among seizure disorder, abnormal EEG, bilateral renal cortical microcysts, and cardiac abnormalities. Univariable multinomial logistic model was used to predict the probabilities of having severe (red), intermediate (blue), or mild (green) overall disease severity from the number of any of these 4 clinical findings. The 95% confidence intervals are shown as the error bars.\n\nFigure 4: Figure 4. Predicted probabilities of each severity category by plasma C26:0 fatty acid levels at any age. Univariable multinomial logistic model was used to predict the probabilities of having severe (red), intermediate (blue), or mild (green) overall disease severity from plasma C26:0 fatty acid levels measured in 8 severe, 44 intermediate, and 36 mild ZSD individuals (total 88 patients) from our natural history study. The 95% confidence intervals are shown as the dotted lines."
      }
    ]
  },
  {
    "id": "PMC9244630_multi",
    "image": [
      "images/PMC9244630-f1.png",
      "images/PMC9244630-f2.png",
      "images/PMC9244630-f3.png",
      "images/PMC9244630-f4.png",
      "images/PMC9244630-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Inferred Subcellular Localization of Peroxisomal Matrix Proteins of Guillardia theta Suggests an Important Role of Peroxisomes in Cryptophytes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Heterologous in vivo localization and analysis of PTS1 function of G. theta urate oxidase (UO) expressed in P. tricornutum. (A) Expression of N-terminally fused GFP to the full-length Gt_UO-containing C-terminal “SKL” as PTS1 in P. tricornutum resulted in small dot-like structures next to the plastid. Without the C-terminal tripeptide “SKL,” GFP-Gt_UO-ΔSKL fluorescence was observed throughout the whole cell. (B) Immunolabeling of GFP-Gt_UO expressing P. tricornutum with α-GFP revealed electron-dense structures in round-shaped compartment near the plastid P, mitochondria M, and nucleus N; PM plasma membrane. (C) Co-expression of GFP-Gt_UO and the peroxisomal marker mRuby3-SKL (Marter et al., 2020) in P. tricornutum resulted in similar small dot-like structures next to the plastid. TL transmitted light, PAF plastidial autofluorescence, GFP enhanced green fluorescence protein, mR3-SKL mRuby3-SKL fluorescence protein as peroxisomal marker, scale bar in (A, C) 10 μm, scale bar in (B) overview 1 μm and 0.5 μm in section.\n\nFigure 2: Figure 2. Immunolabeling with α-Gt_UO.12aaC in G. theta and P. tricornutum expressing GFP-Gt_UO. Electron-dense structures in small round-shaped compartments were immunolabeled with the specific antibody α-Gt_UO.12aaC on ultrathin sections of G. theta (B) wildtype and P. tricornutum (A) expressing GFP-Gt_UO indicating localization in peroxisomes. In G. theta additional labeling in the plastid could be observed. PM plasmid membrane, P plastid, N nucleus, M mitochondrion, scale bar 0.5 μm.\n\nFigure 3: Figure 3. Heterologous in vivo co-localization of G. theta PTS1-containing proteins co-expressed in full length in P. tricornutum mR3-SKL. Heterologous localization studies of G. theta PTS1-containing enzymes in P. tricornutum expressing a peroxisomal marker (mR3-SKL). Peroxisomal localization was confirmed for APX (ascorbate peroxidase), MenB (1,4-dihydroxy-2-naphtoyl-CoA synthase), FAR (fatty acyl-CoA reductase), MD (malate dehydrogenase), and NME (NAD-dependent malic enzyme). TL transmitted light, PAF plastid autofluorescence, GFP enhanced green fluorescence protein, mR3-SKL mRuby3-SKL fluorescence protein as peroxisomal marker, scale bar 10 μm.\n\nFigure 4: Figure 4. Heterologous in vivo co-localization studies of factors involved in the first step of fatty acid β-oxidation in G. theta co-expressed in P. tricornutum mR3-SKL. GFP-Gt_ACOX (acyl-CoA oxidase) was localized in the cytosol, whereas Gt_ACOX-GFP is targeted to the mitochondrion when localized heterologously in P. tricornutum. The initial mitochondrial enzyme for β-oxidation ACAD (acyl-CoA dehydrogenase) was detected in G. theta containing both a mTP and a non-canonical putative PTS1 signal. When expressed heterologously in P. tricornutum, GFP-Gt_ACAD and GFP-Gt_ACAD.12aaC were localized in the cytosol, indicating no impact of the C-terminal tripeptide on PTS1 import into peroxisomes at least in P. tricornutum. Expression of C-terminal GFP fused to ACAD (Gt_ACAD-GFP) in P. tricornutum resulted in dot-like localization not correlating the peroxisomal marker. TL transmitted light, PAF plastid autofluorescence, GFP enhanced green fluorescence protein, mR3-SKL mRuby3-SKL fluorescence protein as peroxisomal marker, scale bar 10 μm.\n\nFigure 5: Figure 5. Model of the predicted metabolic pathways in the cryptomonad G. theta. For details see main text. Abbreviations: ACAD acyl-CoA dehydrogenase, ACOX acyl-CoA oxidase, ECH enoyl-CoA hydratase, 3HCD 3-hydroxyacyl-CoA dehydrogenase, 3KCT 3-Ketoacyl-CoA thiolase, FAR fatty acid reductase, DHAP dihydroxyacetone phosphate, GPAT/DHAPAT glycerolphosphate acyltransferase/dihydroxyacetone phosphate acyltransferase, AGPS alkyl-dihydroxyacetone phosphate synthase, MAO monoamine oxidase, AsA ascorbate, APX ascorbate peroxidase, MDHA monodehydroascorbate, MDHAR MDHA reductase, DHA dehydroascorbate, DHAR DHA reductase, GR glutathione reductase, XDH/XO xanthine dehydrogenase/oxidase, UO urate oxidase, ALN allantoinase, ALC allantoicase, ASP asparaginase, AAT amino aspartate transferase, c/pMD cytosolic/peroxisomal malate dehydrogenase, NME NAD-dependent malic enzyme, PHYLLO consisting of MenF, MenD, MenH, MenC; MenB DNC synthetase, MenA phytyltransferase/polyprenyltransferase, MenG methyltransferase, MVK mevalonate kinase. Bold localized proteins, black bioinformatically predicted location (manually detected PTS1/PTS2-like containing proteins), gray not identified in G. theta; further, not localized PTS1-candidates are not included in this model."
      }
    ]
  },
  {
    "id": "PMC9265560_multi",
    "image": [
      "images/PMC9265560-f1.png",
      "images/PMC9265560-f2.png",
      "images/PMC9265560-f3.png",
      "images/PMC9265560-f4.png",
      "images/PMC9265560-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Alleviation of Metabolic Disturbance by Substituting Kanjang High in Bacillus for Salt through Modulation of Gut Microbiota in Estrogen-Deficient Rats\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Relative abundance of bacteria in traditionally made kanjang according to Bacillus and bioamines contents. (A). The genus level (B). The species level. K-HBLB, TMK with high contents of Bacillus spp. and high biogenic amines; K-HBHB, TMK with high contents of Bacillus spp. and low biogenic amines; K-LBHB, TMK with low contents of Bacillus spp. and high biogenic amines; K-LBLB, TMK with low contents of Bacillus spp. and low biogenic amines. a–c Different letters beside the bars indicated a significant difference among the groups by Tukey test at p < 0.05.\n\nFigure 2: Figure 2. Tail skin temperature and passive avoidance test after ovariectomized rats. (A). Tail skin temperature during 7–12 weeks (B). Time to enter the darkroom. Dots or bars and error bars represent the means ± standard deviations (n = 10). HBLB, the rats fed TMK with high contents of Bacillus spp. and high biogenic amines; HBHB, the rats fed TMK with high contents of Bacillus spp. and low biogenic amines; LBHB, the rats fed TMK with low contents of Bacillus spp. and high biogenic amines; LBLB, the rats fed TMK with low contents of Bacillus spp. and low biogenic amines. * Significantly different among the groups at p < 0.05. a–c Different letters on the bars indicated a significant difference among the groups by Tukey test at p < 0.05.\n\nFigure 3: Figure 3. The differences in body composition (A). Differences of fat mass in abdomen and leg before and after ovariectomy. (B). Differences in lean body mass in the hip and leg before and after ovariectomy. (C). Differences in bone mineral density in the lumbar spine and femur before and after ovariectomy. Bars and error bars represent the means ± standard deviations (n = 10). HBLB, the rats fed TMK with high contents of Bacillus spp. and high biogenic amines; HBHB, the rats fed TMK with high contents of Bacillus spp. and low biogenic amines; LBHB, the rats fed TMK with low contents of Bacillus spp. and high biogenic amines; LBLB, the rats fed TMK with low contents of Bacillus spp. and low biogenic amines. a–c Different letters on the bars indicated a significant difference among the groups by the Tukey test at p < 0.05.\n\nFigure 4: Figure 4. Serum glucose concentrations during oral glucose tolerance (OGTT) and intraperitoneal insulin tolerance test (IPITT). (A). Changes in serum glucose concentrations after oral intake of 2 g glucose per kg body weight during OGTT. (B). Changes in serum insulin concentration during IPITT. (C). Changes in serum glucose concentration after intraperitoneal injection of 1 U insulin per kg body weight. (D). The area under the curve of serum glucose concentration during OGTT and IPITT. Dots or bars and error bars represent the means ± standard deviations (n = 10). HBLB, the rats fed TMK with high contents of Bacillus spp. and high biogenic amines; HBHB, the rats fed TMK with high contents of Bacillus spp. and low biogenic amines; LBHB, the rats fed TMK with low contents of Bacillus spp. and high biogenic amines; LBLB, the rats fed TMK with low contents of Bacillus spp. and low biogenic amines. OGTT, oral glucose tolerance test; IPITT, intraperitoneal insulin tolerance test. * Significantly different among the groups at p < 0.05. a–d Different letters on the bars indicated a significant difference among the groups by Tukey test at p < 0.05.\n\nFigure 5: Figure 5. Short-chain fatty acid (SCFA) concentrations and fecal bacteria composition. (A). SCFA concentrations in the blood from the portal vein. (B). Relative abundance of fecal bacteria from the cecum at the family level. (C). Relative abundance of fecal bacteria from the cecum at the genus level. (D). β-diversity of fecal bacteria. Colored circles indicated the separation of each group by the assigned color in each group. (E). Linear discriminant analysis (LDA) scores in Lefse analysis at the genus level. (F). A network analysis of visceral fat, glucose intolerance, insulin resistance, SCFA, and gut microbiota. The correlation coefficient > 0.4 and p < 0.0001. SCFA, short-chain fatty acids; AUCG, the area of serum glucose concentration during the oral glucose tolerance test; Fat mass, visceral fat mass. Bars and error bars represent the means ± standard deviations (n = 10). HBLB, the rats fed TMK with high contents of Bacillus spp. and high biogenic amines; HBHB, the rats fed TMK with high contents of Bacillus spp. and low biogenic amines; LBHB, the rats fed TMK with low contents of Bacillus spp. and high biogenic amines; LBLB, the rats fed TMK with low contents of Bacillus spp. and low biogenic amines. a–c Different letters on the bars indicated a significant difference among the groups by Tukey test at p < 0.05."
      }
    ]
  },
  {
    "id": "PMC9266905_multi",
    "image": [
      "images/PMC9266905-f1.png",
      "images/PMC9266905-f2.png",
      "images/PMC9266905-f3.png",
      "images/PMC9266905-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Homozygosity for a Novel DOCK7 Variant Due to Segmental Uniparental Isodisomy of Chromosome 1 Associated with Early Infantile Epileptic Encephalopathy (EIEE) and Cortical Visual Impairment\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clinical findings in the index patient. (A) EEG of the patient showing generalized epileptiform discharges. (B–D) Brain MRI: Sagittal T1-weighted image showing pontine hypoplasia (arrowhead in (B)). Axial T2-weighted images (C,D) demonstrating an abnormally marked anterior median fissure at the pontomedullary junction (large arrow in (C)), multiple microcysts in the cerebellar hemispheres and cerebellar vermis (arrowheads in (C,D)), and hyperintense signal of the occipital white matter (asterisk in (D)).\n\nFigure 2: Figure 2. Pedigree and Sanger sequencing profiles: (A) Pedigree of the index patient. The black arrow represents the patient. Symbols with central dots indicate heterozygous carriers. Genotypes are indicated below the pedigree symbols. M represents the sequence variant c.5391delA (p.(Ala1798LeufsTer59)) in the DOCK7 gene, and (-) indicates the reference allele. (B) Shown are the electropherograms of five family members: the homozygous sequence variant c.5391delA (p.(Ala1798LeufsTer59)) was identified in the index patient (III.1). Her mother (II.2) and the maternal grandmother (I.2) were heterozygous, while her father (II.1) and maternal grandfather (I.1) were non-carriers for this variant. The red arrow indicates the variant position.\n\nFigure 3: Figure 3. (A) Schematic of DOCK7 showing the relative location of the frameshift variant c.5391delA in Exon 42 (NM_001271999.1). DOCK homology domains DHR1 (amino acids 516–727) and DHR2 (amino acids 1668–2110) and TACC3-binding region (T-b). (B) Evolutionary conservation of the frameshift variant among 10 vertebrates.\n\nFigure 4: Figure 4. Details of maternal UPD by SNP array analysis of chromosome 1. (A) B-allele chart displayed four segments of chromosome 1 alternately homozygous (UPiD; shown in blue, no heterozygous SNPs, only AA and BB)) and heterozygous (UPhD; SNPs with AB genotype present) regions. (B) The DOCK7 gene (red circle) is located in p31.3, a region situated in one of the four homozygous segments. (C) Aneuploidy screening (Log R Ratio) did not show aneuploidies or CNVs >10 Mb."
      }
    ]
  },
  {
    "id": "PMC9279554_multi",
    "image": [
      "images/PMC9279554-f1.png",
      "images/PMC9279554-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Multifaceted Roles of the E3 Ubiquitin Ligase RING Finger Protein 115 in Immunity and Diseases\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Conserved domains of RNF115. The BZF domain (yellow) binds ubiquitin and is the site of RNF115 auto-ubiquitination (ubiquitinated lysine residues are shown in red). The 14-3-3 binding domain (green) is site of RNF115-14-3-3 interaction (AKT phosphorylation residues are shown in red). The RING H2 domain (blue) is the site of RNF115 autoubiquitination. The E3 ligase activity residues were shown in red.\n\nFigure 2: Figure 2. The signaling pathways regulated by RNF115 in innate immunity. In steady state, RNF115 constitutively interacts with and catalyzes K48-linked ubiquitination of MAVS, leading to the proteasomal degradation of homeostatic MAVS. Upon infection with RNA viruses, RIG-I–MAVS interaction led to RNF115 dissociation from MAVS, thereby initiating downstream signal transduction. Moreover, RNF115 functions as a restriction factor for HIV-1 infection. Firstly, RNF115 interacts with BST2 to promote the newly synthesized HIV-1 particles on the plasma membrane for lysosomal degradation. Secondly, RNF115 directly catalyzes ubiquitination of HIV-1 Gag, leading to its lysosomal degradation independently on BST2. Thirdly, RNF115 targets IκBα for SUMOylation, inhibiting HIV-1-induced NF-κB activation and HIV-1 transcription. In addition, The 14-3-3 chaperones bind to AKT1-phosphorylated RNF115 and facilitate RNF115 localizing at the ER. RNF115 interacts with and induces K63-linked ubiquitination of MITA at ER during infection of DNA viruses, promoting aggregation of MITA and the production of type I IFNs and proinflammatory cytokines. RNF115 also interacts with TLRs and buds off the ER onto the coat protein complex II vesicles. RNF115 catalyzes K11-linked ubiquitination of RAB1A to inhibit the extraction of RAB1A by GDI1. In addition, RNF115 inhibits the post-Golgi trafficking of TLR2, TLR4, and TLR9 by catalyzing K11-linked ubiquitination on RAB13. Consequently, the trafficking of TLR4 from the Golgi apparatus to cell surface and the trafficking of TLR9 to cell surface en route to endolysosomes were inhibited. Finally, RNF115 also inhibits phagosome maturation during S. aureus infection."
      }
    ]
  },
  {
    "id": "PMC9283435_multi",
    "image": [
      "images/PMC9283435-f1.png",
      "images/PMC9283435-f2.png",
      "images/PMC9283435-f3.png",
      "images/PMC9283435-f4.png",
      "images/PMC9283435-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Adipocyte lysoplasmalogenase TMEM86A regulates plasmalogen homeostasis and protein kinase A-dependent energy metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. a Heatmap of RNA-seq data showing the effects of 8 weeks of high-fat diet (HFD) feeding on genes involved in ether lipid metabolism (GO: 0046485) in gWAT. (NCD: normal chow diet, *| fold change (FC) | > 2; p < 0.05) b–d qPCR analysis of Tmem86a and Tmem86b in BAT, iWAT and gWAT of mice fed a NCD or HFD for 8 weeks. n = 6. e–g Immunoblot analysis of TMEM86A expression. n = 6. h Analysis of TMEM86A expression in human adipose tissue (non-obesity (NO): n = 9; insulin-sensitive obesity (OIS): n = 21; insulin-resistant obesity (OIR): n = 18), determined by publicly available transcriptomic data (Gene Expression Omnibus (GEO) repository, accession number GSE94753). qPCR analysis of Tmem86a expression in adipocytes and stromal vascular fraction (SVF; F4/80+, PDGFRα+, or F4/80-PDGFRα-) isolated from iWAT (i) and gWAT (j) of mice. n = 3. Each point represents a biological replicate. Data are presented as the mean ± SEM. Statistical significance was determined using the unpaired, two-tailed t-test in a–j. Source data are provided as a Source Data file.\n\nFigure 2: Figure 2. a Immunoblot analysis of TMEM86A expression in C3H10T1/2 adipocytes overexpressing TMEM86A (OE) or controls (mock) n = 3. Data are presented as the mean ± SEM. b–d PCA, volcano plot, and heatmap of phospholipid profiling of TMEM86A-overexpressing C3H10T1/2 adipocytes (OE) or controls (mock). e, f Normalized intensity of lysoplasmalogens and plasmalogens from phospholipid profiling of TMEM86A-overexpressing C3H10T1/2 adipocytes or controls. n = 3. (Intensity was normalized by median, *FDR < 0.05). Data are presented as the mean ± SEM. g LPE P-18:0 consumption levels of TMEM86A-overexpressing C3H10T1/2 adipocytes or controls. Cells were treated with LPE P-18:0 (1 μM) and then LPE P-18:0 in conditioned media were measured by LC-MS at indicated time. LPE P-18:0 consumption was calculated by subtracting LPE P-18:0 peak area at each time point from the initial value followed by normalization with a total protein quantity of cells. n = 3. Data are presented as the mean ± SD. h AlphaFold 3D model of human TMEM86A protein (AF-Q5BLD1-F1-model_v2.pdb). i Representative images of C3H10T1/2 adipocytes overexpressing GFP-tagged TMEM86A, stained with ER-Tracker. Nuclei and lipid were counterstained with DAPI and LipidTox, respectively. Scale bars = 10 μm. n = 3. j Immunoblot analysis of TMEM86A expression in HEK293T cells overexpressing WT, D82A mutant, or D190A mutant TMEM86A. n = 3. k LPE P-18:0 consumption levels of HEK293T cells overexpressing WT and mutant TMEM86A. n = 3. (WT OE + LPE P-18:0 vs. D82A OE + LPE P-18:0: p = 0.036525, p = 0.002498, p = 0.001757, p = 0.000735, or p = 0.001335, respectively for 2, 4, 6, 8, or 12 h; WT OE + LPE P-18:0 vs. D190A OE + LPE P-18:0: p = 0.019168, p = 0.003337, p = 0.00967, p = 0.02689, or p = 0.251998, respectively for 2, 4, 6, 8, or 12 h). p value was calculated by comparing each mutant group with WT OE + LPE P-18:0 as a control group. Data are presented as the mean ± SD. Each point represents a biological replicate. Statistical significance was determined using the unpaired, two-tailed t-test in a, e, f, g and using ANOVA (one-way, Bonferroni’s test) in k. Source data are provided as a Source Data file.\n\nFigure 3: Figure 3. a Schematic diagram showing generation of adipocyte-specific TMEM86A knockout mice (TMEM86A AKO). b–e Immunoblot analysis of TMEM86A expression in adipose tissue of WT and TMEM86A AKO mice. n = 6. f PCA plots showing a separation of clusters of WT and TMEM86A AKO samples. Heatmap analysis (g) and volcano plots (h–j) of untargeted phospholipid profiling of BAT, iWAT and gWAT from WT and TMEM86A AKO mice. Lysoplasmalogens are highlighted in yellow in h–j. BAT WT: n = 11, KO: n = 12; iWAT WT: n = 13, KO: n = 13; gWAT WT: n = 12, KO: n = 14. k–p Normalized intensities of lysoplasmalogens in BAT, iWAT and gWAT of WT and TMEM86A AKO mice (Intensity was normalized by median, *FDR < 0.05). BAT WT: n = 11, KO: n = 12; iWAT WT: n = 13, KO: n = 13; gWAT WT: n = 12, KO: n = 14. (WT BAT vs. AKO BAT: p < 0.000001 for LPC P-18:0, LPC P-18:1, LPC P-20:0, LPE P-16:0, LPE P-18:0, LPE P-18:1, LPE P-18:2, LPE P-20:0, and LPE P-20:1; WT iWAT vs. AKO iWAT: p = 0.000003 for LPC P-16:0, p = 0.001422 for LPE P-16:0, p = 0.000835 for LPE P-18:1, p < 0.000001 for LPC P-18:0, LPC P-20:0, LPE P-18:0, LPE P-20:0, and LPE P-20:1; WT gWAT vs. AKO gWAT: p = 0.001322 for LPC P-16:0, p = 0.000694 for LPC P-20:0, p = 0.012532 for LPE P-16:0, p = 0.000865 for LPE P-18:1, p < 0.000001 for LPC P-18:0, LPE P-18:0, LPE P-20:0, and LPE P-20:1) Each point represents a biological replicate. Data are presented as the mean ± SEM. Statistical significance was determined using the unpaired, two-tailed t-test in a and k–p. Source data are provided as a Source Data file.\n\nFigure 4: Figure 4. a–d Immunoblot analysis of BAT, iWAT and gWAT of WT and TMEM86A AKO mice. n = 6. e–h Indirect calorimetry analysis. Arrows indicates CL316,243 (CL) injection. EE: energy expenditure; RER: respiratory exchange ratio; VO2: rate of oxygen consumption; VCO2: rate of carbon dioxide production. n = 6. i, j Monitoring of food intake and activity. k Body fat and lean mass. n = 6. l Infrared thermal images showing skin temperature at room temperature or after 60 min of cold exposure (4 °C). n = 4. m, n Triphenyltetrazolium chloride (TTC) staining of BAT, iWAT, and gWAT and quantification. n = 6. o–q Electron microscopy of BAT, iWAT and gWAT. Boxed regions are magnified. n = 6. Each point represents a biological replicate. Data are presented as the mean ± SEM. Statistical significance was determined using the unpaired, two-tailed t-test in d–j and n. Source data are provided as a Source Data file.\n\nFigure 5: Figure 5. a–d Immunoblot analysis of adipocytes differentiated from precursors obtained from BAT, iWAT and gWAT of WT and TMEM86A AKO mice. n = 3. e, f Oxygen consumption rate measurement of adipocytes differentiated from precursors obtained from gWAT of WT and TMEM86A AKO mice. n = 3. g–i Immunoblot and qPCR analyses of TMEM86A overexpression effects in C3H10T1/2 adipocytes. n = 3. j, k Oxygen consumption rate of TMEM86A overexpressing C3H10T1/2 adipocytes or controls. n = 5. Each point represents a biological replicate. Data are presented as the mean ± SEM. Statistical significance was determined by the unpaired, two-tailed t-test in d–f, h–i, and k. Source data are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC9283435_multi_2",
    "image": [
      "images/PMC9283435-f6.png",
      "images/PMC9283435-f7.png",
      "images/PMC9283435-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Adipocyte lysoplasmalogenase TMEM86A regulates plasmalogen homeostasis and protein kinase A-dependent energy metabolism\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. a Body weight monitoring of WT and TMEM86A AKO mice during 8-weeks of HFD feeding. n = 6. (WT HFD vs. KO HFD: p = 0.015084, p = 0.006167, p = 0.042557, p = 0.026351, p = 0.019894, p = 0.040475, p = 0.004757, p = 0.010575, or p = 0.1215, respectively for week 0, 1, 2, 3, 4, 5, 6, 7, or 8; WT NCD vs. KO NCD: p = 0.039863, p = 0.010424, p = 0.003051, or p = 0.003318, respectively for week 5, 6, 7, or 8). b Weights of adipose tissue of WT and TMEM86A AKO mice fed a NCD or HFD. n = 6. c, d Intraperitoneal glucose tolerance test. n = 4. e–g Immunoblot analysis of BAT, iWAT and gWAT. n = 6. h H&E staining of paraffin sections of BAT, iWAT and gWAT. n = 6. Scale bar = 50 μm. i Immunoblot analysis of F4/80 in gWAT. n = 6. j Immunofluorescence staining of F4/80 in paraffin sections of gWAT. n = 6. Scale bar = 20 μm. k, l Flow cytometric analysis of CD45+CD11b+CD64+CD11C+ cells (M1-like macrophages) and CD45+CD11b+CD64+CD206+ cells (M2-like macrophages) in gWAT. n = 3. Each point represents a biological replicate. Data are presented as mean ± SEM. Statistical significance was determined using the unpaired, two-tailed t-test in a, b, d, e–g, i, Source data are provided as a Source Data file.\n\nFigure 7: Figure 7. a, b Immunoblot analysis of C3H10T1/2 adipocytes treated with vehicle control (VC), LPC P-18:0 (LPC-P, 10 μM) or LPE P-18:0 (LPE-P, 10 μM) for 24 h or isoproterenol (ISO, 10 μM) for 4 h. n = 4. c, d Immunoblot analysis of C3H10T1/2 adipocytes treated with VC, ISO (10 μM), LPC-P (10 μM), LPE-P (10 μM), ISO (10 μM) + H89 (PKA inhibitor, 50 μM), LPC-P (10 μM) + H89 (50 μM), or LPE-P (10 μM)+H89 (50 μM). n = 3. (p-HSL/HSL VC vs. ISO: p < 0.000001; VC vs. LPC-P: p = 0.000128; VC vs. LPE-P: p = 0.000009; ISO vs. ISO + H89: p < 0.000001; LPC-P vs. LPC-P + H89: p = 0.000056; LPE-P vs. LPE-P + H89: p = 0.000006)(p-CREB/CREB VC vs. ISO: p = 0.000035; VC vs. LPC-P: p = 0.000018; VC vs. LPE-P: p = 0.000019; ISO vs. ISO + H89: p = 0.000172; LPC-P vs. LPC-P + H89: p = 0.000143; LPE-P vs. LPE-P + H89: p = 0.000109). e Intracellular cAMP levels in C3H10T1/2 adipocytes treated with VC, LPC-P (10 μM), or LPE-P (10 μM) for 24 h or ISO (10 μM) for 4 h. n = 3. f Levels of 5' AMP released by PDE3B incubated with VC, IBMX (40 μM), or LPE-P (10 μM) for 90 min. n = 3. g, h Immunoblot analysis of C3H10T1/2 adipocytes treated with VC, LPC-P (10 μM) or LPE-P (10 μM) for 48 h or isoproterenol (ISO, 10 μM) for 24 h. n = 4. i, j Oxygen consumption rate measurement in C3H10T1/2 adipocytes treated with VC, LPC-P (10 μM) or LPE-P (10 μM) for 24 h. n = 5. Each point represents a biological replicate. Data are presented as mean ± SEM. Statistical significance was determined by the unpaired, two-tailed t-test in b, d, e, f, h and j. * represents statistical analysis between C3H10T1/2 adipocytes treated with VC and C3H10T1/2 adipocytes treated with either ISO, LPC-P, or LPE-P. # represents statistical analysis between C3H10T1/2 adipocytes treated with either ISO, LPC-P, or LPE-P and C3H10T1/2 adipocytes treated with either ISO + H89, LPC-P + H89, or LPE-P + H89. Source data are provided as a Source Data file.\n\nFigure 8: Figure 8. a Concentration of LPE P-18:0 (LPE-P) in serum of TMEM86A AKO mice or WT mice treated with either VC or LPE-P for 2 weeks (i.p. 200 μg/kg/day). n = 4. b, c Intraperitoneal glucose tolerance test of WT mice fed a HFD treated intraperitoneally with VC or LPE-P for 2 weeks. n = 4. d–g Immunoblot analysis of BAT, iWAT and gWAT of WT mice fed a HFD treated with VC or LPE-P for 2 weeks (i.p. 200 μg/kg/day). n = 6. h Grouping of 48 individuals in quartile according to body mass index (BMI). i Normalized intensities of lysoplasmalogen LPE P-18:0 in human subcutaneous adipose tissue (Intensity was normalized by median, *FDR < 0.05). n = 48. j Correlation analysis of normalized intensity of LPE P-18:0 with BMI. n = 48; linear regression of correlation; R = −0.4717, p = 0.0007. Each point represents a biological replicate. Data are presented as mean ± SEM. Statistical significance was determined using the unpaired, two-tailed t-test in a, c, and g and using ANOVA (one-way, Tukey’s HSD post-hoc analysis) in h and i. Source data are provided as a Source Data file."
      }
    ]
  },
  {
    "id": "PMC9366280_multi",
    "image": [
      "images/PMC9366280-f1.png",
      "images/PMC9366280-f2.png",
      "images/PMC9366280-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"X-linked adrenoleukodystrophy caused by maternal ABCD1 mutation and paternal X chromosome inactivation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigree and brain MRI of the patient. (A) Pedigree of the X-linked adrenoleukodystrophy family. III1 indicates the patient; square, male; circle, female. (B) Brain MRI of the patient revealed asymmetric demyelination of bilateral white matter. MRI, magnetic resonance imaging; XCI, X chromosome inactivation.\n\nFigure 2: Figure 2. Sequencing analysis. (A) Mutation was identified by whole exome sequencing, suggested a heterozygous c.919C>T (p.Q307X) variation of ATP-binding cassette subfamily D member 1 (red box). (B) SNP haplotype linkage analysis of the family. The numbers represent the relative distance in kb up-(blue) and downstream (orange) of gene. (C) Mutation was positive in the patient III1 and mother II1, but not in I2 or II2, as shown by Sanger sequencing.\n\nFigure 3: Figure 3. XCI analysis. From the undigested chart, the 277 bp fragment in patient III1 was from her father II2 and the 288 bp fragment was from her mother II1. From the HpaII-digested chart, patient demonstrated skewed XCI and paternal X chromosome was almost completely inactivated. X-axis represents the fragment size (bp) and Y-axis represents the peak value. XCI, X chromosome inactivation."
      }
    ]
  },
  {
    "id": "PMC9388378_multi",
    "image": [
      "images/PMC9388378-f1.png",
      "images/PMC9388378-f2.png",
      "images/PMC9388378-f3.png",
      "images/PMC9388378-f4.png",
      "images/PMC9388378-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Genomic signatures for drylands adaptation at gene-rich regions in African zebu cattle\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The geography of Sudan shows the sampling areas of the Sudanese zebu cattle populations. Map adapted from Impiglia [9]. Photo credit: Professor Hassan Musa, University of Khartoum, Sudan.\n\nFigure 2: Figure 2. Genetic diversity and population structure of the 17 studied breeds. (A) Boxplot of average nucleotide diversities (π). The nucleotide diversity level within each cattle breed was calculated based on an overlapping 100 kb window with a 50 kb step size. (B) Principal component (PC 1 versus PC 2) analysis for 17 cattle breeds. (C) Principal component (PC 1 versus PC 2) analysis for the six Sudanese zebu cattle populations. (D) Admixture plot showing ancestry proportions for the 17 cattle breeds. The population structure was assessed using ADMIXTURE ver.1.3.0. The individual population is represented by a vertical bar and partitioned into coloured segments. Each segment's length represents the proportion of the inferred number of ancestries (K = 2 to K = 5). GIR – Gir, GAS – Gash, ARY – Aryashai, BTN – Butana, KEN – Kenana, BAG – Baggara, FLN – Fulani, OGD – Ogaden, BOR – Kenya Boran, ANK – Ankole, NDA – N'Dama, MUT – Muturu, YKT – Yakutian, WES – Western Finncattle, EAS – Eastern Finncattle, AAN – Angus, and HOL – Holstein. The cattle breeds were also grouped into six entities, namely, Asian zebu (ASZ), Sudanese zebu (SUD), East African zebu (AFZ), African sanga (AFS), West African taurine (WAT), and European taurine (EUT).\n\nFigure 3: Figure 3. Maximum likelihood evolutionary tree and possible gene flow among the 17 cattle breeds: (A) without migration events, (B) assuming ten migration events. E-Finn (Eastern Finncattle) W-Finn (Western Finncattle), K-Boran (Kenyan Boran).\n\nFigure 4: Figure 4. Genome-wide distribution of ZHp scores across bovine autosomes in six Sudanese zebu populations. The blue line indicates the ZHp threshold value (lowest 0.5%) for selecting outlier windows (candidate regions under positive selection). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)\n\nFigure 5: Figure 5. Genome-wide distribution of ZFST scores along the Bos taurus (ARS-UCD1.2) autosomes and overlap of detected protein coding genes following the population differentiation FST analyses between Sudanese zebu populations and the populations of other cattle breeds. (A) FST analysis between population of six Sudanese zebu breeds and other zebu/sanga (Kenya Boran, Ogaden, Ankole and Gir). (B) Venn diagram showing the overlap of detected protein-coding genes between ZHp and FST tests in (A). (C) FST analysis between five Sudanese zebu breeds (except Fulani) and the population of other zebu/sanga comprising Fulani, Kenya Boran, Ogaden, Ankole and Gir). (D) FST analysis between population of five Sudanese zebu breeds (except Fulani) and the population of all taurine breeds studied. The blue lines indicate the top 0.5% ZFST values threshold to consider outlier regions. (E) Venn diagram showing the numbers of overlapping detected protein-coding genes between ZHp and FST tests in (C) and (D). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)"
      }
    ]
  },
  {
    "id": "PMC9388378_multi_2",
    "image": [
      "images/PMC9388378-f6.png",
      "images/PMC9388378-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Genomic signatures for drylands adaptation at gene-rich regions in African zebu cattle\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Strong evidence of positive selection in Sudanese zebu population at a 250-kb chromosome 16 locus. (A) Genomic footprints of low diversity (ZHp) in the candidate region in eight African zebu breeds and Gir zebu. The red and black dashed line indicates the maximum and minimum genome-wide ZHp selection outlier threshold values among the cattle breeds. (B) Population differentiation (FST) between the Sudanese zebu populations (excluding the Fulani) and other zebu and taurine cattle populations. (C) Increased haplotype homozygosity (XP-EHH) at the 250 kb selective sweep locus in Sudanese zebu compared to other cattle populations. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)\n\nFigure 7: Figure 7. Localisation of SNPs at the Sudanese zebu-specific candidate selective sweep at the chromosome 16 locus following XP-EHH analysis between the combined five Sudanese breeds and (A), Fulani, and (B), other zebu breeds (East African and Gir breeds). (C) The decay of extended haplotype homozygosity around rs525024181 in Sudanese Zebu, (D) Fulani, and (E) other zebu breeds."
      }
    ]
  },
  {
    "id": "PMC9421440_multi",
    "image": [
      "images/PMC9421440-f1.png",
      "images/PMC9421440-f2.png",
      "images/PMC9421440-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"High incidence of null variants identified from newborn screening of X-linked adrenoleukodystrophy in Taiwan\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Algorithmic workflow including molecular testing for adrenoleukodystrophy newborn screening. The cutoff for first screen was 0.3 μM, and the second screen cutoff was 0.4 μM. Newborns positive for the first screening, including the first and second tier C26:0-LPC analysis using different methods, were subjected to both third-tier molecular testing for ABCD1 sequencing and a second screen since Aug. 1st, 2019. Those with a negative ABCD1 sequencing but positive second screen result were subjected to whole exome sequencing to clarify the etiology.\n\nFigure 2: Figure 2. C26:0-LPC levels in newborn screening reported in this study. (A) First screen C26:0-LPC levels for normal male newborns, normal female newborns, males with ABCD1 variants (n = 12), females with ABCD1 variants (n = 10), and Zellweger spectrum disorders (n = 3) are shown here. Significant differences were noted between males and emales with ABCD1 variants (p = 0.0026) and between Zellweger spectrum disorders and females with ABCD1 variants (p = 0.007). (B) Comparison of C26:0-LPC levels between male newborns with null (n = 5) or missense (n = 7) variants on the first and second screening. The boxes are the interquartile ranges (IQR, 25th to 75th percentile), and the whiskers are the ranges between 1.5 IQR of the lower quartile and 1.5 IQR of the higher quartile; the vertical bar denotes the median. *: p < 0.05.\n\nFigure 3: Figure 3. Brain MRI images of two adrenoleukodystrophy patients. Serial MRI scans for patient 1(A-C). Normal appearance of MRI at 1 year and 4 months old (A). Follow-up MRI at the age of 1 year 10 months showed a suspicious T2 hyperintensity at right parietal white matter (B). however, 3 months later there was no progression of MRI findings (C). Serial MRI scans for patient 2 (D—F). Normal appearance of MRI at 3 year and 8 months old (C). Follow-up MRI performed rat the age of 4 yeas 2 months was initially reported as normal, but the T2 abnormality at the splenium was already present (E). Follow-up scans revealed rapid progression of splenium T2-hyperintensity (F)."
      }
    ]
  },
  {
    "id": "PMC9438327_multi",
    "image": [
      "images/PMC9438327-f1.png",
      "images/PMC9438327-f2.png",
      "images/PMC9438327-f3.png",
      "images/PMC9438327-f4.png",
      "images/PMC9438327-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Prediction of evolutionary constraint by genomic annotations improves functional prioritization of genomic variants in maize\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Distribution of rejected substitution (RS) scores by category of DNA bases. RS scores, which integrate information about conservation (1 − Substitution rate) and MSA depth (Tree size), were calculated by gerp++ [4] as previously described [14]. Monomorphic sites: sites with no observed polymorphism within maize. SNPs: observed polymorphisms in Hapmap 3.2.1, a representative panel of inbred lines in maize [15]. SNPs in hybrid panels: subset of SNPs which are observed in two panels of hybrid crosses between inbred lines and testers [16]\n\nFigure 2: Figure 2. Prediction of mutation Impact by Calibrated Nucleotide Conservation (PICNC). Methodology for prediction of phylogenetic nucleotide conservation (PNC) by probability random forests. PNC was defined by high conservation (substitution rate < 0.05) over deep MSA (tree size > 5 expected neutral substitutions). Genomic annotations were produced only by sequence analysis. They described genomic structure and protein structure at nonsynonymous point mutations in maize coding regions. Monomorphic sites (no observed polymorphism within maize) were used for training, and observed SNPs were used for prediction. In leave-one-chromosome-out prediction, a probability random forest is trained ten times, once for each left-out chromosome\n\nFigure 3: Figure 3. Contribution of genomic annotations to prediction accuracy in probability random forests. A Classification accuracy of probability random forests for predicted phylogenetic nucleotide conservation (PNC). Accuracy: percentage of correct calls, i.e., the percentage of sites in chromosome 8 for which predicted PNC (rounded) equaled observed PNC, over three replicates. Accuracy was weighted to account for imbalance with respect to PNC (see “Methods”). Sets of genomic annotations were sequentially added to the set of predictors in probability random forests. Mutation type & SIFT score: Mutation type (missense, STOP gain or STOP loss), SIFT score (with missing values set to 1), and SIFT class (“constrained” if SIFT score ≤ 0.05, “tolerated” otherwise). Genomic structure: GC content, k-mer frequency and transposon insertion. Mutagenesis scores: in silico mutagenesis scores for UniRep variables. Protein features: UniRep variables, generated by the 256-unit UniRep model. B Relationship between SIFT scores and predicted PNC at maize SNPs (observed polymorphisms in Hapmap 3.2.1, a representative panel of inbred lines in maize [15]). Predicted PNC is computed by the full PICNC model, including all genomic annotations. Darker colors indicate higher density of SNPs. ρ: Spearman correlation coefficient. C Variable importance of genomic annotations. Variable importance: corrected impurity measure in probability random forests [18]. D Variable importance of protein features (UniRep variables), ordered in decreasing order. A subset of 10 UniRep variables stood out as contributing most to the prediction accuracy for PNC\n\nFigure 4: Figure 4. Relationship between phylogenetic nucleotide conservation (PNC) and experimental annotations at SNPs. A Decrease in observed and predicted PNC over within-species variability, quantified by MAF in reference panel Hapmap 3.2.1 [15]. B Increase in predicted PNC in accessible chromatin regions, defined by MNase hypersensitivity in shoot or root tissues [21]. C Positive association between observed PNC and expression QTL effect (in absolute values) in shoot or root tissues, estimated in a diverse maize panel [22]\n\nFigure 5: Figure 5. Prioritization of SNPs by SIFT score or phylogenetic nucleotide conservation (PNC). A Euler diagram of SNP sets prioritized by SIFT score = 0, observed PNC = 1, or predicted PNC > 90%, 99%, 99.9% percentile, in maize (observed polymorphisms in Hapmap 3.2.1). Concentric dashed circles refer to smaller subsets of SNPs prioritized by increasingly stringent thresholds on predicted PNC. B Decrease in minor allele frequency (MAF) of prioritized SNPs, in maize and sorghum. Difference in MAF between prioritized SNPs and all SNPs. Maize SNPs: observed polymorphisms in the Hapmap 3.2.1 reference panel [15]; Sorghum SNPs: observed polymorphisms in the reference panel of Lozano et al. [23]. SNPs were prioritized if their SIFT conservation (1 − SIFT score) or predicted PNC was above the 50%, 90%, 99%, or 99.9% percentile, or if their observed PNC was equal to 1 (tree size > 5, substitution rate < 0.05). Error bars and dotted lines represent 95% confidence intervals in two-sample t-tests, for SIFT score or predicted PNC, and observed PNC, respectively"
      }
    ]
  },
  {
    "id": "PMC9438327_multi_2",
    "image": [
      "images/PMC9438327-f6.png",
      "images/PMC9438327-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Prediction of evolutionary constraint by genomic annotations improves functional prioritization of genomic variants in maize\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Functional enrichment of genes prioritized by SIFT score or phylogenetic nucleotide conservation (PNC), in maize. Genes were prioritized by selecting SNPs with SIFT conservation (1 − SIFT score) or predicted PNC above the 50%, 90%, 99%, or 99.9% percentile, or observed PNC equal to 1 (tree size > 5, substitution rate < 0.05). A Difference in average expression between prioritized genes and all genes. Gene expression is quantified by RNA abundance (FPKM over 23 tissues) and protein abundance (dNSAF over 32 tissues) based on the gene expression atlas of [29]: median expression, and number of tissues with non-zero expression level. Error bars and dotted lines represent 95% confidence intervals in two-sample t-tests, for predicted and observed PNC, respectively. B Enrichment of prioritized genes for gene ontology (GO) classes. Ratio of number of prioritized genes over expected number under the null hypothesis (random gene prioritization). GO classes belong to the plant GO slim subset [30]. Ontology: BP, biological process; MF: molecular function. For each threshold and ontology, false discovery rates (FDR) were calculated over GO classes, based on P-values from Fisher’s exact tests. Full circles and full lines indicate FDR < 0.05, for SIFT conservation or predicted PNC, and observed PNC, respectively\n\nFigure 7: Figure 7. Prioritization of nonsynonymous SNPs in genomic prediction for grain yield, in hybrid maize lines. A Number of SNPs prioritized by SIFT conservation (1 − SIFT score), predicted phylogenetic nucleotide conservation (PNC), or observed PNC. B Genomic prediction accuracy within panel, in leave-one-family-out prediction in the Nested Association Mapping hybrid panel (NAM-H) [16]. C Genomic prediction accuracy across panels, from a diverse hybrid panel (Ames-H) to NAM-H, and vice versa [16]. Genomic prediction models included effects of population structure variables (top three principal components in the Hapmap 3.2.1 reference panel in maize), effects of genome-wide SNPs, and effects of nonsynonymous SNPs. Diamonds: nonsynonymous SNPs were weighted by SIFT conservation or predicted PNC, and prioritized by truncating weights to zero if they were under the 0%, 50%, 90%, 99%, or 99.9% percentile. Open circles: nonsynonymous SNPs were weighted and prioritized by 20 random permutations of SIFT conservation or predicted PNC, to determine whether the prediction accuracy by SNP weights was significantly different from the accuracy by random SNP weights"
      }
    ]
  },
  {
    "id": "PMC9442330_multi",
    "image": [
      "images/PMC9442330-f1.png",
      "images/PMC9442330-f2.png",
      "images/PMC9442330-f3.png",
      "images/PMC9442330-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal regulation of energy homeostasis: Effect on obesity and related metabolic disorders\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Role of peroxisomes in various organs across lean and obese states. In brown adipose tissue, peroxisome-derived ether lipids promote mitochondrial fission, which increases thermogenesis and energy expenditure. Certain species of plasmalogen, a form of ether lipid, are decreased in serum of obese individuals. Peroxisomal β-oxidation promotes fatty liver through multiple distinct mechanisms and contributes to non-esterified fatty acid (NEFA)-induced lipotoxicity in pancreatic β-cells, likely contributing to impaired glucose-stimulated insulin secretion (GSIS). Reactive oxygen species (ROS) from both peroxisomal and mitochondrial β-oxidation induce oxidative stress in adipose tissue of obese individuals, causing systemic insulin resistance.\n\nFigure 2: Figure 2. Peroxisomal lipid synthetic pathway. Glyceraldehyde 3-phosphate, a glycolysis intermediate, can be converted to dihydroxyacetone phosphate (DHAP) by triose phosphate isomerase (TPI). Glycerol-3-phosphate dehydrogenase (GPDH) catalyzes the conversion of DHAP to glycerol 3-phosphate (G3P), though both DHAP and G3P are believed to be transported to the peroxisomal matrix by peroxisomal membrane protein 2 (PXMP2). In peroxisomes GPDH may convert G3P back to DHAP, which subsequently has an acyl chain added to its sn-1 carbon by glyceronephosphate O-acyltransferase (GNPAT), yielding acyl-DHAP. Acyl-DHAP may have its sn-2 carbonyl reduced by PexRAP (Peroxisomal Reductase activating PPARγ; encoded by Dhrs7b) to yield lysophosphatidic acid (LPA) or it may have its sn-1 acyl chain replaced by a new sn-1 alkyl chain to yield alkyl-DHAP, a reaction catalyzed by alkylglycerone phosphate synthase (AGPS). Alkyl-DHAP is then reduced by PexRAP to form 1-O-Alkyl-G3P (AGP). LPA and AGP are shuttled to the endoplasmic reticulum for formation of diacyl phospholipids and ether-linked phospholipids, respectively. Ether lipids may be processed further to generate plasmalogens, a subclass of ether lipids with a cis-double bond.\n\nFigure 3: Figure 3. Adipose-specific peroxisome deficiency impairs mitochondrial fission and increases diet-induced obesity. Mice with adipose-specific knockout of Pex16 (Pex16-AKO) display impaired mitochondrial fission in brown adipose tissue, decreased thermogenesis, and increased diet-induced obesity. This phenotype is rescued by supplementation of ether-lipid synthetic intermediates, implicating ether lipids as the mediator linking peroxisomes with mitochondrial fission and thermogenesis.\n\nFigure 4: Figure 4. Peroxisomal β-oxidation promotes nonalcoholic fatty liver disease through multiple unique mechanisms. The first step of peroxisomal β-oxidation reduces FAD to FADH2, which in turn reduces O2 to H2O2. The oxidant stabilizes disulfide bonds in peroxisomal biogenesis factor 2 (Pex2), thus increasing the protein levels of Pex2, which mediates poly-ubiquitination of adipose triglyceride lipase (ATGL). This promotes targeted degradation of ATGL by proteasomes, resulting in impaired lipolysis and increased hepatic steatosis. An alternative mechanism involves the use of acetyl-CoA, a product of peroxisomal β-oxidation, in acetylation of regulatory-associated protein of mTOR (Raptor), part of the mammalian target of rapamycin complex 1 (mTORC1). Acetylation of Raptor activates mTORC1, resulting in impaired lipophagy and aberrant hepatic lipid accumulation."
      }
    ]
  },
  {
    "id": "PMC9451027_multi",
    "image": [
      "images/PMC9451027-f1.png",
      "images/PMC9451027-f2.png",
      "images/PMC9451027-f3.png",
      "images/PMC9451027-f4.png",
      "images/PMC9451027-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The SREBP-dependent regulation of cyclin D1 coordinates cell proliferation and lipid synthesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Cyclin D1 is regulated by members of the SREBP family of transcription factors. (A) HepG2 cells were transduced with lentiviruses encoding GFP or FLAG-tagged versions of the nuclear forms of SREBP1a (nS1a), SREBP1c (nS1c), or SREBP2 (nS2). The levels of cyclin D1, HMG-CoA synthase, the nuclear forms of SREBP1a, SREBP1c and SREBP2 (FLAG), and β-actin in total lysates were determined by Western blotting. The quantifications of cyclin D1 and HMG-CoA synthase across three independent experiments are included in Supplementary Figure S1 . (B) HepG2 cells were transduced as in (A), and mRNA was isolated and used to generate cDNA. The expression of cyclin D1 (CCND1) was determined by real-time qPCR using GAPDH for normalization. (C) HepG2 cells were transduced with lentiviruses encoding shRNAs, either non-targeted (C) or targeting SREBP1 (S1) or SREBP2 (S2). The levels of cyclin D1 and the precursor forms of SREBP1 (pSREBP1) and SREBP2 (pSREBP2) were detected by Western blotting. β-Actin was used as a loading control. (D) HepG2 cells were transduced with shRNA as in (C) and the expression of cyclin D1 was determined by real-time qPCR. (E) MCF7 cells were transduced with shRNA as in (C), and the levels of cyclin D1 and the precursor forms of SREBP1 (pSREBP1) and SREBP2 (pSREBP2) were detected by Western blotting. (F) MCF7 cells were transduced with shRNA as in (C), and the expression of cyclin D1 was determined by real-time qPCR. Significance was determined by one-way ANOVA with Tukey’s multiple comparisons adjustment (B, D, and F). p-values lower than 0.05 were considered statistically significant. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001. NS, not significant.\n\nFigure 2: Figure 2. The expression of cyclin D1 responds to physiological changes in SREBP activity. (A) HepG2 cells were grown in media supplemented with regular serum (FBS) or lipoprotein-deficient serum (LPDS). Where indicated, the LPDS was supplemented with 25-hydroxycholesterol (25-HC, 5 μg/ml) for 8 h before the end of the experiment. The levels of cyclin D1, nuclear SREBP1 (nSREBP1), and β-actin were determined by Western blotting (upper panel). The relative levels of cyclin D1 were quantified and are presented as fold change (lower panel). (B) HepG2 cells grown in regular media were left untreated or treated with 1% HPCD (w/v) for the indicated times. The levels of cyclin D1, nuclear SREBP1 (nSREBP1), and β-actin were determined by Western blotting (upper panel). The relative levels of cyclin D1 in untreated cells (−) and cells exposed to HPCD for 2 h (HPCD) were quantified and are presented as fold change (lower panel). Significance was determined by paired t-tests (B) or one-way ANOVA with Tukey’s multiple comparisons adjustment (A). p-values lower than 0.05 were considered statistically significant. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001. NS, not significant.\n\nFigure 3: Figure 3. The human cyclin D1 promoter is SREBP-responsive. (A) HEK293 cells were transfected with the CCND1-luc promoter-reporter gene (CCND1-Luc) together with either empty vector (pcDNA3) or expression vectors for the nuclear forms of SREBP1a (nS1a), SREBP1c (nS1c), or SREBP2 (nS2). Forty-eight hours after transfection, cells were lysed, and luciferase activity was measured. (B) HepG2 cells were transfected with the CCND1-luc promoter-reporter gene and treated as indicated. Cells in regular media were either left untreated or treated with 1% HPCD (w/v) for 4 h (left). Cells in LPDS were either left untreated or treated with 25HC (5 μg/ml) for 8 h (right). Forty-eight hours after transfection, cells were lysed, and luciferase activity was measured. (C) Schematic illustration of the human cyclin D1 promoter with the location of the E-box and putative SRE elements. (D) HepG2 cells were transfected with the CCND1-luc promoter–reporter gene, either wild type (WT) or the indicated deletion mutant (ΔSRE, ΔE-box or ΔΔ) together with either empty vector (pcDNA3) or an expression vector for the nuclear form of SREBP1a (nS1a). Forty-eight hours after transfection, cells were lysed, and luciferase activity was measured. (E) HepG2 cells were transfected with the CCND1-luc promoter–reporter gene, either wild type (WT) or the ΔE-box mutant, together with expression vectors for either non-targeted (C) or SREBP1-targeted (S1) shRNA. Forty-eight hours after transfection, cells were lysed, and luciferase activity was measured. Significance was determined by paired t-tests (B, D, E) or one-way ANOVA with Tukey’s multiple comparisons adjustment (A). p-values lower than 0.05 were considered statistically significant. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p< 0.0001. NS, not significant.\n\nFigure 4: Figure 4. SREBP1 interacts with the human cyclin D1 promoter. (A) 6xMyc-tagged nuclear SREBP1a (nS1a), SREBP1c (nS1c), and SREBP2 (nS2) were expressed in HEK293 cells and used in DNAP assays using a biotinylated DNA probe corresponding to the human cyclin D1 promoter. The three proteins were expressed at similar levels as monitored by Western blotting (left). Increasing amounts of the three proteins were incubated with the promoter probe, captured on streptavidin beads, washed, separated on SDS-PAGE gels, and analyzed by Western blotting (Myc, right). (B) Nuclear SREBP1a (nS1a, 10 μl), SREBP1c (nS1c, 10 μl), and SREBP2 (nS2, 50 μl) were incubated with the biotinylated cyclin D1 probe in the absence or presence of non-biotinylated competitor DNA corresponding to the SREBP-binding site in the human LDL receptor promoter (fivefold excess) and processed as in (A). (C) Nuclear SREBP1a (nS1a) was incubated with the biotinylated cyclin D1 probe, either wild-type (WT) or the indicated deletion mutant (ΔSRE, ΔE-box or ΔΔ) and processed as in (A). (D) FLAG-tagged nuclear SREBP1a (nS1a) was purified from transfected HEK293 cells and incubated with unlabeled DNA probes corresponding to the human cyclin D1 promoter, either wild-type (WT) or ΔE-box, separated on native PAGE gels and stained with SYBR Safe. The shifted SREBP1a–DNA complex is indicated by an arrow. The two probes alone were also run on the same gel (left two lanes). (E) FLAG-tagged nuclear SREBP1a (nS1a) was incubated with an unlabeled DNA probe corresponding to the human cyclin D1 promoter, separated on a native PAGE gel, and stained with SYBR Safe. Monoclonal anti-FLAG antibodies were added to the sample in lane 2 prior to loading it on the gel. The shifted SREBP1a–DNA complex and the supershifted SREBP1a–DNA–antibody complexes are indicated by arrows.\n\nFigure 5: Figure 5. The recruitment of SREBP1 to the cyclin D1 promoter correlates with enhanced expression of the cyclin D1 gene. (A) MCF7 cells were serum starved for 24 h and then left untreated or treated with insulin for an additional 2 h. The cells were collected, permeabilized, incubated with SREBP1 or preimmune rabbit (IgG) antibodies, followed by the protein A/G-MNase fusion protein. Endogenous SREBP1 and its bound DNA was subsequently isolated using protein A magnetic beads and used for PCR with primers specific for the E-box in the human cyclin D1 promoter. The same primers were also used for PCR of the same region from genomic DNA isolated from the same cells (Input). The PCR products were separated on PAGE gels and stained with SYBR Safe (upper panel). The intensity of the signals in the samples and the input were quantified (lower panel). (B) mRNA was isolated from the cells in (A) and used to determine the expression of cyclin D1 by real-time qPCR, using GAPDH as a reference. (C) MCF7 cells were transfected with the CCND1-luc promoter–reporter gene, either wild-type (WT) or the ΔE-box, serum starved for 24 h followed by an additional 2-h incubation in the absence or presence of insulin, after which the cells were lysed, and luciferase activity was measured. Significance was determined by paired t-tests (A–C). p-values lower than 0.05 were considered statistically significant. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p< 0.0001. NS, not significant."
      }
    ]
  },
  {
    "id": "PMC9451027_multi_2",
    "image": [
      "images/PMC9451027-f6.png",
      "images/PMC9451027-f7.png",
      "images/PMC9451027-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"The SREBP-dependent regulation of cyclin D1 coordinates cell proliferation and lipid synthesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. The SREBP pathway regulates the proliferation of MCF7 cells. (A) MCF7 cells were transduced with lentiviruses expressing non-targeted shRNA (C) or shRNA targeting SREBP1 (S1) or SREBP2 (S2). After selection, an equal number of cells were seeded in 12-well plates and cells counted over a 72-h period. (B) MCF7 cells were transduced with lentiviruses expressing non-targeted shRNA (C) or shRNA targeting SREBP1 (S1) or SREBP2 (S2) and metabolically labeled with BrdU, and the incorporation of BrdU was determined by an ELISA assay. (C) MCF7 cells were transduced with lentiviruses expressing non-targeted shRNA (C) or shRNA targeting SREBP1 (S1) or SREBP2 (S2). The cells were collected, fixed, and stained with propidium iodine, and the DNA content was analyzed by FACS. (D) The same cells as in (C) were lysed and the levels of cyclin D1, Rb, and the precursor form of SREBP1 (pSREBP1), and the phosphorylation of Rb on serine 780 (pRb-S780) were analyzed by Western blotting. β-Actin was used as loading control. (E) MCF7 cells were transduced with lentiviruses expressing non-targeted shRNA (C) or shRNA targeting SREBP1 (S1). After selection, the cells were serum-starved for 24 h, followed by an additional 20-h incubation in the absence or presence of serum. The cells were collected and processed as in (C). (F) The same cells as in (E) were lysed and the levels of cyclin D1, Rb and the precursor form of SREBP1 (pSREBP1), and the phosphorylation of Rb on serine 780 (pRb-S780) were analyzed by Western blotting. β-Actin was used as loading control. Significance was determined by paired t-tests (E) or one-way ANOVA with Tukey’s multiple comparisons adjustment (A–C). p-values lower than 0.05 were considered statistically significant. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001. NS, not significant.\n\nFigure 7: Figure 7. The SREBP1-dependent induction of cyclin D1 promotes the phosphorylation of Rb. (A) HepG2 cells were transduced with lentiviruses expressing GFP or nuclear SREBP1a (nS1a), and 48 h following transduction, the cells were treated with or without the cdk4/6 inhibitor palbociclib (10 μM) for 6 h. The levels of cyclin D1, Rb, and the nuclear form of SREBP1 (nSREBP1), and the phosphorylation of Rb on serine 780 (pRb-S780) were analyzed by Western blotting. β-Actin was used as loading control. (B) HepG2 cells were transduced with lentiviruses expressing GFP or nuclear SREBP1a (nS1a) together with non-targeted (C) or cyclin D1 (CCND1) shRNA. Forty-eight hours after transduction, the levels of cyclin D1, Rb, CDK4, and nuclear SREBP1 (nSREBP1), and the phosphorylation of Rb on serine 780 (pRb-S780) were analyzed by Western blotting. β-Actin was used as loading control. (C) HepG2 cells were transduced with lentiviruses expressing GFP or cyclin D1 together with non-targeted (C) or SREBP1 (S1) shRNA. Forty-eight hours after transduction, the levels of cyclin D1, Rb, CDK4 and the precursor form of SREBP1 (pSREBP1), and the phosphorylation of Rb on serine 780 (pRb-S780) were analyzed by Western blotting. β-Actin was used as loading control. (D) The same cells as in (C) were also fixed and stained with propidium iodine, and the DNA content was analyzed by FACS. Significance was determined by one-way ANOVA with Tukey’s multiple comparisons adjustment (D). p-values lower than 0.05 were considered statistically significant. *p < 0.05, **p < 0.01, ***p < 0.001, and ****p < 0.0001.\n\nFigure 8: Figure 8. The SREBP1-dependent expression of cyclin D1 links insulin signaling to Rb phosphorylation. (A) MCF7 cells were transduced with lentiviruses expressing non-targeted (C) or SREBP1 (S1) shRNA. After selection, the cells were serum-starved for 24 h, followed by an additional 2-h incubation in the absence or presence of insulin. The levels of cyclin D1, Rb, and nuclear (nSREBP1) and precursor SREBP1 (pSREBP1) and CDK4, and the phosphorylation of Rb on serine 780 (pRb-S780) were analyzed by Western blotting. (B) MCF7 cells were transduced with lentiviruses expressing non-targeted (C) or cyclin D1 (CCND1) shRNA and treated and processed as in (A). (C) MCF7 cells were serum-starved for 24 h followed by a 2-h stimulation with insulin in the absence or presence of palbociclib (10 μM). The cells were processed and analyzed as in (A). (D) Model. We propose that cells respond to growth-promoting signals, such as insulin or EGF, by activating SREBP1. The active SREBP1 molecules bind to an E-box in the promoter of cyclin D1, thereby enhancing the expression of the corresponding gene. The enhanced expression of cyclin D1 promotes the phosphorylation of Rb by activating cdk4/6, thereby promoting G1 progression. At the same time, SREBP1, especially SREBP1a, has the capacity to enhance the expression of lipogenic genes to support cell growth. Thus, the SREBP-dependent regulation of cyclin D1 could help coordinate cell cycle progression with increased lipid synthesis to support cell growth. This may be especially important in tumor cells, which express the most potent member of the SREBP family of transcription factors, SREBP1a."
      }
    ]
  },
  {
    "id": "PMC9485218_multi",
    "image": [
      "images/PMC9485218-f1.png",
      "images/PMC9485218-f2.png",
      "images/PMC9485218-f3.png",
      "images/PMC9485218-f4.png",
      "images/PMC9485218-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Chaperone-assisted E3 ligase CHIP: A double agent in cancer\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Ubiquitin proteasome system (UPS). ATP mediated activation of free ubiquitin molecules occurs via binding of free ubiquitin to the ubiquitin binding enzyme (E1's) through a thioester linkage, subsequently the activated ubiquitin molecule gets transferred to ubiquitin conjugating enzymes (E2's). This Ub-E2's subsequently forms a complex with abnormal protein and with a specific E3 ubiquitin ligase enzyme which is responsible for transferring the ubiquitin moiety to the amino acid residue lysine present within the abnormal client protein that leads to poly-ubiquitination and 26S proteasome mediated degradation. Extensive role of E3 ubiquitin ligases as an E4 enzyme discovered recently as a new component of UPS is responsible for the elongation of ubiquitination chain. Finally, the ubiquitin molecules are recycled and again gets involved in next cycles of UPS.\n\nFigure 2: Figure 2. Architectural alignment and subcellular localization of CHIP. (A) The schematic diagram represents the architectural alignment of all the three domains (TPR, Ubox and Charged) of CHIP. TPR (tetratricopeptide repeats) domain is present at the N-terminus of CHIP, while Ubox domain is at C-terminus. The charged domain is localized in between TPR and Ubox domains of CHIP. (B) The diagram represents the sub-cellular localization of CHIP in endoplasmic reticulum (ER), mitochondria, cytoplasm, nucleus and golgi bodies.\n\nFigure 3: Figure 3. Molecular chaperones (HSP70/HSC70 and HSP90) dependent, independent and direct mechanisms of CHIP mediated degradation of client proteins. CHIP mediated degradation of client proteins through inhibition of either (A) HSP70/HSC70 mediated refolding; (B) HSP90 mediated refolding or, (C) Chaperones independent route for degradation of client proteins. Arrows indicate either positive (solid) or negative (T shaped) regulation.\n\nFigure 4: Figure 4. Timeline for client proteins of CHIP. The figure depict the timeline of all documented client proteins of CHIP identified till December 2020.\n\nFigure 5: Figure 5. Pie-in-pie chart of CHIP as a double agent in the context to cancer. CHIP client proteins classified according to the hallmarks of cancer and its dual role as a tumor suppressor (left hand sided pie chart) and as an oncogene (right hand sided pie chart) explained."
      }
    ]
  },
  {
    "id": "PMC9497081_multi",
    "image": [
      "images/PMC9497081-f1.png",
      "images/PMC9497081-f2.png",
      "images/PMC9497081-f3.png",
      "images/PMC9497081-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Inhibition of BRD4 Promotes Pexophagy by Increasing ROS and ATM Activation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Inhibition of BRD4 promotes pexophagy in RPE cells. (A) RPE/mRFP-EGFP-SKL cells were treated with inhibitors of BRD4 [molibresib (10 µM), I-BET151 (10 µM), dBET1 (10 µM)] for 72 h. The cells were fixed for imaging under a fluorescence microscope. The numbers of cell with EGFP(+)- and mRFP(+)-labeled autophagosomes or EGFP(-) and mRFP(+)-labeled autolysosomes, which displayed the peroxisomal reporter mRFP-EGFP-SKL due to lysosomal delivery, were counted and are presented as percentages; (B) HeLa cells stably expressing pmTurquiose2-Peroxi, pmTurquiose2-Mito, pmTurquiose2-ER, or pmTurquiose2-Golgi were treated with molibresib (10 µM) for 72 h and stained with DRAQ (red). Cellular organelles were imaged by confocal microscopy. The scale bar indicates 20 µm; (C,D) RPE/mRFP-EGFP-SKL cells were transiently transfected with siRNA targeting BRD4 (siBRD4), and then, EGFP and mRFP fluorescence was imaged and quantified (C); reduced expression of BRD4 by siRNA was verified by Western blotting (D). (Data indicate means ± S.E.M. *** p < 0.001).\n\nFigure 2: Figure 2. Loss of ATG7 blocks molibresib-induced pexophagy in HeLa cells. (A,B) HeLa cells pre-treated with molibresib (10 µM) for 48 h were further incubated with or without bafilomycin A1 (Baf. A1, 25 nM) for 6 h. Then, the cells were harvested to analyze by Western blotting with indicated antibodies (A); the cells were stained with anti-ABCD antibody (red) and Hoechst 33,342 (blue). The number of peroxisomes per cell was calculated by assessing > 100 cells (B); (C) wild-type and ATG7-knockout HeLa cells were treated with molibresib (10 µM) for 48 h. The cells were stained with anti-ABCD3 antibody (red) and Hoechst 33,342 dye (blue). The number of peroxisomes per cell was calculated by assessing approximately 100 cells; (D) wild-type and ATG7-knockout HeLa cells were treated with molibresib (10 µM) for 48 h, and then harvested for analysis by Western blotting with the indicated antibodies; (E) HeLa cells were transiently transfected with scrambled siRNA (Sc) or validated siRNA targeting for NBR1 (siNBR1) or p62 (sip62). After 24 h, the cells were further treated with molibresib (10 µM) for 48 h and stained with anti-ABCD3 antibody (red) and Hoechst 33,342 dye (blue). The number of peroxisomes per cell was calculated by assessing approximately 100 cells; the scale bar indicates 20 µm. (Data indicate means ± S.E.M. * p < 0.05, *** p < 0.001, ns: not significant).\n\nFigure 3: Figure 3. Inhibition of BRD4 promotes pexophagy by increasing the ROS levels in HeLa cells. (A) HeLa cells were treated with molibresib (10 µM) with or without NAC (1 mM) for 48 h. Then, the cells were incubated with fluorescent DCFH-DA dye (10 µM, 10 min). The cells were imaged (scale bar 50 µm), and DCFH-DA fluorescence intensity was measured using image processing software ImageJ; (B) HeLa/pexo-HyPer cells were treated with molibresib (10 µM) with or without NAC (1 mM) for 48 h. The level of peroxisomal H2O2 was imaged (scale bar, 50 μm) and measured using the fluorescence intensity of HyPer-PTS1; (C) HeLa cells were treated with molibresib (10 µM) with or without NAC (1 mM) for 48 h. Then, the cells were immunostained with anti-ABCD3 antibody (red) and Hoechst 33,342 dye (blue) to count the number of peroxisomes in cells. Representative cell images are presented (C, scale bar 20 µm). The experiments were repeated at least three times. (Data indicate means ± S.E.M. ** p < 0.01, *** p < 0.001, ns: not significant).\n\nFigure 4: Figure 4. Inhibition of BRD4 activates ATM to promote pexophagy in HeLa cells. (A) HeLa cells were treated with molibresib (10 µM) with or without NAC (1 mM) for 48 h. The cells were harvested and analyzed by Western blotting with the indicated antibodies; (B) HeLa cells were treated with molibresib (10 µM) with or without KU55933 (10 µM) for 48 h. Then, the cells were immunostained with anti-ABCD3 antibody (red) and Hoechst 33,342 dye (blue) to count the peroxisomes. Representative cell images are presented (scale bar 20 µm). The experiments were repeated at least three times. (Data indicate means ± S.E.M. *** p < 0.001, ns: not significant)."
      }
    ]
  },
  {
    "id": "PMC9500405_multi",
    "image": [
      "images/PMC9500405-f1.png",
      "images/PMC9500405-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Control of mitochondrial dynamics and apoptotic pathways by peroxisomes\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Peroxisomes are important for regulation of mitochondrial morphology. Mitochondrial fission-fusion dynamics in cells treated with 4-PBA (left), which induces peroxisome proliferation, cells under normal conditions (middle), and cells lacking peroxisomes due to Pex3 knockout (right). When peroxisome proliferation is induced pharmacologically, mitochondria acquire an elongated structure, whereas peroxisome deficiency leads to a more fragmented mitochondrial morphology. Note that in general, ZS only lacks peroxisomal matrix proteins but retains the membrane structures of peroxisomes. The figure is created with BioRender.com.\n\nFigure 2: Figure 2. The absence of peroxisomes results in excess mitochondrial fragmentation following caspase activation in mammalian cells. (A) In normal conditions, cytosolic Drp1 is recruited to both peroxisomes and mitochondria. (B) When peroxisomes are acutely depleted by Pex3 KO, Drp1 is recruited to mitochondria more than WT cells. Translocated Drp1 will induce mitochondrial fragmentation along with abnormal cristae structures. This fragmentation induces the release of cytochrome c to the cytosol, resulting in caspase activation. Mito: mitochondrion, Pero: peroxisome, C: cytochrome c. The figure is created with BioRender.com."
      }
    ]
  },
  {
    "id": "PMC9520416_multi",
    "image": [
      "images/PMC9520416-f1.png",
      "images/PMC9520416-f2.png",
      "images/PMC9520416-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Role of MRI in X-linked adrenoleukodystrophy—A case report\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) T1-weighted MRI image in axial plane shows symmetrical low signal intensities in subcortical and deep white matter of bilateral parieto-occipital lobes, splenium of corpus callosum, posterior limbs of internal capsule and posterior aspect of external capsule. (B) T2-weighted MRI image in axial plane shows symmetrical areas of high signal intensities corresponding to low signal intensity areas in T1-weighted images. (C) T2 FLAIR image does not show suppression of the altered signal intensity areas in T1- and T2-weighted images. (D) GRE images do not show blooming foci in altered signal intensity areas.\n\nFigure 2: Figure 2. (A & B) T1-weighted MRI image in sagittal plane shows low signal intensity in the splenium of corpus callosum with corresponding high signal intensity in T2-weighted image. (C & D) Postcontrast MRI images in axial plane (C) and sagittal plane (D) show symmetrical serpiginous enhancement in the periphery of the lesion predominantly in the anterior aspect which represents the advancing edge of demyelination which is suggestive of progression of the lesion.\n\nFigure 3: Figure 3. MRS study from the enhancing edge of the lesion shows choline peak with increased choline creatinine ratio. Similarly, there is decreased NAA in the central part of the lesion and decreased NAA with increased lipid/lactate peak in the peripheral region."
      }
    ]
  },
  {
    "id": "PMC9524157_multi",
    "image": [
      "images/PMC9524157-f1.png",
      "images/PMC9524157-f2.png",
      "images/PMC9524157-f3.png",
      "images/PMC9524157-f4.png",
      "images/PMC9524157-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Dysfunctional peroxisomal lipid metabolisms and their ocular manifestations\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Schematics of retinal structure. The neural retina is supplied by retinal and choroidal vasculature. Photoreceptors (rods and cones) are supported by RPE and Müller glia cells. The figure was generated using Biorender (license # LX24BJEUXV).\n\nFigure 2: Figure 2. Summary of peroxisomal functions in humans. Enzymes involved in the catabolic and anabolic pathways in white boxes. Red box represents ROS/RNS producing enzymes. Green box represents anti-oxidation enzymes in redox homeostasis. 1P5CDH, Δ1-pyrroline-5-carboxylate dehydrogenase; ABCD, ATP-binding cassette sub-family D; ACAA, 3-oxoacyl thiolase; ACOX, acyl-CoA oxidase; ACSL, long chain acyl-CoA synthetase; ACSVL, very long chain acyl-CoA synthetase; ADH, alcohol dehydrogenase; ADHAPR, acyl/alkyl DHAP reductase; AGPS, alkyl-glycerone phosphate synthase; AGT, alanine:glyoxylate aminotransferase; ALA, α-linolenic acid; ALDH, aldehyde dehydrogenase; AMACR, α-methylacyl-CoA racemase; AspAT, aspartate aminotransferase; BAAT, bile acid-CoA:amino acid N-acyltransferase; BCFA, branched chain fatty acids; BG, bubblegum; CAT, catalase; DAAO, D-amino acid oxidase; DASPO, D-aspartate oxidase; DHA, docosahexaenoic acid; DHCA, 3α,7α-dihydroxy-5β-cholestanoic acid; DPAn-3, n-3 docosapentaenoic acid; ELOVL, fatty acid elongase; EPA, eicosapentaenoic acid; EPHX2, epoxide hydrolase 2; FADS, fatty acid desaturase; FALDH, fatty aldehyde dehydrogenase; FAR, fatty acyl-CoA reductase; FATP, fatty acid transport protein; GNPAT, glycerone-phosphate O-acyltransferase; GO, glycolate oxidase; GSH, glutathione; GSTK, glutathione transferase kappa; HACL, 2-hydroxyacyl-CoA lyase; HOGA, 4-hydroxy-2-oxoglutarate aldolase; HPOX, hydroxyproline oxidase; LCFA, long chain fatty acids; MFE, multifuctional enzyme; MGST, microsomal glutathione S-transferase; NOS2, inducible nitric oxide synthase; PAP, phosphatidic acid phosphatase; PCS, phytenoyl-CoA synthetase; PHYH, phytanoyl-CoA 2-hydroxylase; PRDX5, peroxiredoxin 5; PXMP2, peroxisomal membrane protein 2; SELENOI, selenoprotein 1 (ethanolamine phosphotransferase 1); SCPx, SCP-2/3-ketoacyl-CoA thiolase; SOD1, superoxide dismutase; TER, trans-2-enoyl-CoA reductase; THA, tetracosahexaenoic acid; THCA, 3α,7α, 12 α-trihydroxy-5β-cholestanoic acid; TMEM189, plasmanylethanolamine desaturase; VLCFA, very long chain fatty acids; VLCS, very long chain acyl-CoA synthetase; XO, xanthine oxidase. The Figure was partly generated using Servier Medical Art, provided by Servier, licensed under a Creative Commons Attribution 3.0 unported license.\n\nFigure 3: Figure 3. Biochemical pathways of peroxisomal lipid synthesis and degradation. Blue box represents enzymes with published pathogenic variants resulting in ocular manifestations in humans. ABCD, ATP-binding cassette sub-family D; ACAA, 3-oxoacyl thiolase; ACOX, acyl-CoA oxidase; ADHAPR, acyl/alkyl DHAP reductase; AGPS, alkyl-glycerone phosphate synthase; ALA, α-linolenic acid; BG, bubblegum; DHA, docosahexaenoic acid; DHAP, dihydroxyacetone phosphate; DPAn-3, n-3 docosapentaenoic acid; ELOVL, fatty acid elongase; EPA, eicosapentaenoic acid; EtnGpl, ethanolamine glycerophospholipids; FADS, fatty acid desaturase; FAR, fatty acyl-CoA reductase; FATP, fatty acid transport protein; G3P, glycerol-3-phosphate; GNPAT, glycerone-phosphate O-acyltransferase; LCFA, long chain fatty acids; MFE, multifuctional enzyme; PAP, phosphatidic acid phosphatase; PlsEtn, ethanolamine plasmalogens; PXMP2, peroxisomal membrane protein 2; SELENOI, selenoprotein 1 (ethanolamine phosphotransferase 1); THA, tetracosahexaenoic acid; TMEM189, plasmanylethanolamine desaturase; VLCFA, very long chain fatty acids; VLCS, very long chain acyl-CoA synthetase. The figure was partly generated using Servier Medical Art.\n\nFigure 4: Figure 4. Biochemical pathways of peroxisomal branched chain fatty acid, dicarboxylic acid, and bile acid degradations. Blue box represents enzymes with published pathogenic variants resulting in ocular manifestations in humans. ABCD, ATP-binding cassette sub-family D; ACAA, 3-oxoacyl thiolase; ACOX, acyl-CoA oxidase; ADH, alcohol dehydrogenase; ALDH, aldehyde dehydrogenase; AMACR, α-methylacyl-CoA racemase; AspAT, aspartate aminotransferase; BAAT, bile acid-CoA:amino acid N-acyltransferase; BCFA, branched chain fatty acids; CA, cholic acid; CDCA, chenodeoxycholic acid; DHCA, 3α,7α-dihydroxy-5β-cholestanoic acid; FALDH, fatty aldehyde dehydrogenase; HACL, 2-hydroxyacyl-CoA lyase; MFE, multifuctional enzyme; PCS, phytenoyl-CoA synthetase; PHYH, phytanoyl-CoA 2-hydroxylase; SCPx, SCP-2/3-ketoacyl-CoA thiolase; TER, trans-2-enoyl-CoA reductase; THCA, 3α,7α, 12 α-trihydroxy-5β-cholestanoic acid. The figure was partly generated using Servier Medical Art.\n\nFigure 5: Figure 5. Biochemical pathways of glyoxylate, amino acids, and reactive oxygen/nitrogen species degradations. Blue box represents enzymes with published pathogenic variants resulting in ocular manifestations in humans. 1P5CDH, Δ1-pyrroline-5-carboxylate dehydrogenase; AGT, alanine:glyoxylate aminotransferase; AspAT, aspartate aminotransferase; CAT, catalase; DAAO, D-amino acid oxidase; DASPO, D-aspartate oxidase; EPHX2, epoxide hydrolase 2; GO, glycolate oxidase; GRHPR, glyoxylate and hydroxypyruvate reductase; GSH, glutathione; GSTK, glutathione transferase kappa; HOGA, 4-hydroxy-2-oxoglutarate aldolase; HPOX, hydroxyproline oxidase; LDH, lactate dehydrogenase; MGST, microsomal glutathione S-transferase; PRDX5, peroxiredoxin 5; SOD1, superoxide dismutase. The figure was partly generated using Servier Medical Art."
      }
    ]
  },
  {
    "id": "PMC9537587_multi",
    "image": [
      "images/PMC9537587-f1.png",
      "images/PMC9537587-f2.png",
      "images/PMC9537587-f3.png",
      "images/PMC9537587-f4.png",
      "images/PMC9537587-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"YgiM may act as a trigger in the sepsis caused by Klebsiella pneumoniae through the membrane-associated ceRNA network\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Verification of ygiM deletion mutant by PCR and sequencing. (A) The pSGKP plasmid contains YgiM protein N20, and the target band is 220bp after PCR verification. (B) Sanger sequencing indicated that the pSGKP plasmid containing YgiM protein N20 was successfully constructed (red bases represent N20). (C) PCR confirmed that the ygiM mutant was constructed successfully. (D) Sanger sequencing verified that ygiM was successfully knocked out. (Red bases represent upstream of ygiM and blue bases represent downstream of ygiM).\n\nFigure 2: Figure 2. Growth curve and bacterial colony number of K. pneumoniae wild-type strain and ygiM mutant strains. (A) Comparison the growth curves of wild-type and ygiM mutant strains. The experiments were independently repeated three times. (B) Comparison the CFU/ml of wild-type and ygiM mutant strains. The experiments were independently repeated three times.\n\nFigure 3: Figure 3. Determination of phagocytosis resistance of the wild type and the ygiM gene mutant strains. (A) THP-1 cells before induction (round, clear nuclei). (B) THP-1 cells are induced into macrophages by PMA (with pseudopodia, indistinct nuclei). (C) Fluorescence images of macrophages phagocytosing K. pneumoniae. The arrow indicates fluorescence labelled intracellular K. pneumoniae. (D) Plate to count macrophage phagocytosis. Data is displayed as intracellular bacterial counts of macrophages from three independent experiments (**: p < 0.01).\n\nFigure 4: Figure 4. Survival curves and pathological morphology of mice. (A) Survival curves of mice in the tail vein infection model. Ten mice each of PBS, WT and ΔygiM were injected with 106 CFU through the tail vein, respectively. The 5 days survival rate of mice was determined. (B) Histopathology of mouse lung and liver after infection with PBS (negative control), WT and ΔygiM. 48 h after infection, the lungs and livers of different groups of mice were dissected and stained. These numbers represent at least three sections from three mice that exhibited similar pathology in their tissues. The arrows indicate the obvious pathological differences.\n\nFigure 5: Figure 5. Characteristics and functional analysis of differentially expressed genes (DEGs). (A) Differentially expressed transcription factors associated with the identified DEmiRNAs. HOXD8, EGR1, NKX6-1, LHX3, HOXB4, ONECUT1, SP1, HOXA5, FOXJ2 and MEF2A were the most significant molecules in sepsis. (B) GO enrichment analysis of the DEmRNAs in biological process (BP), cellular component (CC) and molecular function (MF) subgroups. (C) KEGG enrichment analysis of DEmRNAs."
      }
    ]
  },
  {
    "id": "PMC9537587_multi_2",
    "image": [
      "images/PMC9537587-f6.png",
      "images/PMC9537587-f7.png",
      "images/PMC9537587-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"YgiM may act as a trigger in the sepsis caused by Klebsiella pneumoniae through the membrane-associated ceRNA network\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Construction of the membrane-related interaction network. (A) The competitive endogenous RNA (ceRNA) network of DEGs in the initiation of sepsis. In total, there were 25 miRNAs and 50 mRNAs in the ceRNA network. (B) The target genes of the identified DEmRNAs were ranked in the PPI network. The depth of red indicates the importance of genes in the network. (C) The most closely-clustered subnetwork was composed of 22 nodes and 178 edges. (D) The clustered subnetwork identified by the MCODE plug-in in Cytoscape had 8 nodes and 15 edges. (E) The membrane-related interaction network in the initiation of sepsis. Based on the results of the prediction of DEmiRNAs and PPI network, we constructed a autophagy interaction network including 15 miRNAs and seven mRNAs. (F) In the membrane-related interaction network, LTF, VNN1, and C3AR1 were the most important hub gene among the identified genes. The depth of red indicates the importance of genes in the network among mRNAs.\n\nFigure 7: Figure 7. The relative expression of mRNA in K. pneumoniae wild-type, ΔygiM and C-ygiM strains. (A) Positive targets of mRNA: VNN1, CEACAM8, PGLYRP1 were considered to be statistically significant in the infection of K. pneumoniae control, wild type and ΔygiM groups (*: p < 0.05, **: p < 0.01, ***: p < 0.001). (B) Negative target of mRNA: C3AR1, HLA-DQA1, ANXA3, LTF were considered to be statistically insignificant in the infection of K. pneumoniae control, wild type and ΔygiM groups (*: p < 0.05).\n\nFigure 8: Figure 8. The relative expression of miRNA in K. pneumoniae wild-type, ΔygiM and C-ygiM strains. (A) Positive targets of miRNA: hsa-miR-7108-5p, hsa-miR-6780a-5p, hsa-miR-6756-5p, hsa-miR-4433b-3p, hsa-miR-3652, hsa-miR-342-3p and hsa-miR-32-5p were considered to be statistically significant in the infection of K. pneumoniae control, wild type and ΔygiM groups (*: p < 0.05, **: p < 0.01, ***, p < 0.001: ****: p < 0.0001). (B) Negative target of micRNA: hsa-miR-501-3p, hsa-miR-17-3p, hsa-miR-3125 and hsa-miR-4318 were considered to be statistically insignificant in the infection of K. pneumoniae control, wild type and ΔygiM groups (*: p < 0.05, **: p < 0.01, ***: p < 0.001)."
      }
    ]
  },
  {
    "id": "PMC9538651_multi",
    "image": [
      "images/PMC9538651-f1.png",
      "images/PMC9538651-f2.png",
      "images/PMC9538651-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Case report: Thirty-year progression of an EMPF1 encephalopathy due to defective mitochondrial and peroxisomal fission caused by a novel de novo heterozygous DNM1L variant\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. DNM1L/DRP1 immunostaining shows the loss of DNM1L normal forms in patient fibroblasts. (A1) Comparison of the GTPase domain structure of nucleotide-free, wild-type (orange, pdb code 4H1U) and mutated THR59ASN DNM1L (gray) in ribbon and Gaussian volume representation, using RCSB pairwise structure alignment tool. The mutation site is indicated by a red circle. Modeling indicates a disorganization of the switch 1 in which the mutation is located, but also in the unique 80-loop, αE1G helix and the loop connecting αE1G and the β2A sheet (indicated by black arrow). (A2) Close-up view of the switch1 in the nucleotide-free structure of the WT (orange) and mutated (gray) DNM1L. ASN59 is underlined in green. Water molecules are represented in yellow. The catalytic water molecule connecting switch I (THR59) with switch II (GLY149) by hydrogen bonds is circled in red. This interaction is lost with the amino acid switch THR59ASN. Amino acids interacting with THR59 or ASN59 are indicated. Detailed view of amino acid interactions in nucleotide-free wild-type (A3) and mutated (A4) protein structures. Hydrophobic interaction is in green, hydrogen bonds in red, and VDW in blue. Analysis was performed using Dynamut2. (B) OPA1 and DNM1L/DRP1 protein quantification and α-tubulin (TUB) as loading control in control (CTL) and patient (P.) fibroblasts. Control and DRP1 knock out MEFs: Mouse embryonic Fibroblasts models. On the right, overlay yellow staining of 2 DNM1L/DRP1 antibodies Ab1 and 2 indicates specific staining. ≪ 12 ≫ and ≪ 14 ≫: controls were charged at 1/2 and 14 to control the linearity range of DNM1L signal detection.\n\nFigure 2: Figure 2. Patient fibroblasts show highly connected mitochondrial network and elongation of peroxisome compare to control. (A) Representative fluorescent images of mitochondrial network structure (in purple) in control (CTL) and patient (P.) fibroblasts. Mitochondrial volume was assessed using the MitoTracker Green fluorescent signal which was analyzed using Imaris software. The color code highlights the different lengths of the mitochondrial tubules with short isolated mitochondria in violet and connected network in red. To present the changes in mitochondrial morphology in patient's cells, types of mitochondria were classified into six groups according to mitochondrial volume, for example, red color represents mitochondria > 20 μm3. Oligomycin 4 μg/ml coupled to antimycin 2 μg/ml (O/A) treatment leads to mitochondrial fission within 4 h in CTL cells. 6 h nocodazole (Noc), 10 μM disrupts microtubules. (B) Immunostaining against mitochondrial Mff DRP1 receptor. Representative TIRF image of mitochondria (left, in purple) shows the hyper-connectivity of the network. Single-molecule localization microscopy dSTORM was used to analyze mitochondrial MFF distribution. The white dots are the fiducial signals used to control drift during acquisition. Scale bar: 2 μm. (C) Immunostaining against peroxisomal PMP70 protein. Peroxisome (PO) volume was assessed using fluorescent signal by Imaris software and color-coded. To present the changes in peroxisome morphology in patient's cells, types of Peroxisomes were classified into five groups according to peroxisome volume, for example, red color represents peroxisomes > 20 μm3. Scale bar = 10 μm; Scale bar in details 1 μm.\n\nFigure 3: Figure 3. Electron microscopy imaging of the patient fibroblasts and muscle. (A) Skin fibroblasts: M, mitochondria; PO, peroxisomes; N, nucleus; AV, autophagic vacuole. (B) Muscle biopsy: a: concentric laminated bodies; b: mitochondrial nano-tunnel; c multiple degenerative myelinoid intramitochondrial foci."
      }
    ]
  },
  {
    "id": "PMC9542479_multi",
    "image": [
      "images/PMC9542479-f1.png",
      "images/PMC9542479-f2.png",
      "images/PMC9542479-f3.png",
      "images/PMC9542479-f4.png",
      "images/PMC9542479-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Targeted Brain Delivery of Dendrimer-4-Phenylbutyrate Ameliorates Neurological Deficits in a Long-Term ABCD1-Deficient Mouse Model of X-Linked Adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Synthesis and characterization of D-4PBA. A Schematic representation of step-wise synthesis of D-4PBA conjugate. B 1H NMR characterization of D-4PBA representing characteristic protons from dendrimer and 4-PBA. C HPLC profile of D-4PBA conjugate demonstrating a purity > 98%. D In vitro drug release profile of conjugate to mimic intracellular and extracellular pH\n\nFigure 2: Figure 2. Biodistribution of Cy5-labeled dendrimer (D-Cy5; red) delivered to 8-month-old WT and KO male mice. Ventral horn uptake is shown in both neurons (Smi32, green; arrow heads) and microglial cells (Iba1, white; arrows). D-Cy5 (50 mg/kg; i.p.) uptake is shown after 24 h. Scale bar represents 20 μm\n\nFigure 3: Figure 3. D-4PBA dose response. D-4PBA (0 n = 3, 50 n = 5, 100 n = 5, or 200 mg/kg n = 3) was delivered weekly to Abcd1 KO mice for 8 weeks. A Analysis of spinal cord VLCFA LPC reveals a dose-dependent decrease in C26:0 after 8 weeks and B no significant change to body weight during the treatment period. For all, error bars indicate standard error of the mean\n\nFigure 4: Figure 4. Study 1 behavior and histology. In parallel to WT and Abcd1− vehicle-treated mice, Abcd1 KO mice were treated with 50 mg/kg D-4PBA biweekly starting at 7 months of age. A Latency (s) to fall from the Rotor Rod was measured monthly. After nearly 9 months of dosing, D-4PBA was increased to 100 mg/kg per month. Mice were dosed for 12 full months. B Representative images of Smi32-stained neurons within the ventral horn of spinal cord sections (scale bar represents 50 μm). C The number of Smi32.+ neurons within the spinal cord gray matter were used as an index of overall neuronal and axonal survival. Although not significant, D-4PBA-treated mice showed an increase in the number of neurons detected. D Quantification of ER stress marker BiP within spinal cord gray matter. E C26:0 LPC was elevated as expected in Abcd1 KO vehicle-treated mice (p = 0.0030) and treatment with D-4PBA significantly reduced VLCFA accumulation within the spinal cord (p = 0.0245). *p ≤ 0.05. At study’s end, WT n = 7, Abcd1 KO n = 6, and Abcd1 D-4PBA n = 6\n\nFigure 5: Figure 5. Study 2 behavior and histology. In parallel to WT and Abcd1− vehicle-treated mice, Abcd1 KO mice were treated with 100 mg/kg D-4PBA weekly starting at 1 year of age. A Latency (s) to fall from the Rotor Rod was measured monthly and mice showed a marked improvement in latency shortly after treatment initiation. B Representative images of Smi32-stained neurons within the ventral horn of the spinal cord (scale bar represents 50 μm). C Smi32.+ neurons were decreased within Abcd1 KO mice with no significant effect of D-4PBA treatment. D Quantification of ER stress marker BiP within spinal cord gray matter. E C26:0 LPC was again elevated as expected in Abcd1 KO vehicle-treated mice (p = 0.0002); however, in this study, treatment with D-4PBA had no effect. At study’s end, WT n = 9, Abcd1 KO n = 7, and Abcd1 D-4PBA n = 7"
      }
    ]
  },
  {
    "id": "PMC9545274_multi",
    "image": [
      "images/PMC9545274-f1.png",
      "images/PMC9545274-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"A syndrome of severe intellectual disability, hypotonia, failure to thrive, dysmorphism, and thinning of corpus callosum maps to chromosome 7q21.13‐q21.3\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigree and linkage analysis. (A) The studied kindred. As can be seen, there are at least two families involved in the analysis, that is, descendants of I:1, I:2, and I:3, I:4. These families are related as individual IV:1 is heterozygous for the 7q21.13‐q21.3 locus. Genome‐wide linkage analysis included 19 family members, denoted by asterisks. WES was performed for three patients, denoted by arrows. (B) Homozygosity scores. Genome‐wide SNP distributions were collected for 19 family members. The distribution of homozygous regions was determined using HomozygosityMapper (http://www.homozygositymapper.org/). Blue arrow indicates the single homozygous locus on chromosome 7q21.13‐q21.3 between rs6952664 and rs13234589, shared by affected individuals. [Colour figure can be viewed at wileyonlinelibrary.com]\n\nFigure 2: Figure 2. Clinical characterization. (A–D) Patients V:5, V:6, IV:4, and V:1, respectively. Craniofacial dysmorphism was apparent with normal to borderline small head circumference, characteristic triangular face with prominent forehead, slightly posterior‐rotated low‐set ears, and small chin. (E–G) Patients V:5, V:6, and V:1, respectively: over‐riding toes, with clinodactyly or syndactyly. (H–K) Brain MRI of patients IV:4, V:4, V:5, and V:9, respectively. (L) Brain MRI of patient V:6 in‐utero. All affected individuals showed thinning of corpus callosum with paucity of white matter. (M) Metopic stenosis of patient V:9. [Colour figure can be viewed at wileyonlinelibrary.com]"
      }
    ]
  },
  {
    "id": "PMC9545763_multi",
    "image": [
      "images/PMC9545763-f1.png",
      "images/PMC9545763-f2.png",
      "images/PMC9545763-f3.png",
      "images/PMC9545763-f4.png",
      "images/PMC9545763-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Therapeutic potential of deuterium‐stabilized (R)‐pioglitazone—PXL065—for X‐linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PXL065 and Pioglitazone suppress very long chain fatty acids (VLCFA) levels in fibroblasts derived from two adrenoleukodystrophy (ALD)—C‐ALD and AMN—patients. (A) Dose–response effect of PXL065, pioglitazone on C26:0 levels measured by mass spectrometry in AMN fibroblasts following incubation with compounds at 0, 0.1, 0.5, 1, 2, 3.5, and 5 μM for 7 days. IC50s were calculated using nonlinear regression analysis. Results are mean ± SEM, n = 5 replicates. (B) Effect of PXL065 and pioglitazone on VLCFA levels measured by mass spectrometry in AMN and C‐ALD fibroblasts, following incubation at 10 μM for 7 days. Results are mean ± SEM, n = 3 replicates/condition/patient. Beneficial effects of the drugs on VLCFA levels were reproduced in fibroblasts derived from these donors in two other independent experiments. ** p < 0.01, *** p < 0.001, **** p < 0.0001 by One‐way analysis of variance (ANOVA) followed by Dunnett's multiple comparison versus untreated AMN/C‐ALD cells\n\nFigure 2: Figure 2. PXL065 improves mitochondrial function and increases compensatory transporters, ABCD2 and ABCD3, mRNA levels in fibroblasts derived from two ALD—C‐ALD and AMN—patients. AMN (A) and C‐ALD (B) fibroblasts were exposed for 72 h to PXL065 or Pioglitazone at 10 μM. Bioenergetics analysis was performed using a Seahorse Analyzer and parameters were evaluated by sequential additions of: oligomycin (Oligo—1 μM), FCCP (0.25 μM) and Rotenone‐Antimycin A (Rot‐AA—1 μM). Basal is first three measurements, ATP‐linked is oxygen consumption rate (OCR) drop following oligo addition, Maximal Oxidative Capacity (MOC) is OCR following addition of FCCP. Results are mean ± SEM, n = 6 replicates/condition/patient. Cells were exposed for 72 h to PXL065 or pioglitazone at 10 μM prior to mRNA level analysis by RT‐qPCR in AMN (C) and C‐ALD fibroblasts (D). Results are mean ± SEM, n = 3–6 replicates/condition/patient. * p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001 by One‐way analysis of variance followed by Dunnett's multiple comparison versus untreated AMN/C‐ALD cells\n\nFigure 3: Figure 3. PXL065 improves adrenoleukodystrophy (ALD) pathology in glial cells from Abcd1‐null mice. Cells were exposed to 10 μM PXL065, pioglitazone, or control media. (A) Very long chain fatty acids (C26:0) quantitative analysis performed by mass spectrometry after 7 days exposure. (B) Bioenergetics analysis performed using a Seahorse Analyzer after 72‐h incubation; parameters were evaluated by sequential additions of: oligomycin (Oligo), FCCP and Rotenone‐Antimycin A. Basal is first three measurements, ATP‐linked is oxygen consumption rate (OCR) drop following oligo addition, Maximal Oxidative Capacity (MOC) is OCR following addition of FCCP. (C) Compensatory transporter gene expression measured by RT‐qPCR (normalized by RLP27 expression) after 72‐h incubation. Results are mean ± SEM, n = 2–6 replicates/condition. ** p < 0.01, *** p < 0.001, **** p < 0.0001 by one‐way analysis of variance followed by Dunnett's multiple comparison versus untreated glial cells\n\nFigure 4: Figure 4. PXL065 represses pro‐inflammatory gene expression in C‐ALD patient‐derived lymphocytes and in glial cells from Abcd1‐null mice. C‐ALD lymphocytes (A) were exposed for 72 h to PXL065 or Pioglitazone at 10 μM prior to mRNA level analysis by RT‐qPCR. Abcd1 null glial cells (B) were incubated with PXL065 or Pioglitazone at 10 μM for 2 h prior to stimulation by TNFα and IL1β for 70 h (total drug exposure of 72 h), followed by mRNA level analysis by RT‐qPCR. Results are mean ± SEM, n = 3 replicates/condition. Results were normalized by RLP27 expression. ** p < 0.01, *** p < 0.001, **** p < 0.0001 by One‐way ANOVA followed by Dunnett's multiple comparison vs untreated C‐ALD or Abcd1 null gial cells.\n\nFigure 5: Figure 5. PXL065 reduces C26:0 levels in plasma, brain and spinal cord. Six‐8‐week‐old Abcd1‐null mice were treated with PXL065 or pioglitazone (15 mg/kg QD) for 8 weeks. C26:0 content was measured in plasma (A), brain (B) and spinal cord (C) by mass spectrometry. Results are mean ± SEM, n = 12 wild‐type, 15 untreated Abcd1‐null, 15 PXL065 treated Abcd1‐ null and 15 pioglitazone treated Abcd1‐null mice. * p < 0.05, ** p < 0.01, **** p < 0.0001 by one‐way analysis of variance followed by Dunnett's multiple comparison or by Kruskal–Wallis followed by Dunn's multiple comparison versus untreated Abcd1‐null mice"
      }
    ]
  },
  {
    "id": "PMC9545763_multi_2",
    "image": [
      "images/PMC9545763-f6.png",
      "images/PMC9545763-f7.png",
      "images/PMC9545763-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Therapeutic potential of deuterium‐stabilized (R)‐pioglitazone—PXL065—for X‐linked adrenoleukodystrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. In older Abcd1‐null mice, PXL065 lowers spinal cord very long chain fatty acids, improves sciatic nerve morphology and enhances neurobehavioral functions. Older (age 13 months) Abcd1‐null mice were treated for 12 weeks with PXL065 or pioglitazone (15 mg/kg QD). (A) C26:0 content measured in spinal cord by mass spectrometry; results are mean ± SEM, n = 8 animals/condition. (B) Open‐field test monitoring results. Data are mean ± SEM, n = 8 animals/condition (seven animals for wild‐type in graph presenting number of rearings). (C) Axonal morphology (with representative images) of neurons determined by morphometric analysis of transversal slices of the sciatic nerve by electronic microscopy (800×). Data are mean ± SEM, n = 4 animals/condition. * p < 0.05, ** p < 0.01, **** p < 0.0001 by one‐way analysis of variance followed by Dunnett's multiple comparison or by Kruskal–Wallis followed by Dunn's multiple comparison vs untreated Abcd1‐null mice\n\nFigure 7: Figure 7. PXL065 retains nongenomic actions—inhibition of ACSL4—without PPARγ agonist activity. Enzymatic activities were measured by ex situ biochemical assays. PPARγ agonist activity (A) was measured using recombinant enzyme with a cofactor recruitment fluorescence assay using recombinant ligand binding domain protein in the presence of increasing concentrations of PXL065 or pioglitazone from 0.03 to 100 μM. Results are expressed as a percent of the control response to 10 μM rosiglitazone. ACSL4 (B) and ACSL1 activity (C) assays were performed using recombinant enzymes and [14C] palmitate, in the presence of increasing concentrations of PXL065, pioglitazone and leriglitazone from 0.5 to 6 μM. Results are mean ± SEM, n = 3 experiments for ACSL and 2 experiments for PPARγ.\n\nFigure 8: Figure 8. Diagram depicting the effects of PXL065 and Pioglitazone on PPARγ, the mitochondrial pyruvate carrier (MPC) and ACSL4, and the associated pathways. Potential mechanisms linking the targets of the compounds of interest to very long chain fatty acids lowering and their efficacy on the disease phenotype are represented in the blue tags."
      }
    ]
  },
  {
    "id": "PMC9555615_multi",
    "image": [
      "images/PMC9555615-f1.png",
      "images/PMC9555615-f2.png",
      "images/PMC9555615-f3.png",
      "images/PMC9555615-f4.png",
      "images/PMC9555615-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ether lipid deficiency disrupts lipid homeostasis leading to ferroptosis sensitivity\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A and B) structures of a typical phospholipid with two ester-linked fatty acids (A) or an “ether lipid”, with one ether linked fatty acid and one ester linked fatty acid (B). (C,D, H and I) Young adult worms were harvested and the end-product of lipid peroxidation, malondialdehyde (MDA), was measured and normalized to total protein using BCA. Each data point represents an independent experiment of 1,250 worms for each treatment. Statistical significance was determined using a two-way ANOVA with Tukey’s test for multiple comparisons summarized in S2 Table. TBHP, tert-butyl hydroperoxide; DGLA, dihommo-gamma-linolenic acid. (E) Simplified fatty acid composition in wild type, ads-1, and tmem-189. Detailed fatty acid composition of each strain with averages and standard deviations in S1 Table. PUFA, polyunsaturated fatty acid; MUFA, monounsaturated fatty acid; Plas, plasmalogen; SFA, saturated fatty acid. (F) Percentage (%) sterility in wild type, ads-1, and tmem-189 raised on 0.05mM, 0.1mM, 0.15mM, and 0.2mM DGLA. Each data point represents an independent experiment of 50 worms for each treatment. Statistical significance was determined using a two-way ANOVA with Tukey’s test for multiple comparisons. Shown are the comparison of the mutant vs. WT, all comparisons are summarized in S2 Table. (G) Oxidative stress survival assays were performed with 14.7 mM TBHP. Wild type and ads-1 were used as controls to compare with the survival of tmem-189. Approximately 100–200 worms were used for each strain per treatment. Statistical significance for survival was determined using log rank tests (Mantel Cox) and summarized in S2 Table. Fatty acid composition and sterility for (E, F and H) are displayed in S1 Table. Statistical differences shown are NS, not significant, * P<0.05, **P<0.01, ***P<0.001, ****P<0.0001.\n\nFigure 2: Figure 2. (A) Relative fatty acid composition of strains used for this study determined using gas chromatography-mass spectrometry. Complete composition of each strain with averages and standard deviations are displayed in S1 Table. SA-stearic acid (18:0), Pla-plasmalogen, OA-oleic acid (18:1(n-9)), cVA-cis-vaccenic acid (18:1(n-7)), LA-linoleic acid (18:2(n-6)), ALA-alpha linolenic acid (18:3(n-3)), GLA-gamma linolenic acid (18:3(n-6)), STA-stearidonic acid (18:(4n-3)), DGLA-dihomo-gamma linolenic acid (20:(3n-6)), AA-arachidonic acid (20:(4n-6)), ETA-eicosatetraenoeic acid (20:(4n-3)), EPA-eicosapentaenoic acid (20:(5n-3)). (B,C, and D) Survival of young adult wild type, ads-1, fat-3, and ads-1;fat-3 on 14.7mM tert-buryl hyderoperoxide (TBHP) ((E, F) Percentage (%) sterility in young adult worms of the indicated genotype raised on DGLA In (B, C, and D) approximately 100–200 worms were used for each strain per treatment. Statistical significance for survival was determined using log rank tests (Mantel Cox) and is shown in S2 Table. In (E and F), each dot represents an independent experiment of 50 worms for each treatment. Statistical significance was determined using a two-way ANOVA with Tukey’s test for multiple comparisons shown in S2 Table. For (E and F), fatty acid composition and sterility data are reported in S1 Table. Statistical differences compared to WT are * P<0.05, **P<0.01, ***P<0.001, ****P<0.0001.\n\nFigure 3: Figure 3. (A) Relative fatty acid composition in wild type worms treated with DGLA, AA, and EPA determined using gas chromatography-mass spectrometry. SA-stearic acid (18:0), Pla-plasmalogen, OA-oleic acid (18:1(n-9)), cVA-cis-vaccenic acid (18:1(n-7)), LA-linoleic acid (18:2(n-6)), ALA-alpha linolenic acid (18:3(n-3)), GLA-gamma linolenic acid (18:3(n-6)), STA-stearidonic acid (18:(4n-3)), DGLA-dihomo-gamma linolenic acid (20:(3n-6)), AA-arachidonic acid (20:(4n-6)), ETA-eicosatetraenoeic acid (20:(4n-3)), EPA-eicosapentaenoic acid (20:(5n-3)) (B) Percentage (%) sterility of wild type wormsraised on the indicated fatty acids. (C and D) Survival of young adult worms raised on the indicated fatty acids before exposure to 14.7mM tert-butyl hydroperoxide (TBHP). In (B) each dot represents an independent experiment of 50 worms for each treatment. Statistical significance was determined using a two-way ANOVA with Tukey’s test for multiple comparisons summarized in S2 Table. In (C and D) approximately 100–200 worms were used for each strain per treatment. Statistical significance for survival was determined using log rank tests (Mantel Cox) is shown in S2 Table. In (B, C and D), fatty acid compositions are reported in S1 Table.\n\nFigure 4: Figure 4. (A) Percentage (%) sterility in young adult worms of the indicated genotype raised on dihommo-gamma linolenic acid (DGLA). (B) Survival of young adult worms exposed to 14.7mM tert-butyl-hydroperoxide (TBHP). (C) Relative fatty acid composition determined with gas chromatography-mass spectrometry of strains used in (A) and (B). (D and E) Fold-change of basal mRNA levels in mutant worms relative to wild type worms grown on standard nematode growth media. mRNA levels were normalized to cdc-42 and Y45F10D.4. In (A) each dot represents an independent experiment of 50 worms for each treatment. Statistical significance was determined using a two-way ANOVA with Tukey’s test for multiple comparisons summarized in S2 Table. In (B) approximately 100–200 worms were used for each strain per treatment. Statistical significance for survival was determined using log rank tests (Mantel Cox) and is shown in S2 Table. In (C), values do not add up to 100% because dietary cyclopropane fatty acids and several others are not displayed in this chart. The complete fatty acid composition and sterility data are reported in S1 Table. In (D and E), student’s t-tests were performed to determine statistical significance and summarized in S2 Table. Statistical differences compared to WT are NS, not significant, * P<0.05, **P<0.01, ***P<0.001, ****P<0.0001.\n\nFigure 5: Figure 5. (A) Relative fatty acid composition of worms of the indicated genotype as determined with gas chromatography-mass spectrometry. SA-stearic acid (18:0), Pla-plasmalogen, OA-oleic acid (18:1(n-9)), cVA-cis-vaccenic acid (18:1(n-7)), LA-linoleic acid (18:2(n-6)), ALA-alpha linolenic acid (18:3(n-3)), GLA-gamma linolenic acid (18:3(n-6)), STA-stearidonic acid (18:(4n-3)), DGLA-dihomo-gamma linolenic acid (20:(3n-6)), AA-arachidonic acid (20:(4n-6)), ETA-eicosatetraenoeic acid (20:(4n-3)), EPA-eicosapentaenoic acid (20:(5n-3)) (B and C) Percentage (%) sterility in young adult worms of the indicated genotype raised on the indicated fatty acids. In (B and C) each dot represents an independent experiment of 50 worms for each treatment. Statistical significance was determined using a two-way ANOVA with Tukey’s test for multiple comparisons summarized in S2 Table. Fatty acid composition and sterility for (B, C, and D) are reported in S1 Table. In (D) each data point represents an independent experiment of 1,250 worms for each treatment. Statistical analysis was performed with Student’s t-test and P values are reported in S2 Table. * P<0.05, **P<0.01, ***P<0.001, ****P<0.0001."
      }
    ]
  },
  {
    "id": "PMC9569537_multi",
    "image": [
      "images/PMC9569537-f1.png",
      "images/PMC9569537-f2.png",
      "images/PMC9569537-f3.png",
      "images/PMC9569537-f4.png",
      "images/PMC9569537-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Protective Effect of Nopal Cactus (Opuntia ficus-indica) Seed Oil against Short-Term Lipopolysaccharides-Induced Inflammation and Peroxisomal Functions Dysregulation in Mouse Brain and Liver\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Effect of cactus seed oil, olive oil, or colza oil treatment on gene expression of the proinflammatory markers Il-1β (A,D), iNos (B,E), and Il-6 (C,F), in the brain and liver, respectively. Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. First, total RNA was isolated from mice brains or livers, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are means ± SD (n = 4–6), statistical significance of higher mean signal (*** p ≤ 0.001. ** p ≤ 0.01.) compared to control, (### p ≤ 0.01. ## p ≤ 0.01) compared to LPS, and ($$$ p ≤ 0.001. $$ p ≤ 0.01) compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons.\n\nFigure 2: Figure 2. Effect of cactus seed oil, olive oil, or colza oil treatment on protein expression of the proinflammatory marker Il-1β (A–D), in the brain (A,B) and liver (C,D), respectively. Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. Brain and liver homogenates were separated in PAGE-SDS electrophoresis and subjected to immunoblotting as described in Material and Methods section. Immunoblots were performed in triplicate and here we showed a representative blot. The three processed Il-1β bands (B1: 33 kDa; B2: 28 kDa; B3:17 kDa) intensities were analyzed by densitometry and standardized to α-tubulin (55 kDa) expression level in brain (B) and in liver (D). All values are means ± SD (n = 3) of 3 independent replicates. Statistical significance of higher mean signal strength compared to control, (### p ≤ 0.01. ## p ≤ 0.01. # p ≤ 0.05) compared to LPS, and ($$$ p ≤ 0.001. $$ p ≤ 0.01) compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons.\n\nFigure 3: Figure 3. Effect of cactus seed oil, olive oil, or colza oil treatment on protein expression of the iNOS in the brain (A) and liver (C), respectively. Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. Brain and liver homogenates were separated in PAGE-SDS electrophoresis and subjected to immunoblotting as described in Material and Methods section. Immunoblots were performed in triplicate and here we showed a representative blot. The iNOS 130 kDa band intensities were analyzed by densitometry and standardized to α-tubulin (55 kDa) expression level in brain (B) and in liver (D). All values are means ± SD (n = 3) of 3 independent replicates. Statistical significance of higher mean signal strength (* p ≤ 0.05) compared to control, compared to LPS, and compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons.\n\nFigure 4: Figure 4. Effect of cactus seed oil, olive oil, or colza oil treatment on gene expression of the anti-inflammatory markers Il-10 (A,C) and Il-4 (B,D), in the brain and liver, respectively. Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. First, total RNA was isolated from mice brains or livers, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are means ± SD (n = 4–6), statistical significance of higher mean signal (*** p ≤ 0.001. ** p ≤ 0.01) compared to control, (### p ≤ 0.01) compared to LPS, and ($$$ p ≤ 0.001. $ p ≤ 0.05) compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons.\n\nFigure 5: Figure 5. Effect of cactus seed oil, olive oil, or colza oil treatment on gene expression of Acox1 (A,D), Cat (B,E), and Sod1 (C,F) in brain and liver, respectively. Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 µg) four hours antemortem. First, total RNA was isolated from mice brains and livers, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are means ± SD (n = 3), statistical significance of higher mean signal (*** p ≤ 0.001. ** p ≤ 0.01. * p ≤ 0.05) compared to control, (### p ≤ 0.01, # p ≤ 0.05) compared to LPS, and ($$$ p ≤ 0.001. $$ p ≤ 0.01) compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons."
      }
    ]
  },
  {
    "id": "PMC9569537_multi_2",
    "image": [
      "images/PMC9569537-f6.png",
      "images/PMC9569537-f7.png",
      "images/PMC9569537-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Protective Effect of Nopal Cactus (Opuntia ficus-indica) Seed Oil against Short-Term Lipopolysaccharides-Induced Inflammation and Peroxisomal Functions Dysregulation in Mouse Brain and Liver\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Effect of cactus seed oil, olive oil, or colza oil treatment on the expression of peroxisomal CAT in brain (A) and in liver (C). Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 μg) four hours antemortem. Brain and liver homogenates were separated in PAGE-SDS electrophoresis and subjected to immunoblotting as described in Material and Methods section. Immunoblots were performed in triplicate and here we showed a representative blot. The CAT 66 kDa band intensities were analyzed by densitometry and standardized to β-actine (42 kDa) expression level in brain (B) and in liver (D). All values are means ± SD (n = 3) of 6 independent replicates for CTRL, LPS, CSO, and CSO+LPS, and 3 replicates for OO, OO+LPS, CO, and CO+LPS; statistical significance of higher mean signal strength (** p ≤ 0.01) compared to control, (# p ≤ 0.05) compared to LPS, and ($ p ≤ 0.05) compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons.\n\nFigure 7: Figure 7. Effect of cactus seed oil, olive oil, or colza oil treatment on the expression of peroxisomal ACOX1 in brain (A) and in liver (C). Male C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 μg) four hours antemortem. Brain and liver homogenates were separated in PAGE-SDS electrophoresis and subjected to immunoblotting as described in Material and Methods section. Immunoblots were performed in triplicate and here we showed a representative blot. The ACOX1 72 and 52 kDa band intensities were analyzed by densitometry and standardized to β-actine (42 kDa) expression level in brain (B) and in liver (D). All values are means ± SD (n = 3) of 6 independent replicates for CTRL, LPS, CSO, and CSO+LPS, and 3 replicates for OO, OO+LPS, CO, and CO+LPS; statistical significance of higher mean signal strength (*** p ≤ 0.001) compared to control, (# p ≤ 0.05) compared to LPS, and ($ p ≤ 0.05) compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons.\n\nFigure 8: Figure 8. Effect of cactus seed oil, olive oil, or colza oil treatment on the peroxisomal enzymes activities of brain and liver GPx (A,C) and CAT (B,D), respectively, and on liver ACOX1 (E). C57BL/6 mice received for 28 days a standard diet (control (CTRL)), a diet enriched with 6% (w/w) CSO, OO, or CO, and intravenous injection of LPS (100 μg) four hours antemortem. Brain and liver homogenates were prepared as described in Material and methods section. Results are expressed in (UI.mg−1 = one μmol of substrate transformed/minute/mg of proteins). All values are means ± SD (n = 6), statistical significance of higher mean signal strength (*** p ≤ 0.001. ** p ≤ 0.01. * p ≤ 0.05) compared to control, (### p ≤ 0.01) compared to LPS, and ($$$ p ≤ 0.001 and $$ p ≤ 0.01, $ p ≤ 0.05) compared to the different treatments with or without LPS administration. Statistics were executed using two-way ANOVA followed by Tukey test for multiple comparisons."
      }
    ]
  },
  {
    "id": "PMC9668298_multi",
    "image": [
      "images/PMC9668298-f1.png",
      "images/PMC9668298-f2.png",
      "images/PMC9668298-f3.png",
      "images/PMC9668298-f4.png",
      "images/PMC9668298-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Ubiquitin-based pathway acts inside chloroplasts to regulate photosynthesis\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A and B) Chloroplasts isolated from transgenic plants expressing Myc-tagged ubiquitin (6Myc-Ub), and from wild type, were analyzed by immunoblotting (A). Similar chloroplasts were treated with thermolysin protease (Ther), or buffer lacking protease (Mock), before immunoblotting analysis (B). The asterisk in (B) indicates a nonspecific band. (C) Chloroplasts isolated from 6Myc-Ub plants were separated into membrane pellet and soluble supernatant (predominantly stroma) fractions by centrifugation at 18,000g and then analyzed by immunoblotting. Analysis of control proteins confirmed the efficacy of the protease treatment and fractionation steps. Positions of molecular weight markers (sizes in kDa) are shown to the right of the images.\n\nFigure 2: Figure 2. (A) Dot plot showing significantly overrepresented gene ontology (GO) terms in the chloroplast ubiquitinome, as determined using chloroplasts purified from CDC48-DN plants after estradiol induction. Dot size indicates overrepresentation (fold enrichment) compared to the whole genome. Dot color indicates false discovery rate [FDR; −log10 (P value)], where higher FDR values indicate more statistically significant enrichment. Dots are not shown for terms lacking statistically significant (P < 0.05) enrichment. (B) Suborganellar and functional distribution of the chloroplast ubiquitinome, showing also ubiquitination sites as determined by di-Gly analysis. Localizations were assigned manually, and only proteins localized in a defined chloroplast compartment (OEM, IEM, stroma, and thylakoid), or in an internal chloroplast membrane fraction (comprising IEM and thylakoids), are shown. Boxes indicate individual proteins (white, nucleus-encoded; orange, chloroplast-encoded), and red circles with numbers indicate which amino acids showed ubiquitination. (C) Histogram showing the number of ubiquitination sites detected per protein in the chloroplast ubiquitinome. (D) Pie chart showing the relative abundance (based on peptide intensity) of different polyubiquitin linkage types in the chloroplast ubiquitinome. Values are means from three experiments. (E) Logo plot showing motif analysis of ubiquitinated peptides in the chloroplast ubiquitinome. Six residues either side of the modification site (position 0) are shown.\n\nFigure 3: Figure 3. (A) Pie chart showing the differential accumulation of chloroplast (cp) proteins upon CHLORAD inhibition, as determined by quantitative proteomic analysis of CDC48-DN and CDC48-WT transgenic plants after estradiol induction. (B) Dot plot showing significantly overrepresented GO terms for chloroplast proteins that are overaccumulated in CDC48-DN plants. Dot size indicates overrepresentation (fold enrichment) compared to the whole genome. Dot color indicates false discovery rate [FDR; −log10 (P value)], where higher FDR values indicate more statistically significant enrichment. Dots are not shown for terms lacking statistically significant (P < 0.05) enrichment. (C) Pie chart showing the differential accumulation of ubiquitinated chloroplast proteins in the quantitative proteomic analysis depicted in (A). Only proteins in the chloroplast ubiquitinome (Fig. 2) are shown. (D) Pie chart showing the differential expression of mRNAs corresponding to the chloroplast proteins identified by proteomics in (A), as determined by RNA-seq transcriptomics. (E) Dot plot showing a lack of correlation between chloroplast protein abundancies [from (A)] and corresponding mRNA abundancies [from (D)]. The coefficient of determination (R2) value is shown.\n\nFigure 4: Figure 4. (A and B) Proteasome dependency of PrfB3 degradation was analyzed. Wild-type protoplasts expressing PrfB3-HA were incubated with/without cycloheximide (CHX) and proteasome inhibitor bortezomib (Btz) and analyzed by immunoblotting (A). Bands for PrfB3-HA were quantified and normalized to histone H3 control data (B). Time 0 was taken as 100%. Data are means ± SEM from at least two experiments. (C to E) SP2 dependency of chloroplast-encoded protein degradation was analyzed. Wild-type and sp2 plants were incubated with lincomycin (Lin) and analyzed by immunoblotting (C) and Coomassie staining (D). Bands were quantified as in (B). Data are means ± SEM from at least four experiments. Asterisks in (E) indicate significance according to unpaired two-tailed Student’s t tests comparing the two genotypes at each time point (*P < 0.05, **P < 0.01, and ****P < 0.0001; ns, not significant). (F to H) CDC48 dependency of chloroplast-encoded protein degradation was analyzed. Data are equivalent to those in (C) to (E), except that CDC48-WT/DN transgenic plants were used. (I to K) Interaction of substrates with the CHLORAD apparatus was assessed by coimmunoprecipitation (co-IP). In (I), wild-type protoplasts were cotransfected with SP2-6Myc and either PrfB3-HA, YFP-HA, or SP1-HA. In (J), wild-type or SP2-6Myc seedlings were analyzed without protoplastation. In (K), wild-type protoplasts were transfected with YFP-HA or CDC48-Trap-HA [AtCDC48AE581Q that stabilizes substrate binding (8)]. Immunoprecipitations used anti-Myc (I and J) or anti-HA (K) resin. YFP-HA acted as a negative control. Positions of molecular weight markers (sizes in kDa) are shown. Asterisk in (I) indicates a nonspecific band. TL, total lysate; poly-Ub, poly-ubiquitinated.\n\nFigure 5: Figure 5. (A) The role of CDC48 in the extraction of chloroplast-encoded PsaA and PsbC substrates was analyzed using an in vivo retrotranslocation assay. Protoplasts from CDC48-WT and CDC48-DN transgenic plants that were transiently expressing FLAG-Ub were treated, after estradiol induction, with bortezomib proteasome inhibitor and then separated into cytosol and chloroplast fractions. In this assay, retrotranslocation occurred in intact cells, and the extracted substrates were protected by bortezomib inhibition, which initiated the experiment. After fractionation, ubiquitinated proteins were immunoprecipitated from both fractions and detected by immunoblotting. Tic40, which is not a substrate of CHLORAD, served as a negative control. Typical immunoblotting results are shown. Positions of molecular weight markers (sizes in kDa) are shown to the left of the images. The asterisk indicates a nonspecific band. (B and C) Retrotranslocation efficiency was assessed by quantifying the relative amounts of ubiquitinated PsaA (B) and PsbC (C) in the cytosol and chloroplast fractions described in (A). Data are means ± SEM from at least three experiments."
      }
    ]
  },
  {
    "id": "PMC9682283_multi",
    "image": [
      "images/PMC9682283-f1.png",
      "images/PMC9682283-f2.png",
      "images/PMC9682283-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Cerebello-brainstem dominant form of X-linked adrenoleukodystrophy with intrafamilial phenotypic variability\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Pedigree of the present family. The proband is indicated by an arrow. Affected males are designated by filled symbols and the carrier female by circle with dot (squares for males and circles for females).\n\nFigure 2: Figure 2. Brain MRI scans of the patients. The proband (II-1) had symmetric T2-weighted hyperintensities in the dentate nuclei and the surrounding cerebellar white matter. The first younger brother (II-3) presented brainstem and cerebellar atrophy with asymmetric T2-weighted hyperintensities in the middle cerebellar peduncles, cerebral peduncles, posterior limbs of the internal capsules, and periventricular white matter of the frontal lobe. The third younger brother (II-6) had diffuse T2-weighted hyperintensities in the midbrain, pons, middle cerebellar peduncle and cerebellum.\n\nFigure 3: Figure 3. (A) Sanger sequencing confirmed a hemizygous missense variant (c.887A>G, p.Tyr296Cys) of the ATP-binding cassette subfamily D member 1 gene (ABCD1) (NM_000033.4) that had been identified using whole-exome sequencing for the genome of the affected members (II-1, II-3, and II-6). The same variant was detected in a heterozygous state in the asymptomatic female carrier (II-8). (B) Wild-type and mutant residues (p.Tyr296Cys) in the ABCD1 protein are colored light-green and represented as sticks alongside the surrounding residues, which were involved in any interaction type. Red dots are hydrogen bonds, with orange representing weak ones. The crystal structure of the domain from wild-type ABCD1 isoform 1 was generated using SWISS-MODEL (https://swissmodel.expasy.org/) and is depicted as a cartoon representation. (C) Results obtained using other predictive tools (NMA based and other structure-based approaches) are also displayed, which predict the effect of the mutation using the DynaMut web-server with the normal mode analysis function (http://biosig.unimelb.edu.au/dynamut/). Visual representation of the Δ vibrational entropy energy in which the amino acids are colored according to the vibrational entropy change upon mutation. Blue regions indicate rigidification and red regions indicate an increase in flexibility."
      }
    ]
  },
  {
    "id": "PMC9683791_multi",
    "image": [
      "images/PMC9683791-f1.png",
      "images/PMC9683791-f1-2.png",
      "images/PMC9683791-f1-3.png",
      "images/PMC9683791-f1-4.png",
      "images/PMC9683791-f1-5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural and functional insights of the human peroxisomal ABC transporter ALDP\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Schematic of very-long-chain fatty acids transport into the peroxisomes by ALDP. (B–C) ATP hydrolysis of ALDP stimulated by C22:0-CoA (data are represented as mean ± SD; n=3; three biological repeats). (D) Cryo-electron microscopy structure of ALDP. The transmembrane domains (TMDs) and nucleotide-binding domains (NBDs) are indicated. Figure 1—source data 1.Cryo-electron microscopy data collection, refinement, and validation statistics.\n\nFigure 1: Figure 1. (A) A flowchart description of EM data processing. (B) The Fourier Shell Correlation (FSC) curve for the cryo-EM map. The average resolution is estimated to be 3.4 Å based on the FSC value of 0.143. (C) FSC curves of the refined model versus the overall 3.4 Å map that it was refined against (black); of the model refined in the first of the two independent maps used for the FSC calculation versus that same map (red); and of the model refined in the first of the two independent maps versus the second independent map (green). The small difference between the red and green curves indicates that the refinement of the atomic coordinates did not suffer from overfitting. (D) Resolution estimation of the density map. (E) Angular distribution of the particles used for reconstruction of the ALDP. Each cylinder represents one view, and the height of the cylinder is proportional to the number of particles for that view.\n\nFigure 1: Figure 1. (A) Cryo-EM map of ALDP with each monomer individually colored. The attached lipids around the transmembrane domains (TMDs) are colored in white. (B) The overall structure of ALDP. The TMDs and nucleotide-binding domains (NBDs) are indicated. ALDP contains a short helix at the peroxisomal side. (C) Representative cryo-EM densities of structural elements of ALDP.\n\nFigure 1: Figure 1. (A) Two unknown densities in the ligand-free state of adrenoleukodystrophy protein (ALDP). The surface electrostatic potential is shown. (B–C) Structures of C22:0-CoA-bound and oleoyl-CoA-bound ALDP. All these residues in the lower panels are reported to be mutation sites in ALD.\n\nFigure 1: Figure 1. (A) Structure similarities of the ABCD members. High structural similarities are found between adrenoleukodystrophy protein (ALDP) and ABCD2 or ABCD3 and ABCD4. The model of ABCD2 and ABCD3 is predicted by Alphafold. (B) Distinctive extracellular helix of ALDP at the peroxisomal side. (C) Sequence alignment of ABCD members. The sequences corresponding to the short peroxisomal helix are highlighted."
      }
    ]
  },
  {
    "id": "PMC9683791_multi_2",
    "image": [
      "images/PMC9683791-f2.png",
      "images/PMC9683791-f3.png",
      "images/PMC9683791-f3-2.png",
      "images/PMC9683791-f3-3.png",
      "images/PMC9683791-f3-4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural and functional insights of the human peroxisomal ABC transporter ALDP\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. (A) Structural alignments of ALDP in ligand-free, C22:0-CoA-bound (7VZB) (Chen et al., 2022), and ATP-bound states (7SHM) (Wang et al., 2022). The distance change (in Å) between transmembrane helix 4 (TM4) and TM6 reflects the conformational changes during lipid transport. The hollow arrows indicate three views of ALDP that are enlarged in B–D. CH: C-terminal helix; EH: extracellular helix.\n\nFigure 3: Figure 3. (A) Conformational changes of adrenoleukodystrophy protein (ALDP) from ligand-free to ATP-bound state. (B) Structural mapping of clinical-derived pathogenic mutations of ALDP. The Cα atoms of the indicated residues are shown as spheres. The residues involved in substrate binding are shown as red spheres. Other mutation sites on transmembrane domains are presented in green. Mutations on nucleotide-binding domain (NBD) and the single-mutation T693M on C-terminal helix are colored cyan, respectively. (C) Spatial location of selected ALD mutants and rationally designed mutations. (D) Transport of cytosolic C22:0-CoA, C24:0-CoA, C26:0-CoA, and ATP hydrolysis by wild-type (WT) ALDP and mutations (data are represented as mean ± SD; n = 3; three biological repeats). EH: extracellular helix.\n\nFigure 3: Figure 3. Cytoplasmic localization of adrenoleukodystrophy protein (ALDP) mutants. Green, ALDP-GFP (Green fluorescent protein). Red, catalase, a peroxisome marker. Blue, DAPI (4',6-diamidino-2-phenylindole dihydrochloride).\n\nFigure 3: Figure 3. (A) Expression level of adrenoleukodystrophy protein (ALDP) mutants. Glyceraldehyde-3-phosphate dehydrogenase (GAPDH) was used as loading control (data are represented as mean ± SD; n = 3; three statistical repeats). (B) The Tm values of selected mutations (data are represented as mean ± SD; n = 2; two technical repeats). Figure 3—figure supplement 3—source data 1.Western blot for Figure 3—figure supplement 3A.\n\nFigure 3: Figure 3. (A) A predicted model of adrenoleukodystrophy protein (ALDP) by AF (AF-ALDP). (B) Comparison of AF-model with the cryo-EM structure in apo state. (C) Structural comparison between the AF-model and the cryo-EM model in ATP-bound state (colored white)."
      }
    ]
  },
  {
    "id": "PMC9713710_multi",
    "image": [
      "images/PMC9713710-f1.png",
      "images/PMC9713710-f2.png",
      "images/PMC9713710-f3.png",
      "images/PMC9713710-f4.png",
      "images/PMC9713710-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin ligase RNF115 regulates phagosome maturation and host response to bacterial infection\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. AIntraphagosomal proteolysis assay shows that IFN‐γ activation of macrophages reduces phagosomal maturation. Shaded area represents SEM (six technical replicates; representative graph of three independent experiments).BWorkflow of phagosome isolation.C–EWestern blots showing increased polyubiquitylation on phagosomes compared to Total Cell Lysate (TCL) and further increases by IFN‐γ activation (C, E). Equal protein amounts were loaded for phagosomal and TCL samples. Vimentin serves as loading control; EEA1 as purity marker. (D) Phagosomal ubiquitylation is not changing substantially over the maturation of the phagosome (30 min pulse, 0, 30 and 180 min chase, respectively). LAMP1 serves as purity marker. Representative images of three replicates.FUbiquitin AQUA PRM assay for phagosomes from RAW264.7 cells shows abundance of atypical chains and increases for K6, K11, K48 and K63 chains on phagosomes in response to IFN‐γ activation. As the experiment is complex and has inherent variability, five independent experiments of three biological replicates were combined. M1 represents linear ubiquitin chains. M1 = linear ubiquitin chains. Error bars represent SEM of five biological replicates.GUbiquitin AQUA PRM assay of total cell lysates of RAW264.7 cells. Error bars represent SEM of three technical replicates in three independent experiments.HUbiquitin Chain Restriction (UbiCRest) experiment removing polyubiquitin chains from phagosomal extracts using specific and unspecific DUBs. UT = untreated.IRepresentative immunofluorescence micrograph showing that K63 polyubiquitin (in green) localises around the phagosome defined by Rab7 staining (in red). Bead size (in white): 3 μm. To account for people with red‐green colour‐blindness, we have added a magenta/cyan/yellow version in Appendix Fig S2. Scale bar is 2 μm. Intraphagosomal proteolysis assay shows that IFN‐γ activation of macrophages reduces phagosomal maturation. Shaded area represents SEM (six technical replicates; representative graph of three independent experiments). Workflow of phagosome isolation. Western blots showing increased polyubiquitylation on phagosomes compared to Total Cell Lysate (TCL) and further increases by IFN‐γ activation (C, E). Equal protein amounts were loaded for phagosomal and TCL samples. Vimentin serves as loading control; EEA1 as purity marker. (D) Phagosomal ubiquitylation is not changing substantially over the maturation of the phagosome (30 min pulse, 0, 30 and 180 min chase, respectively). LAMP1 serves as purity marker. Representative images of three replicates. Ubiquitin AQUA PRM assay for phagosomes from RAW264.7 cells shows abundance of atypical chains and increases for K6, K11, K48 and K63 chains on phagosomes in response to IFN‐γ activation. As the experiment is complex and has inherent variability, five independent experiments of three biological replicates were combined. M1 represents linear ubiquitin chains. M1 = linear ubiquitin chains. Error bars represent SEM of five biological replicates. Ubiquitin AQUA PRM assay of total cell lysates of RAW264.7 cells. Error bars represent SEM of three technical replicates in three independent experiments. Ubiquitin Chain Restriction (UbiCRest) experiment removing polyubiquitin chains from phagosomal extracts using specific and unspecific DUBs. UT = untreated. Representative immunofluorescence micrograph showing that K63 polyubiquitin (in green) localises around the phagosome defined by Rab7 staining (in red). Bead size (in white): 3 μm. To account for people with red‐green colour‐blindness, we have added a magenta/cyan/yellow version in Appendix Fig S2. Scale bar is 2 μm. Data information: *P‐value < 0.05; **P‐value < 0.01 by paired two‐tailed Student's t‐test. Relative mobilities of reference proteins (masses in kDa) are shown on the right of each blot.\n\nFigure 2: Figure 2. AWorkflow. 30‐min‐old phagosomes were isolated from RAW264.7 cells. Phagosome extracts were tryptically digested for total proteome analysis or Gly‐Gly pull‐downs were performed to enrich for ubiquitylated peptides.B, CSelected phagosomal proteins of the ubiquitin system (Ubiquitin & ubiquitin‐like modifiers (ULM), E1, E2 and E3 and deubiquitylases (DUBs)) and their abundance changes in response IFN‐γ activation. “IFN‐γ only” or “Resting only” are used when the proteins were only detected in the respective sample by label‐free proteomics.DCombined analysis of total proteome and Gly‐Gly proteomics data sets of phagosomes from untreated and IFN‐γ activated RAW264.7 cells.EGene Ontology (GO) Analysis of proteins that were ubiquitylated in response to IFN‐γ activation but did not change (−0.5 > Log2 < 0.5) significantly on the protein level.FSelected networks of proteins and their ubiquitylation sites obtained from STRING using data from panel D. Level of shading of connecting lines indicates interaction confidence. Workflow. 30‐min‐old phagosomes were isolated from RAW264.7 cells. Phagosome extracts were tryptically digested for total proteome analysis or Gly‐Gly pull‐downs were performed to enrich for ubiquitylated peptides. Selected phagosomal proteins of the ubiquitin system (Ubiquitin & ubiquitin‐like modifiers (ULM), E1, E2 and E3 and deubiquitylases (DUBs)) and their abundance changes in response IFN‐γ activation. “IFN‐γ only” or “Resting only” are used when the proteins were only detected in the respective sample by label‐free proteomics. Combined analysis of total proteome and Gly‐Gly proteomics data sets of phagosomes from untreated and IFN‐γ activated RAW264.7 cells. Gene Ontology (GO) Analysis of proteins that were ubiquitylated in response to IFN‐γ activation but did not change (−0.5 > Log2 < 0.5) significantly on the protein level. Selected networks of proteins and their ubiquitylation sites obtained from STRING using data from panel D. Level of shading of connecting lines indicates interaction confidence.\n\nFigure 3: Figure 3. Proteomics intensity levels of selected phagosomal E3 ligases enriched upon IFN‐γ activation. Missing values for RNF115 and Herc6 in resting macrophages have been added by imputation. Standard deviation bars represent SD of three biological replicates.Western blot of phagosomal and TCL extracts showing enrichment of RNF115 on phagosomes of RAW264.7 cells and its increased abundance in response to IFN‐γ activation. Rab7 serves as purity control, iNOS as activation control and vimentin as loading control. Representative image of three replicates. Relative mobilities of reference proteins (masses in kDa) are shown on the right of each blot.Representative immunofluorescence micrograph showing RNF115 co‐staining with LAMP1 around the phagosome in murine BMDMs. Scale bar equals 5 μm.Volcano plot of proteomics data of resting WT and RNF115 KO BMDM phagosomes. Selected proteins are highlighted.Gene Ontology (GO) analysis of enriched and depleted proteins from (D).Proteomics intensity data of selected protein complexes derived from (D). Error bars represent of three biological replicates. Proteomics intensity levels of selected phagosomal E3 ligases enriched upon IFN‐γ activation. Missing values for RNF115 and Herc6 in resting macrophages have been added by imputation. Standard deviation bars represent SD of three biological replicates. Western blot of phagosomal and TCL extracts showing enrichment of RNF115 on phagosomes of RAW264.7 cells and its increased abundance in response to IFN‐γ activation. Rab7 serves as purity control, iNOS as activation control and vimentin as loading control. Representative image of three replicates. Relative mobilities of reference proteins (masses in kDa) are shown on the right of each blot. Representative immunofluorescence micrograph showing RNF115 co‐staining with LAMP1 around the phagosome in murine BMDMs. Scale bar equals 5 μm. Volcano plot of proteomics data of resting WT and RNF115 KO BMDM phagosomes. Selected proteins are highlighted. Gene Ontology (GO) analysis of enriched and depleted proteins from (D). Proteomics intensity data of selected protein complexes derived from (D). Error bars represent of three biological replicates. Data information: n.d., not detected; *P‐value < 0.05; **P‐value < 0.01 by unpaired two‐tailed Student's t‐test.\n\nFigure 4: Figure 4. A, BIntraphagosomal proteolysis and acidification assays show that loss of RNF115 increases phagosome maturation in BMA cells.CComplementing the RNF115 KO with WT RNF115 or a W259A mutant which is unable to bind to E2 enzymes, shows that RNF115 ligase activity is required for the increase of phagosome maturation. Shaded areas represent SEM. Intraphagosomal proteolysis and acidification assays show that loss of RNF115 increases phagosome maturation in BMA cells. Complementing the RNF115 KO with WT RNF115 or a W259A mutant which is unable to bind to E2 enzymes, shows that RNF115 ligase activity is required for the increase of phagosome maturation. Shaded areas represent SEM. Data information: six technical replicates; representative graphs of three independent experiments.\n\nFigure 5: Figure 5. Volcano plot of proteomics experiment of Gly‐Gly peptides from phagosomal extracts of WT and RNF115 KO macrophages. Selected proteins are highlighted.Network representation (from STRING v11) (Szklarczyk et al, 2019) of selected proteins with reduced ubiquitylated peptide abundance in response to loss of RNF115, that is potential phagosomal substrates of RNF115.Immunofluorescence micrographs of VAMP8 (green) and Syntaxin‐7 (STX7; red) show strong colocation around 3 μm silica bead phagosomes (white) in BMA macrophages. Nuclei are stained with Dapi. Scale bar is 5 μm. To account for people with red‐green colour‐blindness, we have added a magenta/cyan/yellow version in Appendix Fig S5.Colocation of VAMP8 (green) and STX7 (red) on individual phagosomes between WT and RNF115 KO cells represented by intersection, Manders' M1 and overlap coefficients. Data are represented as a box and whisker plot of total values across biological duplicate experiments, where the whiskers represent the minimum to maximum values and the central band indicates the median. Error bars represent SEM of two technical replicates of two biological replicates. *P‐value < 0.05; by unpaired two‐tailed Student's t‐test.Structure of VAMP8 and STX7 complex onto which a single ubiquitin molecule on VAMP8 K59 was modelled. Inlay: ubiquitylation of K59 disrupts a hydrogen bond between VAMP8 K59 and STX7 Q219. Volcano plot of proteomics experiment of Gly‐Gly peptides from phagosomal extracts of WT and RNF115 KO macrophages. Selected proteins are highlighted. Network representation (from STRING v11) (Szklarczyk et al, 2019) of selected proteins with reduced ubiquitylated peptide abundance in response to loss of RNF115, that is potential phagosomal substrates of RNF115. Immunofluorescence micrographs of VAMP8 (green) and Syntaxin‐7 (STX7; red) show strong colocation around 3 μm silica bead phagosomes (white) in BMA macrophages. Nuclei are stained with Dapi. Scale bar is 5 μm. To account for people with red‐green colour‐blindness, we have added a magenta/cyan/yellow version in Appendix Fig S5. Colocation of VAMP8 (green) and STX7 (red) on individual phagosomes between WT and RNF115 KO cells represented by intersection, Manders' M1 and overlap coefficients. Data are represented as a box and whisker plot of total values across biological duplicate experiments, where the whiskers represent the minimum to maximum values and the central band indicates the median. Error bars represent SEM of two technical replicates of two biological replicates. *P‐value < 0.05; by unpaired two‐tailed Student's t‐test. Structure of VAMP8 and STX7 complex onto which a single ubiquitin molecule on VAMP8 K59 was modelled. Inlay: ubiquitylation of K59 disrupts a hydrogen bond between VAMP8 K59 and STX7 Q219."
      }
    ]
  },
  {
    "id": "PMC9713710_multi_2",
    "image": [
      "images/PMC9713710-f6.png",
      "images/PMC9713710-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"The E3 ubiquitin ligase RNF115 regulates phagosome maturation and host response to bacterial infection\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. AInfection of WT and RNF115 KO BMA cells with S. Typhimurium for 4 h shows an increased survival in RNF115 KO macrophages. Output/input values correspond to the number of bacteria inside the cell recovered at the specific time point normalised over the number of bacteria added to the cells at the start of the infection. UI, uninfected cells. Standard deviation bars represent SD of four biological replicates.BInfection with S. Typhimurium for 6 h shows increased TNF‐α and IL6 secretion in RNF115 KO BMA. Data of five independent replicates. MOI = 10. Error bars represent SEM of six biological replicates.C, DPercentage (%) of GFP was analysed by flow cytometry from Salmonella‐infected BMA cells for 4 h. (C) % GFP of Salmonella encoding SPI‐2 response (PsseG)‐inducible promoter fused to GFP and (D) acidity exposure (Pasr)‐inducible promoter fused to GFP. Stronger SPI‐2 response and acidity exposure was shown in RNF115 KO compared to WT cells. Each dot represents a biological replicate. Groups were compared using an unpaired two‐tailed t‐test. Standard deviation bars represent SD of four biological replicates. Data information: *P < 0.05; **P‐value < 0.01; by paired two‐tailed Student's t‐test. Infection of WT and RNF115 KO BMA cells with S. Typhimurium for 4 h shows an increased survival in RNF115 KO macrophages. Output/input values correspond to the number of bacteria inside the cell recovered at the specific time point normalised over the number of bacteria added to the cells at the start of the infection. UI, uninfected cells. Standard deviation bars represent SD of four biological replicates. Infection with S. Typhimurium for 6 h shows increased TNF‐α and IL6 secretion in RNF115 KO BMA. Data of five independent replicates. MOI = 10. Error bars represent SEM of six biological replicates. Percentage (%) of GFP was analysed by flow cytometry from Salmonella‐infected BMA cells for 4 h. (C) % GFP of Salmonella encoding SPI‐2 response (PsseG)‐inducible promoter fused to GFP and (D) acidity exposure (Pasr)‐inducible promoter fused to GFP. Stronger SPI‐2 response and acidity exposure was shown in RNF115 KO compared to WT cells. Each dot represents a biological replicate. Groups were compared using an unpaired two‐tailed t‐test. Standard deviation bars represent SD of four biological replicates. Data information: *P < 0.05; **P‐value < 0.01; by paired two‐tailed Student's t‐test.\n\nFigure 7: Figure 7. AInfection of WT and RNF115 KO BMA cells with S. aureus for 6 h. Output/input values correspond to the number of bacteria inside the cell recovered at the specific time point normalised over the number of bacteria added to the cells at the start of the infection. UI, uninfected cells. Standard deviation bars represent SD of four biological replicates.BELISA data show that loss of RNF115 increases TNF‐α and IL6 secretion after 6 h of infection with S. aureus and in uninfected (UI) cells. Error bars represent SEM (n = 3 biological replicates, representative graph from three independent experiments). Statistical analysis was don through paired two‐tailed Student's t‐test.CWT and RNF115 mice were infected with S. aureus and after 48 h CFUs were counted in liver and spleen. Error bars represent SEM of six biological replicates. There was no significant difference between WT and RNF115 KO mice.DBox and whisker plot represents the quantification of the percentage (%) of the hepatic lesion area in the livers from six wild‐type (WT) and six RNF115 KO (KO) mice after 48 h infection with S. aureus. Haematoxylin and eosin (H&E)‐stained liver sections of one representative animal per genotype are shown on the right, dotted line depicts the damaged area. Groups were compared using an unpaired two‐tailed t‐test. The statistical significance of the comparisons is indicated as follows: Each dot represents an individual animal.E, FBox and whisker plots represent the average cell counts per high power field (HPF) of CD3 positive T‐cells (E), and CD68 positive macrophages (F) in the livers from six wild‐type (WT) and six RNF115 KO (KO) mice after 48 h infection with S. aureus. Representative immunohistochemistry sections are shown on the right. Groups were compared using an unpaired two‐tailed t‐test. The statistical significance of the comparisons is indicated as follows: **P < 0.01. Each dot represents an individual animal. Infection of WT and RNF115 KO BMA cells with S. aureus for 6 h. Output/input values correspond to the number of bacteria inside the cell recovered at the specific time point normalised over the number of bacteria added to the cells at the start of the infection. UI, uninfected cells. Standard deviation bars represent SD of four biological replicates. ELISA data show that loss of RNF115 increases TNF‐α and IL6 secretion after 6 h of infection with S. aureus and in uninfected (UI) cells. Error bars represent SEM (n = 3 biological replicates, representative graph from three independent experiments). Statistical analysis was don through paired two‐tailed Student's t‐test. WT and RNF115 mice were infected with S. aureus and after 48 h CFUs were counted in liver and spleen. Error bars represent SEM of six biological replicates. There was no significant difference between WT and RNF115 KO mice. Box and whisker plot represents the quantification of the percentage (%) of the hepatic lesion area in the livers from six wild‐type (WT) and six RNF115 KO (KO) mice after 48 h infection with S. aureus. Haematoxylin and eosin (H&E)‐stained liver sections of one representative animal per genotype are shown on the right, dotted line depicts the damaged area. Groups were compared using an unpaired two‐tailed t‐test. The statistical significance of the comparisons is indicated as follows: Each dot represents an individual animal. Box and whisker plots represent the average cell counts per high power field (HPF) of CD3 positive T‐cells (E), and CD68 positive macrophages (F) in the livers from six wild‐type (WT) and six RNF115 KO (KO) mice after 48 h infection with S. aureus. Representative immunohistochemistry sections are shown on the right. Groups were compared using an unpaired two‐tailed t‐test. The statistical significance of the comparisons is indicated as follows: **P < 0.01. Each dot represents an individual animal. Data information: *P < 0.05; **P < 0.01; ***P < 0.001."
      }
    ]
  },
  {
    "id": "PMC9718529_multi",
    "image": [
      "images/PMC9718529-f1.png",
      "images/PMC9718529-f1-2.png",
      "images/PMC9718529-f2.png",
      "images/PMC9718529-f2-2.png",
      "images/PMC9718529-f2-3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Modular UBE2H-CTLH E2-E3 complexes regulate erythroid maturation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. (A) Cartoon indicating key features of mammalian erythropoiesis. (B) Heat map of z-scored protein abundance (log2 data-independent acquisition (DIA) intensity) of differentially expressed E2 enzymes in differentiated HUDEP2 cells. (C) Heat map of z-scored protein abundance (log2 DIA intensity) of differentially expressed E2 enzymes in differentiated CD34+ cells. (D) HUDEP2 cells were differentiated in vitro and analysed by immunoblotting with indicated antibodies. (E) CD34+ cells were differentiated in vitro, cell populations enriched by FACS, and analysed by immunoblotting with indicated antibodies. (F) Heat map of z-scored protein abundance (log2 DIA intensity) of differentially expressed CTLH complex subunits in differentiated HUDEP2 cells. (G) Heat map of z-scored protein abundance (log2 DIA intensity) of differentially expressed CTLH complex subunits in differentiated CD34+ cells. Figure 1—source data 1.Original, uncropped scans of immunoblots.\n\nFigure 1: Figure 1. (A) Schematic with two-phase culture conditions of in vitro reconstituted erythropoiesis of CD34+ cells. Stem cell factor, SCF; erythropoietin, EPR. (B) Schematic with culture conditions of in vitro reconstituted erythropoiesis of HUDEP2 cells. (C) Number of different proteins quantified in each differentiation stage (days 0, 3, 6, 9, 12) of HUDEP2 parental (WT) and MAEA-/-cl3-1 cells (Dataset 1), and HUDEP2 parental, MAEA-/-cl3-1, and UBE2H-/-cl13 (Dataset 2). The mean value ± SD of three biological replicates is shown. (D) Correlation-based analysis illustrating reproducibility between biological replicates. High (1.0) and lower (0.94) Pearson correlation are indicated in blue and white, respectively. (E) Heat map of z-scored protein abundance (log2 data-independent acquisition (DIA) intensity) of 2771 differentially expressed proteins in differentiated HUDEP2 cells (ANOVA, false discovery rate [FDR] < 0.01). Differentiation time stages correspond to schematic in (B).\n\nFigure 2: Figure 2. (A) Cartoon of the supramolecular RANBP9-CTLH assembly indicating the catalytic (blue), core (grey/yellow), and supramolecular assembly (orange) modules. (B) Model of remodelling RANBP9- and RANBP10-CTLH complexes. (C) HUDEP2 cell lysates from differentiation days 0 and 6 were separated on sucrose gradients, and fractions analysed by immunoblotting with indicated antibodies. Fractions containing supramolecular CTLH assemblies are boxed in red. (D) Workflow of the sequential immunoprecipitation (IP) to determine RANBP9- and RANBP10-CTLH complexes. (E) HUDEP2 cell lysates from differentiation days 0, 4, and 8 were subjected to sequential IPs with RANBP9 antibody and ARMC8-specific nanobody as described in (D) followed by immunoblot analysis with indicated antibodies. IgG: unspecific antibody; mock: absence of nanobody. (F) Immunoblots of lysates of HUDEP2 parental, RANBP9-/-, and RANBP10-/- cells probing for RANBP9 and RANBP10. Actin serves as loading control. (G) Sucrose gradient fractionation of HUDEP2 cell lysates from RANBP9-/- or RANBP10-/- knock out lines, fractions were analysed by immunoblotting with indicated antibodies. Fractions containing supramolecular CTLH assemblies are boxed in red. Figure 2—source data 1.Original, uncropped scans of immunoblots. Figure 2—source data 2.Original, uncropped scans of immunoblots. Figure 2—source data 3.Original, uncropped scans of immunoblots.\n\nFigure 2: Figure 2. (A) Alignment of human RANBP9 and RANBP10 sequences, with identical sequences highlighted in black. (B) Structural alignments of SPRY domains of RANBP9 (PDB: 7NSC, light green) and RANBP10 (PDB:5JIA, dark green).\n\nFigure 2: Figure 2. The homology model of the nanobody (grey) and the structure of the CTLH core (colour-coded by subunits as in Figure 3C, PDB: 7NSC) was fitted in the cryo-EM density (transparent surface). The CDR loop of the nanobody contacts the C-terminal armadillo repeats of ARMC8 (purple) ranging from aa 420 to 470."
      }
    ]
  },
  {
    "id": "PMC9718529_multi_2",
    "image": [
      "images/PMC9718529-f2-4.png",
      "images/PMC9718529-f3.png",
      "images/PMC9718529-f4.png",
      "images/PMC9718529-f4-2.png",
      "images/PMC9718529-f4-3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Modular UBE2H-CTLH E2-E3 complexes regulate erythroid maturation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 2: Figure 2. (A) Schematics of CRISPR knockouts of RANBP9, showing exon structure and indicated guide RNAs and PAM sequences. (B) Schematics of CRISPR knockouts of RANBP10, showing exon structure and indicated guide RNAs and PAM sequences.\n\nFigure 3: Figure 3. (A) Chromatograms (top) and Coomassie-stained SDS-PAGE gels (bottom) from size-exclusion chromatography of recombinant RANBP10-CTLHSR4 and RANBP9-CTLHSR4 complexes. (B) Cryo-EM map of RANBP10-CTLHSR4 (EMDB: EMD-16242, left) and RANBP9-CTLHSR4 (EMDB: EMD-12537) (right) with Cat-module and SRS-module indicated. (C) Focused refined map of the RANBP10-CTLH SRS-module with coloured subunits: ARMC8, purple; TWA1, salmon;GID4(Δ1–99), red; RANBP10 SPRY-domain, green. (D) Immunoprecipitation (IP) from HUDEP2 cell lysates with IgG control and UBE2H-specific antibody and immunoblot analysis. (E) IP from K562 cell lysates with IgG control and UBE2H-specific antibody and immunoblot analysis. IgG light chain (IgG-LC), IgG heavy chain (IgG-HC). (F) Fluorescence scan of SDS-PAGE gels presenting time course of in vitro ubiquitylation assay with fluorescently labelled model substrate peptide PGLW(X)n-23K with lysine at position 23 (pep*) in the presence of UBE2H, RANBP10-CTLH or RANBP9-CTLH, and GID4. Figure 3—source data 1.Original, uncropped scans of Coomassie-stained SDS-PAGEs and immunoblots.\n\nFigure 4: Figure 4. (A) Immunoblots of lysates of HUDEP2 parental, MAEA-/-, and UBE2H-/- knockout clones probing for MAEA and UBE2H. Actin serves as loading control. (B) Quantitation of flow cytometry blots of indicated HUDEP2 cell lines assessing fraction of CD235a+ cells in expansion growing media condition. Error bars represent mean ± SD of n = 3–5 biological replicates. (C) Overlap between proteins with abundance differences of UBE2H-/- versus parental and MAEA-/- versus parental comparisons (top). Proteins with abundance differences (log2) of UBE2H-/- versus parental blotted against proteins with abundance differences (log2) MAEA-/- versus parental comparisons (bottom). Commonly enriched proteins are highlighted (top-right quadrant). (D) Gene Ontology (GO) enrichment analyses of upregulated protein in MAEA-/- versus parental and UBE2H-/- versus parental comparisons performed using Fisher’s exact test (Benj. Hoch. FDR 5%). (E) Quantitation of flow cytometry blots of indicated HUDEP2 cell lines assessing fraction of CD49d+/Band3+ cells at differentiation day 3. Error bars represent mean ± SD of n = 2–4 biological replicates. (F) Indicated HUDEP2 cell lines, cultured in expansion media, were sorted for CD49d+/Band3- (flow cytometry blots, top) followed by induction of erythroid maturation. Flow cytometry blots of indicated HUDEP2 cell lines showing CD49d/Band3 expression at day 4 after induced erythroid maturation. (G) Quantitation of (H) with graph showing fraction of CD49d+/Band3+ cells. Error bars represent mean ± SD of n = 2 biological replicates. (H) Principal component analysis (PCA) of erythroid differentiation stages (day 0, green; day 3, purple; day 6, orange; day 9, blue; day 12, brown) of HUDEP2 parental (par) and MAEA-/-cl3-1 (∆M) cell lines with their biological replicates based on expression profiles of selected erythroid marker proteins. (I) Immunoblot analysis of CRISPR-Cas9-mediated targeting of MAEA (MAEAsg1-3) in CD34+ cells. Histone H3 serves as loading control. (J) Quantitation of flow cytometry blots of MAEAsg-targeted cell lines assessing fraction of enucleated cells. Error bars represent mean ± SD of n = 2 biological replicates. (K) Immunoblot analysis of CRISPR-Cas9-mediated targeting of UBE2H (UBE2Hsg1-3) in CD34+ cells. Histone H3 serves as loading control. (L) Quantitation of flow cytometry blots of UBE2Hsg-targeted cell lines assessing fraction of enucleated cells. Error bars represent mean ± SD of n = 2 biological replicates. Figure 4—source data 1.Original, uncropped scans of immunoblots.\n\nFigure 4: Figure 4. (A) Schematics of CRISPR knockouts of MAEA, showing exon structure and indicated guide RNAs and PAM sequences. (B) Schematics of CRISPR knockouts of UBE2H, showing exon structure and indicated guide RNAs and PAM sequences. (C) Immunoblots of lysates of K562 parental, MAEA-/-cl1-1, UBE2H-/-cl1-5 cells probing for MAEA and UBE2H. Actin serves as loading control. Figure 4—figure supplement 1—source data 1.Original, uncropped scans of immunoblots.\n\nFigure 4: Figure 4. (A) Flow cytometry plots of mock (top) or NaB-treated (bottom) K562 parental, MAEA-/-cl1-1 and UBE2H-/-cl1-5 cell lines showing CD235a expression. (B) Quantitation of (A), with graph showing fraction of CD235a-expressing K562 parental, MAEA-/-cl1-1, UBE2H-/-cl1-5 cells in the presence of Na-butyrate (NaB) or mock treated. Error bars represent mean ± SD of n = 3 biological replicates. (C) Immunoblot analysis of cell lysates from K562 parental, MAEA-/-cl1-1, UBE2H-/-cl1-5 treated with 0, 0.3, or 0.6 mM NaB for 24 hr. Anti-GYPA/CD235a antibody detects variant forms of glycosylated GYPA. Actin serves as loading control. (D) Flow cytometry plots of indicated HUDEP2 cell lines showing CD235a expression in expansion growing media condition. (E) Volcano plots of p-values (-log10) versus protein abundance (log2) differences between parental and UBE2H-/-cl13 cells with erythroid marker proteins highlighted in red. (F) Volcano plots of p-values (-log10) versus protein abundance (log2) differences between parental and MAEA-/-cl3-1 cells with erythroid marker proteins highlighted in red. (G) Proteins with abundance difference (log2) of UBE2H-/- versus parental plotted against proteins with abundance difference (log2) of MAEA-/- versus parental comparisons. Proteins implicated in quiescence are highlighted. (H) Flow cytometry plots of indicated HUDEP2 cell lines showing CD49d/Band3 expression at day 3 after induced erythroid differentiation. Figure 4—figure supplement 2—source data 1.Original, uncropped scans of immunoblots."
      }
    ]
  },
  {
    "id": "PMC9718529_multi_3",
    "image": [
      "images/PMC9718529-f4-4.png",
      "images/PMC9718529-f4-5.png",
      "images/PMC9718529-f5.png",
      "images/PMC9718529-f5-2.png",
      "images/PMC9718529-f6.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Modular UBE2H-CTLH E2-E3 complexes regulate erythroid maturation\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 4: Figure 4. (A) Correlation-based analysis illustrating reproducibility between biological replicates. High (1.0) and lower (0.75) Pearson correlation are indicated in blue and white, respectively. (B) Heat map of z-scored protein abundance (log2 data-independent acquisition [DIA] intensity) of 3193 differentially expressed proteins in differentiated HUDEP2 parental and MAEA-/-cl3-1 cells (ANOVA, false discovery rate [FDR] < 0.01). (C) Heat map of z-scored protein abundance (log2 DIA intensity) of differentially expressed erythroid marker proteins in differentiating HUDEP2 parental and MAEA-/-cl3-1 cells. (D) Principal component analysis (PCA) of erythroid differentiation stages (day 0, green; day 3, purple; day 6, orange; day 9, blue; day 12, brown) of HUDEP2 parental (par) and MAEA-/-cl3-1 (∆M) cell lines with their biological replicates based on expression profiles of all quantified proteins.\n\nFigure 4: Figure 4. (A) Flow cytometry plots of mock, non-target, and MAEA_short guide (sg) targeted CD34+ cell lines showing Hoechst 33342-negative cell populations (enucleated cells) of erythroid maturation at day 14. (B) Flow cytometry plots of mock, non-target, and UBE2H_sg targeted CD34+ cell lines showing Hoechst 33342-negative cell populations (enucleated cells) of erythroid maturation at day 14.\n\nFigure 5: Figure 5. (A) Immunoblot analysis of CRISPR-Cas9-edited (RANBP9 or RANBP10) HUDEP2 cell pools using indicated antibodies. (B) Quantitation of flow cytometry blots of indicated CRISPR-Cas9 HUDEP2 cell pools assessing fraction of CD235a+ cells in expansion growing media condition. Error bars represent mean ± SD of n = 3 biological replicates. (C, D) Immunoblot analysis of HUDEP2 RANBP9-/- or RANBP10-/- cell lines using indicated antibodies. (E) Quantitation of flow cytometry blots of indicated CRISPR-Cas9 HUDEP2 cell lines assessing fraction of CD235a+ cells in expansion growing media condition. Error bars represent mean ± SD of n = 3 biological replicates. (F, H) Flow cytometry blots of indicated HUDEP2 cell lines showing CD49d/Band3 expression at day 3 after induced erythroid maturation. (G, I) Quantitation of (F) and (H) with graphs showing fraction of CD49d+/Band3+ cells. Error bars represent mean ± SD of n = 3 biological replicates. Figure 5—source data 1.Original, uncropped scans of immunoblots.\n\nFigure 5: Figure 5. (A) Flow cytometry plots of expansion growing HUDEP2 cells comparing parental, sgRANBP9- and sgRANBP10 CRISPR-Cas9-targeted cells showing CD235a expression. (B) Flow cytometry plots of expansion growing parental HUDEP2, RANBP9-/- clones (cl1-7, cl1-116, cl2-1) and RANBP10-/- clones (cl1-8, cl1-103, cl1-108) showing CD235a expression.\n\nFigure 6: Figure 6. (A) HUDEP2 parental and MAEA-/- (clone 3-1 and 11) cells were differentiated in vitro and analysed by immunoblotting to detect UBE2H protein levels. (B) mRNA determination by RT-qPCR of HUDEP2 parental and MAEA-/-cl3-1 cells at differentiation stage day 9. Results (normalized to GAPDH) are mean ± SD of n = 2 experiments. (C) K562 cell can be either induced with Na-butyrate (NaB) for erythroid-like differentiation, or induced with 12-O-tetradodecanoyl-phorbol-13 acetate (TPA) for megakaryocyte-like differentiation. (D) K562 parental and knockout cell lines were treated with NaB for 24 hr and analysed by immunoblotting with indicated antibodies. (E) K562 parental and knockout cell lines were treated with TPA for 24 hr and analysed by immunoblotting with indicated antibodies. (F) K562 parental and MAEA-/-cl1-1 cell lines were treated with either NaB or TPA for 24 hr, and UBE2H mRNA levels determination by RT-qPCR. Results (normalized to GAPDH) are mean ± SD of n = 6–8 experiments. (G) K562 parental and MAEA-/-cl1-1 cell lines were mock- or 0.6 mM NaB-treated for 24 hr, followed by 2, 6, and 24 hr proteasome inhibition (MG132) and immunoblot analysis of cell lysates for UBE2H. Actin serves as protein loading control. (H) Quantitation of UBE2H immunoblot signals from (G) normalized to Actin and relative to parental mock values. Graph shows results by mean ± SD of n = 3–5 experiments. (I) Cell lysates of K562 parental and MAEA-/-cl1-1 cells stably expressing Flag-MAEA wildtype (WT) or mutated Flag-MAEA-Y394A (Y394A) were analysed for UBE2H protein levels by immunoblotting. (J) Quantitation of immunoblots in (I) normalized to Actin and relative to parental values. Graph shows results by mean ± SD of n = 10–12 experiments. (K) Coomassie-stained SDS-PAGE gels presenting time course of in vitro autoubiquitylation assay with either ubiquitin or lysine-less ubiquitin (ubiquitin-K0) comparing UBE2H with UBE2H-C87A. Figure 6—source data 1.Original, uncropped scans of immunoblots. Figure 6—source data 2.Original, uncropped scans of immunoblots and Coomassie-stained SDS-PAGEs."
      }
    ]
  },
  {
    "id": "PMC9723204_multi",
    "image": [
      "images/PMC9723204-f1.png",
      "images/PMC9723204-f2.png",
      "images/PMC9723204-f3.png",
      "images/PMC9723204-f4.png",
      "images/PMC9723204-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Peroxisomal Fitness: A Potential Protective Mechanism of Fenofibrate against High Fat Diet-Induced Non-Alcoholic Fatty Liver Disease in Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Fenofibrate (FF) ameliorates high-fat diet (HFD)-induced liver dysfunction in wild-type (WT) mice. (A) Liver sections were immunofluorescence (IF) stained for adipose differentiation-related protein (ADFP; red) and 4´,6-diamidino-2-phenylindole dihydrochloride (DAPI) nuclear counterstaining (blue). Original magnification, 200×; scale bar, 100 μm. (A, B, C, D, E) Liver sections were also stained with anti-F4/80, 8-hydroxyguanine (8-oxo-dG), nitrotyrosine (NT), and 4-hydroxynonena (4-HNE) antibodies and were quantified. Original magnification, 100×; scale bar, 200 μm, n=4. (F) Interleukin 1β (Il1b), Il6, F4/80, and monocyte chemoattractant protein 1 (Mcp1) were measured by real-time polymerase chain reaction, and the results were normalized to the 18S rRNA levels. (G, H) The protein levels of phospho-nuclear factor kappa B (p-NF-κB) and total-NF-κB (t-NF-κB) were measured by Western blotting. (I) Plasma alanine aminotransferase (ALT) levels were measured using an enzyme-linked immunosorbent assay (ELISA) kit. Data are expressed as the mean±standard error of 6 mice/group. ND, normal diet. aP<0.05 vs. ND mice, bP<0.05 vs. HFD mice.\n\nFigure 2: Figure 2. Fenofibrate (FF) improves liver peroxisomal function in high-fat diet (HFD)-fed wild-type (WT) mice. (A) Peroxisome-related genes were analyzed by real-time polymerase chain reaction, and the results were normalized to 18S rRNA levels. (B, C, D) Liver sections were used for immunofluorescence (IF) staining of ATP binding cassette subfamily D member 3 (ABCD3; red), catalase (green), and 4´,6-diamidino-2-phenylindole dihydrochloride (DAPI) counterstaining (blue) and were quantified. Original magnification, 200×; scale bar, 200 μm. (E, F) Protein levels of acyl-CoA oxidase 1 (ACOX1) were measured by Western blotting, and the results were normalized to β-actin levels. (G) Peroxisomal fatty acid oxidation (FAO) was measured in liver tissue. Data are expressed as the mean±standard error of 6 mice/group. ND, normal diet; Pex, peroxisomal biogenesis factor; DPM, disintegration per minute. aP<0.05 vs. ND mice, bP<0.05 vs. HFD mice.\n\nFigure 3: Figure 3. Role of peroxisome proliferator-activated receptor α (PPARα) in maintaining liver homeostasis in Ppara-/- mice. (A, B, C) Liver morphology was detected by H&E staining. Original magnification, 100×; scale bar, 200 μm. Liver sections were immunofluorescence (IF) stained for adipose differentiation-related protein (ADFP; red) and 4´,6-diamidino-2-phenylindole dihydrochloride (DAPI) nuclear counterstaining (blue). Original magnification, 200×; scale bar, 200 μm. Liver sections were also stained with anti-4-hydroxynonena (4-HNE) and collagen 1 (COL1) antibody and the positive area were quantified. Original magnification, 100×; scale bar, 200 μm. (D, E, F) Interleukin 1β (Il1b), Il6, and F4/80 were measured by real-time polymerase chain reaction, and the results were normalized to the 18S rRNA levels. (G) Plasma alanine aminotransferase (ALT) levels were measured using an enzyme-linked immunosorbent assay (ELISA) kit. Data are expressed as the mean±standard error of 6 mice/group. ND, normal diet; WT, wild-type; HFD, high-fat diet; ADRP, adipose differentiation-related protein. aP<0.05 vs. WT mice with ND, bP<0.05 vs. Ppara-/- mice with ND, cP<0.05 vs. WT mice with HFD.\n\nFigure 4: Figure 4. Fenofibrate fails to maintain peroxisomal biogenesis in Ppara-/- mice. (A) The expression of peroxisome-related genes was decreased in Ppara-/- mice compared to wild-type (WT) mice. (B) Peroxisome-related genes in Ppara-/- mice were analyzed by real-time polymerase chain reaction, and the results were normalized to 18S rRNA levels. Data are expressed as the mean±standard error of 6 mice/group. PPAR, peroxisome proliferator-activated receptor; Pex, peroxisomal biogenesis factor; Abcd, ATP binding cassette subfamily D member; Acox1, acyl-CoA oxidase 1; ND, normal diet; HFD, high-fat diet; FF, fenofibrate. aP<0.05 vs. WT mice or Ppara-/- mice with ND.\n\nFigure 5: Figure 5. Fenofibrate fails to improve peroxisomal function in Ppara-/- mice. (A, B, C) Liver sections were immunofluorescence stained for ATP binding cassette subfamily D member 3 (ABCD3; red), catalase (green), and 4´,6-diamidino-2-phenylindole dihydrochloride (DAPI) nuclear counterstaining (blue) and intensities were quantified. Original magnification, 200×; scale bar, 200 μm. (D) Peroxisomal fatty acid oxidation (FAO) was measured in liver tissue. Data are expressed as the mean±standard error of 6 mice/group. PPAR, peroxisome proliferator-activated receptor; ND, normal diet; HFD, high-fat diet; FF, fenofibrate; DPM, disintegration per minute. aP<0.05 vs. Ppara-/- mice with ND."
      }
    ]
  },
  {
    "id": "PMC9729927_multi",
    "image": [
      "images/PMC9729927-f1.png",
      "images/PMC9729927-f2.png",
      "images/PMC9729927-f3.png",
      "images/PMC9729927-f4.png",
      "images/PMC9729927-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Exercise attenuates angiotensinⅡ-induced muscle atrophy by targeting PPARγ/miR-29b\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Exercise protects against AngⅡ-induced muscle atrophy. (A) The grip strength of mice in the Ang-infused control (n = 11) and run groups (n = 10) were evaluated. (B) Gastrocnemius was harvested from mice in the AngⅡ-treated control and run groups, and muscle weight was measured; scale bar = 1 cm, n = 11:10. (C) The cross-sectional area of myofiber of gastrocnemius in the AngⅡ-infused control and run groups was observed and measured by WGA staining, scale bar = 50 μm, n = 9:10. (D) The AngⅡ-induced muscle atrophy of the gastrocnemius in the control and run groups was evaluated by HE staining, scale bar = 50 μm, n = 7:7. (E) The expression of Atrogin-1 and MuRF-1 in gastrocnemius in the AngⅡ-infused control and run groups was detected by western blot; GAPDH was used as the loading control, n = 6:6. (F) Western blot was used to detect the phosphorylation of the AKT/FOXO3A/mTOR pathway proteins (AKT, FOXO3A, mTOR, p70S6K, and EIF-4EBP1) in the gastrocnemius in the AngⅡ-infused control and run groups; GAPDH was used as the loading control, n = 6:6. (G) The apoptosis of the gastrocnemius in the AngⅡ-infused control and run groups was detected by TUNEL staining. Blue indicates nuclear stained with DAPI, green indicates cells stained with TUNEL–FITC, and red indicates cell membrane stained with WGA conjugates, scale bar = 50 μm, n = 8:8. (H) The apoptosis-related proteins, including Bax, Bcl-2, cleaved caspase-3, and caspase-3, in the gastrocnemius in the AngⅡ-infused control and run groups were detected by western blot; GAPDH was used as the loading control, n = 6:6. Data are presented as mean ± SD, each dot on the column indicates an independent sample in this group, and the number of dots on the column indicates the total number of samples in this group. Differences between the AngⅡ-infused control and run groups were analyzed by an independent sample t test. * p < 0.05; ** p < 0.01; *** p < 0.001. AKT = protein kinase B; AngⅡ = angiotensin Ⅱ; Atogin-1 = F-box-only protein 32; BAX = Bcl-2-associated X; Bcl2 = B-cell lymphoma-2; Caspase-3 = cysteine-aspartic acid protease 3; DAPI = 4, 6-diamidino-2-phenylindole; EIF-4EBP1 = eukaryotic initiation factor 4E (EIF-4E) binding protein 1; FOXO3A = forkhead box O3A; GAPDH = glyceraldehyde-3-phosphate dehydrogenase; HE = Hematoxylin-eosin; mTOR = mammalian target of rapamycin; MuRF-1 = muscle specific RING-finger 1; ns = not significant; p70S6K = p70 ribosomal protein s6 kinase; p = phosphorylation; T = total; TUNEL = terminal deoxynucleotidyl transferase dUTP nick end labeling; TUNEL-FITC = TUNEL-fluorescein isothiocyanate; WGA = wheat germ agglutinin.\n\nFigure 2: Figure 2. Exercise upregulates PPARγ and downregulates miR-29b in AngⅡ-induced muscle atrophy. (A) The expression of PPARγ in the gastrocnemius in the AngⅡ-infused control (n = 6) and run groups (n = 6) was measured by western blot; GAPDH was used as the loading control. (B) The miR-29b expression level relative to 5S in the gastrocnemius in the AngⅡ-infused control (n = 11) and run groups (n = 10) were detected by RT-qPCR. Data are presented as mean ± SD. Differences between the AngⅡ-treated control and run groups were analyzed by an independent sample t test. * p < 0.05; ** p < 0.01. 5S = 5S ribosomal RNA; AngⅡ = angiotensin Ⅱ; GAPDH = glyceraldehyde-3-phosphate dehydrogenase; miR-29b = microRNA-29b; PPARγ = peroxisome proliferator-activated receptor gamma; RT-qPCR = reverse transcription quantitative polymerase chain reaction.\n\nFigure 3: Figure 3. The protective effect of exercise in AngⅡ-induced muscle atrophy was abolished by a PPARγ inhibitor. (A) The expression of PPARγ in the gastrocnemius in the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907), was measured by western blot; GAPDH was used as the loading control, n = 3:3:3:3. (B) The grip strength of mice in the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907), was measured, n = 12:12:8:12. (C) The gastrocnemius was harvested from the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907), and muscle weight was measured; scale bar = 1 cm, n = 12:12:8:12. (D) The cross-sectional area of myofiber of the gastrocnemius in the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907), was measured by WGA staining, scale bar = 50 μm, n = 8:8:8:8. (E) The AngⅡ-induced muscle atrophy of the gastrocnemius in the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907), was evaluated by HE staining, scale bar = 50 μm, n = 8:8:8:8. (F) The expression of Atrogin-1 and Murf-1 in the gastrocnemius in the AngⅡ-infused control and run groups, treated with or without PPARγ inhibitor (T0070907), was detected by western blot; GAPDH was used as the loading control, n = 3:3:3:3. (G) Western blot was used to detect the phosphorylation of the AKT/FOXO3A/mTOR pathway proteins (AKT, FOXO3A, mTOR, p70S6K, and EIF-4EBP1) in the gastrocnemius in the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907); GAPDH was used as the loading control, n = 3:3:3:3. (H) The apoptosis of the gastrocnemius in the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907), was observed by TUNEL staining: blue indicates nuclear stained with DAPI, green indicates cells stained with TUNEL-FITC, and red indicates cell membrane stained with WGA conjugates; scale bar = 50μm, n = 8:8:8:7. (I) Western blot was used to evaluate the apoptosis-related proteins, including Bax, Bcl-2, cleaved caspase-3, and caspase-3, in the gastrocnemius in the AngⅡ-infused control and run groups, treated with or without the PPARγ inhibitor (T0070907); GAPDH was used as the loading control, n = 3:3:3:3. Results are presented as mean ± SD, each dot on the column indicates an independent sample in this group, and the number of dots on the column indicates the total number of samples in this group. Two-way ANOVA followed by the Tukey post hoc test was used to analyze the data. * p < 0.05; ** p < 0.01; *** p < 0.001. AKT = protein kinase B; AngⅡ = angiotensin Ⅱ; ANOVA = analysis of variance; Atrogin-1 = F-box only protein 32; BAX = Bcl-2-associated X; Bcl2 = B-cell lymphoma-2; Caspase-3 = cysteine-aspartic acid protease 3; DAPI = 4, 6-diamidino-2-phenylindole; EIF-4EBP1 = eukaryotic initiation factor 4E (eIF-4E) binding protein 1; FOXO3A = Forkhead box O3A; GAPDH = glyceraldehyde-3-phosphate dehydrogenase; mTOR = mammalian target of rapamycin; MuRF-1 = muscle specific RING-finger 1; ns = not significant; p70S6K = p70 ribosomal protein S6 kinase; p = phosphorylation; PPARγ = peroxisome proliferator-activated receptor gamma; TUNEL = terminal deoxynucleotidyl transferase dUTP nick end labeling; T = total; TUNEL-FITC = TUNEL-fluorescein isothiocyanate; WGA = wheat germ agglutinin.\n\nFigure 4: Figure 4. The protective effect of exercise in AngⅡ-induced muscle atrophy was abolished by miR-29b overexpression. (A) The grip strength of mice in the AngⅡ-infused control and run groups, treated with control AAV8 (AAV8-control) or miR-29b overexpression AAV8 (AAV8-miR-29b) was measured, n = 10:11:11:11. (B) The gastrocnemius was harvested from mice of the AngⅡ-infused control and run groups, treated with control AAV8 or miR-29b overexpression AAV8, and muscle weight was measured; scale bar = 1 cm, n = 10:11:11:11. (C) The cross-section area of myofiber of the gastrocnemius in the AngⅡ-infused control and run groups, treated with control AAV8 or miR-29b overexpression AAV8, was measured by WGA staining; scale bar = 50 μm, n = 8:8:8:8. (D) The AngⅡ-induced muscle atrophy of the gastrocnemius in the control and run groups, treated with control AAV8 or miR-29b overexpression AAV8, was evaluated by HE staining; scale bar = 50 μm, n = 6:8:8:8. (E) The expression of Atrogin-1 and MuRF-1 in the gastrocnemius in the AngⅡ-infused control and run groups, treated with control AAV8 or miR-29b overexpression AAV8, was detected by western blot; GAPDH was used as the loading control, n = 6:6:6:6. (F) Western blot was used to detect the phosphorylation of AKT/FOXO3A/mTOR pathway proteins (AKT, FOXO3A, mTOR, P70S6K, and EIF-4EBP1) in the gastrocnemius in the AngⅡ-infused control and run groups, treated with control AAV8 or miR-29b overexpression AAV8, GAPDH was used as the loading control, n = 6:6:6:6. (G) The AngⅡ-induced apoptosis of the gastrocnemius in the control and run groups, treated with control AAV8 or miR-29b overexpression AAV8, was observed and measured by TUNEL staining; blue indicates nuclear stained with DAPI; green indicates cells stained with TUNEL-FITC; red indicates cell membrane stained with WGA conjugates); scale bar = 50 μm, n = 8:8:8:8. Results are presented as mean ± SD, each dot on the column indicates an independent sample in this group, and the number of dots on the column indicates the total number of samples in this group. Two-way ANOVA followed by the Tukey–post hoc text. AAV8 = adeno-associated virus serotype-8; AKT = protein kinase B; AngII = angiotensin II; ANOVA = analysis of variance; atogin-1 = F-box only protein 32; DAPI = 4, 6-diamidino-2-phenylindole; EIF-4EBP1 = eukaryotic initiation factor 4E (eIF-4E) binding protein 1; FOXO3A = Forkhead box O3A; GAPDH = glyceraldehyde-3-phosphate dehydrogenase; miR-29b = microRNA-29b; mTOR = mammalian target of rapamycin; MuRF-1 = muscle specific RING-finger 1; ns = not significant; p = phosphorylation; p70S6K = p70 ribosomal protein S6 Kinase; T = total; TUNEL = terminal deoxynucleotidyl transferase dUTP nick end labeling; TUNEL-FITC = TUNEL-fluorescein isothiocyanate; WGA = wheat germ agglutinin.\n\nFigure 5: Figure 5. The model of exercise-mediated protective function against AngⅡ-induced muscle atrophy. miR-29b = microRNA-29b; PPARγ = peroxisome proliferator-activated receptor gamma."
      }
    ]
  },
  {
    "id": "PMC9745560_multi",
    "image": [
      "images/PMC9745560-f1.png",
      "images/PMC9745560-f2.png",
      "images/PMC9745560-f3.png",
      "images/PMC9745560-f4.png",
      "images/PMC9745560-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Pyruvate dehydrogenase kinase 4 promotes ubiquitin–proteasome system‐dependent muscle atrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. PDK4 is upregulated in human and mouse models of muscle atrophy. (A) Immunoblot analysis of indicated proteins in gastrocnemius anterior (GA) muscles from obese, corticotrophin releasing hormone (CRH)‐Tg mice, and Type 2 diabetes (T2D) human myotube. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. (B) Immunoblot analysis of indicated proteins in human gluteus maximus muscles (GM) from a normal subject and steroid patients. (Right) Quantification represents the levels of the indicated protein normalized to ACTB. (C) Representative image of haematoxylin and eosin staining of myofibre cross section isolated from human gluteus maximus (hGM) muscles. A microscope with a ×20 objective was used to capture the images. (Right) the cross‐sectional diameter of human gluteus maximus (GM) muscles. (D) (GSE169571) RNA sequencing analysis of quadriceps muscles from saline and dexamethasone (DEX) treated mouse. (E) Immunoblot analysis of indicated proteins in VXY and FLAG‐tagged PDK4 overexpressing C2C12 myotubes stable cells. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. (F) Representative image of MYOG immunofluorescence in VXY and PDK4‐flag expressing C2C12 myotubes stable cells. (Right) Quantification represents the levels of the MYOG + ve cell (Mean ± SEM). (C, F) Scale bar 50 μM. (A, D and E) n = 3. (F) n = 4; number of image capture sites 20 from each group. (B, C) n = 6 human per group. **P < 0.01; ***P < 0.001; ****P < 0.0001. Unpaired t‐test was used for all analyses.\n\nFigure 2: Figure 2. Knockdown of PDK4 prevents glucocorticoids‐induced muscle atrophy in vitro. (A) Immunoblot analysis of indicated protein in C2C12 myotubes after being treated with dexamethasone (DEX) for 24 h with different concentrations of 0, 10, 50 and 100 μM. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. (B) qPCR analysis of indicated genes in C2C12 myotubes transfected with shPdk4 or shControl and treated with or without dexamethasone (DEX) (100 μM) for 24 h. (C) Immunoblot analysis of indicated proteins in C2C12 myotubes transfected with shPdk4 or shControl and treated with or without dexamethasone (DEX) (100 μM) for 24 h. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. (D, E) Representative image of MYOG and MYHC immunofluorescence of C2C12 myotubes transfected with shPdk4 or shControl and treated with or without dexamethasone (DEX) (100 μM) for 24 h. (Below) Quantification represents the levels of the MYOG + ve cell and (Below) fusion index. (F) The distribution of nuclei per myotubes were calculated at Day 6 differentiation. Yellow arrowheads number of nuclei in one myotube. Mean ± SEM. (D and E) Scale bar 50 μM. (A–C) n = 3. (D, E) n = 4; number of image capture sites 20 from each group. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. Dunnett's multiple comparisons test was used for the analysed panel (A). *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. Tukey's multiple comparisons test was used for the analysed panels (B–F). ROI, region of interest. Red * = nonspecific band.\n\nFigure 3: Figure 3. PDK4 mediates MYOG proteasomal degradation by ubiquitination. (A) Immunoblot analysis of indicated proteins in AD293T cells transfected with indicated constructs. After 48 h, cells were treated with or without MG132 10 μM for 6 h. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. (B) C2C12 myotubes were transfected with the indicated Adenovirus (Ad‐Pdk4‐flag) and (Ad‐GFP) in the presence of MG132 10 μM for 6 h. Co‐immunoprecipitation (co‐IP) using MYOG antibody and immunoblot analysis of indicated proteins. (Right) Quantification represents the levels of the poly‐ub MYOG protein. (C) AD293T cells were transfected with indicated constructs; after 48 h, cells were treated with or without MG132 10 μM for 6 h. Co‐immunoprecipitation (co‐IP) using HA antibody and immunoblot analysis of indicated proteins. (D) Immunoblot analysis of indicated proteins in C2C12 myotubes transfected with control or Mafbx siRNA in the presence or absence of dexamethasone (DEX) 100 μM for 24 h. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. Mean ± SEM. (A, D) n = 3. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. Tukey's multiple comparisons test was used for the analysed panel (A) and unpaired t‐test was used for the analysed panel (B). Red * = nonspecific band.\n\nFigure 4: Figure 4. Identification of MYOG as a novel substrate of PDK4. (A) AD293T cells were transfected with indicated constructs. After 48 h, cells were treated with or without MG132 10 μM for 6 h. Co‐immunoprecipitation (co‐IP) using HA antibody and immunoblot analysis of indicated proteins. (B) AD293T cells were transfected with indicated constructs and performed in situ proximity ligation assay (PLA). (C) In vitro kinase assay. Using recombinant GST‐MYOG and PDK4 protein in the presence of ATP and the phosphorylation was detected by indicated antibody. (D) AD293T cells were transfected with indicated constructs for 48 h. Co‐immunoprecipitation (co‐IP) using HA antibody and immunoblot analysis of indicated proteins. (E) AD293T cells were transfected with indicated constructs. After 48 h, transfected cells were treated with cycloheximide (CHX) 100 μM and incubated cells for indicated time before harvest. Immunoblot analysis of indicated proteins. (Below) Quantification represents the levels of the indicated protein normalized to HSP90. (F) C2C12 myotubes were infected with adenovirus expressing MYOG (AdMYOG) and mutant MYOGᴬᴬ (AdMYOGᴬᴬ) in the presence or absence of dexamethasone (DEX) (100 μM) for 24 h, treated MG132 10 μM for 6 h. Co‐immunoprecipitation (co‐IP) using HA antibody and immunoblot analysis of indicated proteins. (Below) Quantification represents the levels of the poly‐ub MYOG protein. Mean ± SEM. (B) Scale bar 50 μM. (E) n = 3. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. Unpaired t‐test was used for the analysed panels (E, F). ROI, region of interest.\n\nFigure 5: Figure 5. Ectopic overexpression of MYOG mutant protects against glucocorticoids‐induced muscle atrophy in human myotube and mice. (A) Immunoblots analysis of indicated proteins in human myotubes infected with adenovirus expressing mutant MYOGᴬᴬ (Ad MYOGᴬᴬ) or GFP (AdGFP). Myotubes were culture for 24 h in the presence or absence of dexamethasone (DEX) 100 μM. (Below) Quantification represents the levels of the indicated protein normalized to HSP90. (B) Representative image of MYHC immunofluorescence in human myotubes infected with adenovirus expressing mutant MYOGᴬᴬ (Ad MYOGᴬᴬ) or GFP (AdGFP) in the presence or absence of dexamethasone (DEX) 100 μM for 24 h. (Below) Quantification represents the levels of fusion index and the distribution of nuclei per myotube were calculated at Day 6 differentiation. (C) The distribution of nuclei per myotubes were calculated at Day 6 differentiation. Yellow arrowheads indicate the number of nuclei in one myotube. (D) Immunoblots analysis of indicated proteins in gastrocnemius anterior (GA) muscle. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. (E) The ratio of the weight of gastrocnemius anterior (GA) to total body weight. (F) Representative image of haematoxylin and eosin staining of myofibre cross section from AdGFP or AdMYOGᴬᴬ injected in gastrocnemius anterior muscles from dexamethasone (DEX)‐treated mice. A microscope with a ×20 objective was used to capture the images. (Right) the cross‐sectional diameter of gastrocnemius anterior (GA) muscle. Mean ± SEM. (B) Scale bar 50 μM. (F) n = 5 for each group. (A, E) n = 3. (B, C) n = 4; number of image capture sites 20 from each group. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. Unpaired t‐test was used for analyzed for panel (E–F). *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. Tukey's multiple comparisons test was used for analysed panels (A–C). ROI = region of interest."
      }
    ]
  },
  {
    "id": "PMC9745560_multi_2",
    "image": [
      "images/PMC9745560-f6.png",
      "images/PMC9745560-f7.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Pyruvate dehydrogenase kinase 4 promotes ubiquitin–proteasome system‐dependent muscle atrophy\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. PDK4 ablation prevents muscle loss in glucocorticoids ‐induced muscle atrophy in mice. (A) Experimental scheme for dexamethasone‐induced muscle atrophy model in WT and Pdk4KO mice. (B) Immunoblots analysis of indicated proteins using gastrocnemius anterior (GA) muscle. (Right) Quantification represents the levels of the indicated protein normalized to HSP90. (C) Total body weight. (D) Grip strength test. (E) The ratio of gastrocnemius anterior (GA) muscle weight to body weight. (F) Representative haematoxylin and eosin staining of myofibre cross‐section of Gast. A microscope with a ×20 objective was used to capture the images. (Right) the cross‐sectional diameter of gastrocnemius anterior (GA) muscle. Mean ± SEM. (F) Scale bar 50 μM. (B) n = 3 for each group. (C–F) n = 6 for each group. & P < 0.05; && P < 0.01; &&& P < 0.001; &&&& P < 0.0001, Pdk4KO + DEX vs WT + DEX. # P < 0.05; ## P < 0.01; ### P < 0.001; #### P < 0.0001, Pdk4KO versus WT + DEX. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001, WT versus WT + DEX. (Body weight and grip strength). *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. Tukey's multiple comparisons test was used for the analysed panels (B, E, and F). ROI, region of interest.\n\nFigure 7: Figure 7. Proposed model for PDK4‐induced muscle atrophy."
      }
    ]
  },
  {
    "id": "PMC9788354_multi",
    "image": [
      "images/PMC9788354-f1.png",
      "images/PMC9788354-f2.png",
      "images/PMC9788354-f3.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Structure and function of the peroxisomal ubiquitin ligase complex\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. The scheme shows different steps during peroxisomal matrix protein import by the receptor PEX5. In step 1, the C-terminal SKL sequence of cargo is recognized and bound by the TPR domain of PEX5. In step 2, the complex of cargo and PEX5 binds to the docking complex in the peroxisomal membrane. In step 3, the PEX5-cargo complex moves all the way into the lumen. In step 4, the N terminus of PEX5 inserts into the pore of the ubiquitin ligase complex and a ubiquitin (Ub) molecule is attached. In step 5, monoubiquitinated PEX5 is pulled into the cytosol by the ATPase complex, resulting in the unfolding of PEX5 and cargo release. In step 6, ubiquitin is removed from monoubiquitinated PEX5 by deubiquitinating enzymes (DUBs).\n\nFigure 2: Figure 2. (A) Cartoon model of the structure of the ubiquitin ligase complex from T. thermophilus, determined by cryo-EM. Shown is a side view, with the three components PEX2, PEX10, and PEX12 in different colors. The ligase complex has two distinct domains: a membrane-embedded domain (TMD) and a cytosolic domain (CytD) formed by the three RING fingers (RFs). CytD is also referred to as the RING finger tower. (B) View of the ligase complex from the lumen. Shown are cartoon models of the components together with semi-transparent space-filling models. Note the open pore. The broken line indicates a short luminal loop that is invisible in the density map, but would partially obstruct the pore.\n\nFigure 3: Figure 3. In the normal receptor recycling pathway (left), the receptor PEX5 inserts an N-terminal segment into the ligase pore, positioning a conserved cysteine for monoubiquitination by the RING finger of PEX2 (RF2). A region of PEX5 is in the background behind PEX12 and is indicated by a broken line. In the RADAR pathway (right), which is activated when normal recycling is compromised, the N-terminal segment of PEX5 moves sideways to position a lysine residue for polyubiquitination by RF10. A region of PEX5 is in the background behind PEX10 and is indicated by a broken line."
      }
    ]
  },
  {
    "id": "PMC9854540_multi",
    "image": [
      "images/PMC9854540-f1.png",
      "images/PMC9854540-f2.png",
      "images/PMC9854540-f3.png",
      "images/PMC9854540-f4.png",
      "images/PMC9854540-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Two Argan Oil Phytosterols, Schottenol and Spinasterol, Attenuate Oxidative Stress and Restore LPS-Dysregulated Peroxisomal Functions in Acox1−/− and Wild-Type BV-2 Microglial Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Effects of Schot and Spina on the cell proliferation and viability of the Wt and the Acox1−/− BV-2 microglial cells for 24 (A) or 48 (B) hours. Cell proliferation and viability were assessed by the MTT test. Cells were treated with Schot or Spina at a range of concentrations from 1 to 20 µM. 7-ketocholesterol (7-KC) was used at 20 µM as a positive control. All compounds were tested for 24 or 48 h. All values are presented as means ± SD of two independent experiments performed in triplicate. Values were normalized to the control. Statistical significance compared to control (*** p ≤ 0.001, ** p ≤ 0.01, * p ≤ 0.05) was determined using one-way ANOVA followed by Tukey’s test.\n\nFigure 2: Figure 2. Effects of Schot and Spina on ROS production induced by LPS in the Wt (A) and Acox1−/− (B) BV-2 microglial cells assessed by the H2DCFDA (5 µM) dye test. Cells were incubated for 7 h with Schot or Spina (1 or 2.5 µM) in the absence or presence of LPS (1 µg/mL). All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increase in mean signal indicated as ### p ≤ 0.01 and # p ≤ 0.05 compared to LPS and $$$ p ≤ 0.001 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons.\n\nFigure 3: Figure 3. Effect of Schot and Spina on ROS production induced by LPS in the Wt (A) and Acox1−/− (B) BV-2 microglial cells assessed by the DHE (5 µM) dye test. Cells were incubated for 7 h with Schot or Spina (1 or 2.5 µM) in the presence or absence of LPS (1 µg/mL). All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increase in mean signal indicated as ### p ≤ 0.01, # p ≤ 0.05 compared to LPS and $$ p ≤ 0.01 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons.\n\nFigure 4: Figure 4. Effect of Schot and Spina on the NO production induced by LPS in the culture media of the Wt (A) and Acox1−/− (B) BV-2 microglial cells assessed by the Griess test. Cells were incubated for 24h with Schot or Spina (1 or 2.5 µM) in the absence or the presence of LPS (1 µg/mL). All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increase in mean signal indicated as ### p ≤ 0.01 compared to LPS and $$$ p ≤ 0.001 and $$ p ≤ 0.01 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons.\n\nFigure 5: Figure 5. Effect of Schot and Spina on catalase activity in the Wt (A) and Acox1−/− (B) BV-2 microglial cells, and on ACOX1 activity (C) in Wt BV-2 microglial cells. Cells were incubated for 24 h with Schot or Spina (1 or 2.5 µM) in the absence or the presence of LPS (1 µg/mL). All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increased mean signal indicated as ### p ≤ 0.01 and # p ≤ 0.05 compared to LPS and $$$ p ≤ 0.001 and $$ p ≤ 0.01 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons."
      }
    ]
  },
  {
    "id": "PMC9854540_multi_2",
    "image": [
      "images/PMC9854540-f6.png",
      "images/PMC9854540-f7.png",
      "images/PMC9854540-f8.png",
      "images/PMC9854540-f9.png",
      "images/PMC9854540-f10.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Two Argan Oil Phytosterols, Schottenol and Spinasterol, Attenuate Oxidative Stress and Restore LPS-Dysregulated Peroxisomal Functions in Acox1−/− and Wild-Type BV-2 Microglial Cells\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Immunoblotting assay showing effects of Schot and Spina on the expression of the peroxisomal proteins ACOX1, CAT, ABCD1, and ABCD2 and the inflammatory marker iNOS in Wt (A) and Acox1−/− (B) BV-2 microglial cells. Cells were incubated for 24 h with Schot or Spina (1 or 2.5 µM) in the absence or presence of LPS (1 µg/mL). Cell homogenates were analyzed by PAGE-SDS electrophoresis and subjected to immunoblotting. Band intensities were analyzed by densitometry and standardized to β-actin expression level. Table values represent standardized densitometric analysis obtained after the signal intensity quantification of different proteins.\n\nFigure 7: Figure 7. Effect of Schot and Spina treatment on the gene expression of Cat (A,B) and Acox1 (C) in Wt (A,C) and Acox1−/− (B) BV-2 microglial cells. Cells were incubated for 24 h with Schot or Spina (1 or 2.5 µM) in the absence or presence of LPS (1 µg/mL). Total RNA was isolated from BV-2 cells, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increased mean indicated as ** p ≤ 0.01 compared to control; ### p ≤ 0.001 and ## p ≤ 0.01 compared to LPS and $$$ p ≤ 0.001 and $$ p ≤ 0.01 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons.\n\nFigure 8: Figure 8. Effect of Schot or Spina treatment on the gene expression of Abcd1 (A,C) and Abcd2 (B,D) in Wt (A,B) and Acox1−/− (C,D) BV-2 microglial cells. Cells were incubated for 24h with Schot or Spina (1 or 2.5 µM) in the absence or presence of LPS (1 µg/mL). Total RNA was isolated from BV-2 cells, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increased mean signal indicated as *** p ≤ 0.001 compared to control; ## p ≤ 0.01 and # p ≤ 0.05 compared to LPS; and $$$ p ≤ 0.001 and $$ p ≤ 0.01 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons.\n\nFigure 9: Figure 9. Effect of Schot and Spina treatments on the gene expression of the proinflammatory markers Tnf-α (A,C) and iNos (B,D) in Wt (A,B) and Acox1−/− (C,D) BV-2 microglial cells. Cells were incubated for 24 h with Schot or Spina (1 or 2.5 µM) in the absence or presence of LPS (1 µg/mL). Total RNA was isolated from BV-2 cells, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increased mean signal indicated as ** p ≤ 0.01 compared to control; ### p ≤ 0.01 and # p ≤ 0.05 compared to LPS; $$ p ≤ 0.01 and $$$ p ≤ 0.001 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons.\n\nFigure 10: Figure 10. Effect of Schot and Spina treatment on the gene expression of the proinflammatory marker Il-b (A,B) and the anti-inflammatory marker Il-4 (C,D) in the Wt (A,C) and Acox1−/− (B,D) BV-2 microglial cells. Cells were incubated for 24 h with Schot or Spina (1 or 2.5 µM) in the absence or presence of LPS (1 µg/mL). Total RNA was isolated from BV- 2 cells, and then the expression level of genes of interest was quantified by real-time RT-qPCR. All values are presented as means ± SD of two independent experiments performed in triplicate, with the statistical significance of the increased mean signal indicated as *** p ≤ 0.001 and * p ≤ 0.05 compared to control; ### p ≤ 0.01 and compared to LPS; and $$$ p ≤ 0.001 and $ p ≤ 0.05 compared to the different treatments with or without LPS administration. Statistical significance was determined using two-way ANOVA followed by Tukey’s test for multiple comparisons."
      }
    ]
  },
  {
    "id": "PMC9855061_multi",
    "image": [
      "images/PMC9855061-f1.png",
      "images/PMC9855061-f2.png",
      "images/PMC9855061-f3.png",
      "images/PMC9855061-f4.png",
      "images/PMC9855061-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Bavachin and Corylifol A Improve Muscle Atrophy by Enhancing Mitochondria Quality Control in Type 2 Diabetic Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Bavachin (10 mg/kg) or corylifol A (10 mg/kg) was orally administered for 12 d, starting two days prior to DEX administration. (A) Body weight changes in mice and (B) total muscle weight. (C) Muscle weights of the gastrocnemius (GA), soleus (SOL), tibialis anterior (TA), extensor digitorum longus (EDL), and quadriceps femoris (QD) muscles. (D) Grip strength. (E) Representative images of the cross-sectional area (CSA) in the GA muscle tissue at 200× magnification. Average CSA of muscle fibers. (F) CSA distribution of the muscle fibers. CSA data were measured using the ImageJ software. Protein expression levels in GA muscles were determined via western blotting. (G) Representative images of the atrophic muscle factors. (H) Protein expression levels of the atrophic muscle factors. All data are represented as the mean ± standard error of the mean (S.E.M)., n = 6/group; * p < 0.05, ** p < 0.01, *** p < 0.001; nonparametric analysis of variance, followed by Kruskal-Wallis test.\n\nFigure 2: Figure 2. Bavachin and corylifol A increase the muscle strength in diabetic (db/db) mice. Twelve week old male db/db mice were administered bavachin (10 mg/kg) or corylifol A (10 mg/kg) for 40 d. (A) Body weight changes in mice, and (B) non-fasting blood glucose levels. (C) Total muscle weight. (D) Grip strength. (E) Representative images of CSA of GA muscle tissue at 200× magnification. (F) Average CSA of muscle fibers. (G) CSA distribution of muscle fibers. CSA data were measured using the ImageJ software. All data are represented as the mean ± S.E.M., n = 6–7/group; * p < 0.05, ** p < 0.01, *** p < 0.001; nonparametric analysis of variance, followed by Kruskal-Wallis test.\n\nFigure 3: Figure 3. Bavachin and corylifol A suppress pro-inflammatory cytokine expression levels in db/db mice. Twelve week old male db/db mice were administered bavachin (10 mg/kg) or corylifol A (10 mg/kg) for 40 d. Protein expression levels in the GA muscle were determined using western blotting. (A) Representative images of western blotting. (B) Protein expression levels of inflammatory cytokines. All data are represented as the mean ± S.E.M., n = 6/group; ** p < 0.01, *** p < 0.001; nonparametric analysis of variance, followed by Kruskal-Wallis test.\n\nFigure 4: Figure 4. Bavachin and corylifol A decrease muscle atrophy in db/db mice. Twelve week old male db/db mice were administered bavachin (10 mg/kg) or corylifol A (10 mg/kg) for 40 d. Protein expression levels in GA muscles were measured using western blotting. (A) Representative images of the atrophic muscle factors. (B) Protein expression levels of the atrophic muscle factors. (C) Representative images of the AKT signaling pathway. (D) Protein expression levels in the AKT signaling pathway. All data are represented as the mean ± S.E.M., n = 6/group; * p < 0.05, ** p < 0.01, *** p < 0.001; nonparametric analysis of variance, followed by Kruskal-Wallis test.\n\nFigure 5: Figure 5. Bavachin and corylifol A improve the organization of muscle fibers and attenuate mitochondrial damage in skeletal muscles of db/db mice. Twelve week old male db/db mice were administered bavachin (10 mg/kg) or corylifol A (10 mg/kg) for 40 d. Transmission electron microscopy (TEM) of the GA muscle. (A,E) Control + vehicle, (B,F) db/db + vehicle, (C,G) db/db + bavachin, and (D,H) db/db + corylifol A groups. Red arrowheads indicate mitochondria. Images (A–D) were captured at 8000× magnification, and (E,F) at 20,000× magnification."
      }
    ]
  },
  {
    "id": "PMC9855061_multi_2",
    "image": [
      "images/PMC9855061-f6.png",
      "images/PMC9855061-f7.png",
      "images/PMC9855061-f8.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\nThese figures are from the study \"Bavachin and Corylifol A Improve Muscle Atrophy by Enhancing Mitochondria Quality Control in Type 2 Diabetic Mice\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 6: Figure 6. Bavachin and corylifol A induce the conversion of fast muscle fibers to slow muscle fibers in db/db mice. Twelve week old male db/db mice were administered bavachin (10 mg/kg) or corylifol A (10 mg/kg) for 40 d. (A) Representative images of MyHC immunofluorescence in GA muscle. Images were triple labeled for MyHC 1 (blue, type 1 fibers), MyHC 2A (green, type 2A fibers), and MyHC 2B (red, type 2B fibers). Scale bar indicates 50 µm. Images were captured at 600× magnification. (B) Proportion of MyHC isoform-specific fibers. Protein expression levels in the GA muscles were determined via western blotting. (C) Protein expression levels of MyHC 1, MyHC 2B, troponin I fast skeletal muscle (TnI-FS) and troponin I slow skeletal muscle (TnI-SS). All data are represented as the mean ± S.E.M., n = 6/group; * p < 0.05, ** p < 0.01, *** p < 0.001; nonparametric analysis of variance, followed by Kruskal-Wallis test.\n\nFigure 7: Figure 7. Bavachin and corylifol A induce mitochondrial dynamics in the skeletal muscle via the AMP-activated protein kinase (AMPK) signaling pathway. Twelve week old male db/db mice were administered bavachin (10 mg/kg) or corylifol A (10 mg/kg) for 40 d. Protein expression levels in the GA muscle were measured via western blotting. (A) Representative images of mitochondrial biogenesis. (B) Protein expression levels of mitochondrial biogenesis. (C) Representative images of fusion and fission factors. (D) Protein expression levels of fusion and fission factors. All data are represented as the mean ± S.E.M., n = 6/group; * p < 0.05, ** p < 0.01, *** p < 0.001; nonparametric analysis of variance, followed by Kruskal-Wallis test.\n\nFigure 8: Figure 8. Bavachin and corylifol A promote mitophagy and improve the mitochondrial homeostasis. Twelve week old male db/db mice were administered bavachin (10 mg/kg) or corylifol A (10 mg/kg/day) for 40 d. Protein expression levels in the GA muscle were measured via western blotting. (A) Representative images of mitophagy factors. (B) Protein expression levels of mitophagy factors. (C) Dihydroethidium (DHE) staining. Images were captured at 600× magnification. (D) Protein expression levels of 4-hydroxynonenal (4HNE). All data are represented as the mean ± S.E.M., n = 6/group; * p < 0.05, ** p < 0.01, *** p < 0.001; nonparametric analysis of variance, followed by Kruskal-Wallis test."
      }
    ]
  },
  {
    "id": "PMC9869129_multi",
    "image": [
      "images/PMC9869129-f1.png",
      "images/PMC9869129-f2.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\nThese figures are from the study \"Newborn screening for X-linked adrenoleukodystrophy in Italy: Diagnostic algorithm and disease monitoring\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Diagnostic process of X-ALD newborn screening.\n\nFigure 2: Figure 2. Timing of monitoring of pre-symptomatic ABCD1-mutated males subjects."
      }
    ]
  },
  {
    "id": "PMC9898238_multi",
    "image": [
      "images/PMC9898238-f1.png",
      "images/PMC9898238-f2.png",
      "images/PMC9898238-f3.png",
      "images/PMC9898238-f4.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Lysine 222 in PPAR γ1 functions as the key site of MuRF2-mediated ubiquitination modification\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Distribution of the candidate sites in PPAR γ1 protein. The spatial model of PPAR γ1 molecule was derived by PyMOL software (version 2.4.0 openvr; DeLano Scientific, San Carlos, CA, USA; https://pymol.org/2/). The filtered ubiquitination sites K68, K222, K228, and K242 and K356 were showed as red spheres.\n\nFigure 2: Figure 2. Identification of ubiquitination site(s) in vitro by GST-pulldown assay (original blots are presented in Supplementary Figs. S1–S3). (a) The upper: the over-expression plasmid of PPAR γ1 or the mutant of PPAR γ1 (K68R, K222R, K228R, K242R, K356R) was transfected in HEK293T cells respectively. The PPAR γ1 proteins levels were verified by immunoblot, and no endogenous PPAR γ1 was observed in 293T cells. The lower: immunoblot analysis of the purification efficiency of PPAR γ1 protein. Compared to the negative and positive controls, no GAPDH protein was detected in the total protein derived from the PPAR γ1 and mutants transfected groups, indicating that purified proteins of PPAR γ1 and the mutants were obtained. (b) The upper: MuRF2 auto-ubiquitination was demonstrated by immunoblot of MuRF2 (lane 5 and lane 6). The lower: MuRF2’s ability to ubiquitinate PPAR γ1. The smeared PPAR γ1 was observed obviously in the full reaction (the far right lane 6). (c) Residue K68 showed the remote possibility of being the ubiquitination site. Except the PPAR γ1 K68R, all the protein stability of the mutant PPAR γ1 K222, K228, and K242 and K356 were weakened in the presence of MuRF2 compared to that of the PPAR γ1 protein, indicating the dispensability of lysine site K68 in MuRF2 mediated PPAR γ1 ubiquitination modification. Ub, ubiquitin; E1, ubiquitin activating enzyme; E2, ubiquitin conjugating enzyme.\n\nFigure 3: Figure 3. Identification of ubiquitination site(s) in vivo by transfection study (original blots are presented in Supplementary Figs. S3–S5). (a) MuRF2 interacted with PPAR γ1 and modified PPAR γ1 via poly-ubiquitination. HEK 293T cells were co-transfected with plasmids His-MuRF2, HA-Ub and PPAR γ1. Cells were treated with proteasome inhibitor MG132 for 6 h before harvest a, and followed by immunoprecipitation and immunoblot analyses. The immunoprecipitation studies identified the interaction between MuRF2 and PPAR γ1 proteins, and the immunoblots of PPAR γ1 indicated that MuRF2 modified PPAR γ1 protein by poly-ubiquitination (the right lanes of the middle and the bottom). (b) Lysine site 222 exhibited the essential for MuRF2 ubiquitinating PPAR γ1. HEK 293T cells were co-transfected with plasmid of His-MuRF2, HA-Ub and PPAR γ1 wild type or mutant K68R, K222R, K228R, K242R and K356R respectively. The immunoblots of PPAR γ1 demonstrated the ubiquitination level of K222R mutant was significantly reduced (the middle and the bottom of the left figure), indicating residue K222 on PPAR γ1 is the target for MuRF2. (c) Compared to the ubiquitination level of the wildtype PPAR γ1, the level of the mutant K222R was decreased significantly (p < 0.05). No difference was observed between the wildtype and the other mutants.\n\nFigure 4: Figure 4. Confirmation of K222 is the key site of MuRF2 ubiquitination modification PPAR γ1 (original blot is presented in Supplementary Fig. S6). (a) Function of K222 in PPAR γ1 stability. HEK 293T cells were co-transfected with plasmids His-MuRF2, HA-Ub and PPAR γ1 or K222R mutant. The cells were treated with CHX (final concentration 60 μg/mL) for 3 h and 6 h respectively before harvest. The proteins turnover of PPAR γ1 and PPAR γ1 K222R were determined by immunoblot. Signals of the PPAR γ1 from immunoblots were analyzed using the Image J (National Institutes of Health) and normalized by GAPDH signal. (b) Percentage of the remaining PPAR γ1 and K222R proteins. Compared to the significantly weakened PPAR γ1 protein, the remaining K222R proteins remained unchanged after 3 h and 6 h of CHX administration (p < 0.05). (c) HEK 293 T cells were transfected with plasmids of His-MuRF2, HA-Ub and PPAR γ1 or the K222R mutant. Samples were subjected to quantitative-PCR analysis of cardiac genes ACOX1, PLIN2 and CPT1b. Data were presented as mean ± SD. n = 3. #p < 0.05 by two-tailed Student’s t-test. (d) The 3D spatial structure of PPAR γ1 ligating ubiquitin derived by PyMOL software (version 2.4.0 openvr; DeLano Scientific, San Carlos, CA, USA; https://pymol.org/2/). At position 76 of glycine carboxyl, ubiquitin ligates PPAR γ1 at lysine 222 site. The green is ubiquitin and the blue is PPAR γ1."
      }
    ]
  },
  {
    "id": "PMC9944889_multi",
    "image": [
      "images/PMC9944889-f1.png",
      "images/PMC9944889-f2.png",
      "images/PMC9944889-f3.png",
      "images/PMC9944889-f4.png",
      "images/PMC9944889-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"Structural insights into substrate recognition and translocation of human peroxisomal ABC transporter ALDP\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. ATPase activity of human ABCD1 stimulated by substrates. a ATPase activity of the full-length wild-type, E630Q mutant, and the N-terminal truncated proteins purified in GDN. The full-length wild-type protein showed a KM of 279 ± 18 µM for ATP and a maximal hydrolysis activity of 18 nmol/mg/min. b ATPase activity of the truncation mutant devoid of N-terminal 54 residues in the presence of Acyl-CoA at different concentrations. c ATPase activity of the truncation mutant devoid of N-terminal 54 residues in the presence of different concentrations of C26:0. d Normalized ATPase activity of E630Q mutant protein. The activity of the full-length wild-type protein, truncation mutant devoid of N-terminal 54 residues, and truncation mutant devoid of N-terminal 54 residues and C-terminal 60 residues was simulated. Maximal hydrolysis activity was selected to calculate the stimulated fold. e Stimulated ATPase activity of the truncation mutant devoid of N-terminal 54 residues in the presence of C26:0, C26:0-CoA, and acetyl-CoA. The maximal hydrolysis activity was selected to calculate the stimulate fold. f ATPase activity of ABCD1 mutants, in which the residues locating in the substrate-binding sites were mutated to alanine. g ATPase activity of ABCD1 mutants in the presence of C26:0-CoA. h ATPase activity of ABCD1 truncation mutants. The reported errors represent standard deviation. ns no significance, ✱✱✱✱P < 0.0001, ✱✱✱P < 0.001, ✱✱P < 0.01, and ✱P < 0.05\n\nFigure 2: Figure 2. Overall structure of ABCD1 in complex with C26:0 fatty acid. a, b Cartoon representation of the side view of the overall structure of ABCD1. The two subunits are colored in cyan and yellow. c, d TMD of ABCD1 viewed from peroxisomal lumen and cytosol. e, f Domain structures of ABCD1\n\nFigure 3: Figure 3. Inward-facing structure of ABCD1 with a cytosolic vestibule that houses the substrate-binding site. a, b Surface representation of ABCD1 showing that C26:0 binds to a vestibule that penetrates half-way into the lipid bilayer. c, d Electron density map of C26:0 substrate and zoomed-in view of the substrate in the same orientation as b, respectively. e, f Overall and slice views of ABCD1-E630Q in complex with C26:0-CoA as surface representation, respectively. g, h EM density of parts of C26:0-CoA and zoomed-in view of the CoA binding site, respectively. The EM density maps in c and g are displayed at the same sigma level (5σ)\n\nFigure 4: Figure 4. ATP-bound inward-facing and outward-facing structures of ABCD1. a, c, e, d Cartoon structures representing ABCD1 in complex with ATP in outward-facing state. a, e View from the peroxisome lumen side and cytosol; c side view. g Zoomed-in view of the ATP-binding site. b, d, f, h Cartoon representations of ABCD1 in the complex of ATP in inward-facing state, viewed from a similar orientation as the outward-facing structure on the left\n\nFigure 5: Figure 5. Three inward-facing states and one outward-facing state of ABCD1. a, b Surface representation of ABCD1 in inward-facing state 1, characterized by the presence of C-terminal coil. c Structure of ABCD1 in inward-facing state 2, with a shortened distance of two NBDs compared with that in state 1. d ABCD1 with narrower vestibule opening to the cytosol when captured in inward-facing state 3. e ATP stapling the two NBDs and the outer segments of the TMD pealed open to the peroxisome lumen. f–j Measurement of the distance between the two NBDs based on the different states of ABCD1 above"
      }
    ]
  },
  {
    "id": "PMC9950183_multi",
    "image": [
      "images/PMC9950183-f1.png",
      "images/PMC9950183-f2.png",
      "images/PMC9950183-f3.png",
      "images/PMC9950183-f4.png",
      "images/PMC9950183-f5.png"
    ],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\n<image>\n<image>\n<image>\n<image>\nThese figures are from the study \"CLEC16A interacts with retromer and TRIM27, and its loss impairs endosomal trafficking and neurodevelopment\". Summarise what they collectively show."
      },
      {
        "from": "gpt",
        "value": "Figure 1: Figure 1. Clinical features and brain MRI of individuals with CLEC16A variants. a, b Pedigrees of the two families with CLEC16A variants. Black boxes represent affected individuals. + / − indicate heterozygous individual, + / + indicates homozygous individual, − / − indicates homozygous WT. Subjects II-1/2 from family 1 presented with similar clinical features as observed in individual II-3 but were not tested for the CLEC16A variant, as there was no DNA available for these siblings. Heterozygosity was confirmed for both parents. c, d Facial features of subject II-1 from family 2. e–j Brain MRI of the affected individual of family 2 made at 3 months of age with midsagittal T1-weighted images (e), and axial T1-weighted images\n\nFigure 2: Figure 2. Subcellular localization of CLEC16A-WT and -Δ19. a Immunocytochemistry assessing co-localization of transiently expressed pEGFP-CLEC16A-WT (green) with the late endosomal/lysosomal marker LAMP2 (red). Nuclei were counterstained with DAPI. b Partial zoom of a, showing 3.5 × enlargement. c, d Immunocytochemistry assessing the localization of transiently expressed pEGFP-CLEC16A-WT (green, upper panel) and pEGFP-CLEC16A-Δ19 (lower panel) in HEK293T cells. Cells were stained for the early endosomal marker EEA1 (red). Nuclei were counterstained with DAPI. Overview images were made with confocal microscopy (c) and high-resolution images were with 3D-SIM super-resolution microscopy (d). Two representative images of pEGFP-CLEC16A-WT made with 3D-SIM super-resolution microscopy are shown in d. Scale bars represent 5 µm (a, c) and 1 µm (d)\n\nFigure 3: Figure 3. CLEC16A interactome and endosomal F-actin levels. a HEK293T cells were transfected with pEGFP-CLEC16A-WT, pEGFP-CLEC16A-Δ19, or negative control GFP-C1 for 48 h, followed by immunoprecipitation with anti-rabbit GFP antibodies and LC–MS/MS (n = 2 for all groups). Proteins interacting with pEGFP-CLEC16A-WT or pEGFP-CLEC16A-Δ19 but not with GFP-C1 were filtered based on their Andromeda score (> 40). Panel a shows the most significant network, which is related to the retromer complex. The colors of the lines indicate the stringency of the interaction. Light blue: from curated databases, pink: experimentally determined, green: gene neighborhood, red: gene fusions, dark blue: gene co-occurrence, yellow: text miming, black: co-expression, purple: protein homology. b The interaction between pEGFP-CLEC16A-WT/Δ19 was confirmed after reciprocal IP with anti-TRIM antibodies 48 h after overexpression with pEGFP-CLEC16A-WT, pEGFP-CLEC16A-Δ19, or GFP. All plasmids were revealed on immunoblot with anti-GFP antibodies. c The binding of pEGFP-CLEC16A-WT and Δ19 to the retromer component VPS35 was confirmed on immunoblot 48 h after transfection with pEGFP-CLEC16A-WT, pEGFP-CLEC16A-Δ19, or GFP, followed by immunoprecipitation. d Immunostainings on HEK293T cells treated with siCTRL or siCLEC16A siRNAs 48 h after transfection. Cells were stained with antibodies against EEA1 (green) and TRIM27 (red). e Quantification of d, unpaired t test with Welch’s correction (n = 2 experiments; n = 12–15 fields/section, > 150 endosomes per field counted). f Immunostainings on HEK293T cells treated with siCTRL or siCLEC16A siRNAs 72 h after transfection. Cells were stained with antibodies against TRIM27 (green) and phalloidin-alexa 647 (red). g Quantification of f, unpaired t test with Welch’s correction (n = 3 experiments, n = 10 fields/section, 3–5 regions per field analyzed). All scale bars in this Fig. represent 1 µm. **p < 0.01, ****p < 0.0001\n\nFigure 4: Figure 4. Quantification of autophagy and mitophagy in clec16a crispants. a Acidic compartments stained with LysoTracker in the clec16a crispants and control injected embryos at 5dpf. Scale bars indicate 50 µm. b Quantification of acidic compartments > 5 µm in the optic tectae of the clec16a crispants brain quantified. Unpaired t test with Welch’s correction (n = 2 experiments, n = 25 fish per group). c LysoTracker staining (magenta) in slc1a2b:Citrine background (green), visualizing radial glia. Scale bars indicate 5 µm (number of fish: n = 12; clec16a crispants n = 13, 2–3 cells per brain were counted, N = 2 experiments). d Quantification of c, unpaired t test with Welch’s correction. e LysoTracker staining (magenta) in mpeg1:GFP background (green), visualizing microglia (n = 11 fish for both groups, 3–4 cells per brain were counted, N = 2 experiments). Scale bars indicate 10 µm. f Quantification of e, Mann–Whitney U test. g, h Single-cell embryos were simultaneously injected with a crRNA targeting clec16a + CLEC16A-WT or CLEC16A-Δ19 mRNA or H2O (number of fish: CLEC16A-WT n = 12, CLEC16A-Δ19 n = 12, H2O n = 11, 2–3 cells per brain were counted, N = 2 experiments). Scale bars indicate 10 µm, one-way Anova. i MitoTracker staining of the right hemisphere midbrain region. j Quantification of i, total high MitoTracker intensity area was quantified in the radial fibers. Scale bars indicate 10 µm (n = 10 fish for both groups, N = 2 experiments, unpaired t test with Welch’s correction). k Intensities of the Parkin protein band were quantified from immunoblot (Supplementary Fig. 7a) and corrected for total protein (Supplementary Fig. 7b). The average relative Parkin abundance of the two control samples was set as a relative abundance of 1 (unpaired t test). *p < 0.05, **p < 0.01, ****p < 0.0001\n\nFigure 5: Figure 5. Graphical abstract of CLEC16A interaction with retromer and TRIM27. Left panel shows normal interaction of CLEC16A with early endosome, retromer, and TRIM27. Under physiological conditions, CLEC16A protects from autophagy and regulates mitophagy. Right panel: C-terminus truncated CLEC16A loses interaction with early endosomes, hereby increasing TRIM27 binding to early endosome and F-actin polymerization. CLEC16A dysfunction leads to dysregulated autophagy and accumulation of unhealthy mitochondria"
      }
    ]
  }
]